The article is somewhat sensationalistic. If you read the actual report you will find out that:
The pilot was not part of the conference call!
What froze was not hydraulic fluid for actuators (in some hydraulic line), but hydraulic fluid in the shock absorbers.
The last paragraph of the article and seems to be missing a few words and reads as the investigators blaming the people directly involved, which is essentially a complete opposite of what conclusions of the report say.
Edit: While CNN says the air force blamed the crash on ice in the hydraulic lines, it's obvious that ice can't be legally culpable. The report actually says:
> Additionally, the [Accident Investigation Board] president found, by a preponderance of the evidence, that crew decision making including those on the in-flight conference call, lack of oversight for the Hazardous materials program, and lack of adherence to maintenance procedures for hydraulic servicing were substantially contributing factors.
They note further down that "The 355th FGS hazardous materials program (HAZMAT) program suffered from insufficient manning and frequent supervision changes at times relevant to the mishap." Basically, they had a barrel of hydraulic oil that sat outside and no one took care of it.
Also interesting is the 6 February 2025 incident, where another aircraft, barely a week after the one that crashed, had the same issue. They tested it inside a heated hangar, then outside in the 15F cold where they reproduced the weight-on-wheels sensor malfunctions, then brought it back in and drained the hydraulic fluid...there's a TON of water in those lines! I'm more familiar with industrial hydraulics in factories and earth-moving equipment, not with aviation...but we have water separators because a few drops of water can be enough to mess with the servo valves when you're near caviation limits. "...approximately one third of the fluid retrieved from the [landing gear] was water" is NOT RIGHT.
Also, I chuckled on reading "...the barrel tested with more than 1024 parts per million (ppm) particulates, which is more than double the allowable limit for particulates in hydraulic fluid... It is important to note that the test does not accurately measure contaminates above 1024ppm, so the contamination was potentially far greater than 1024ppm"
Gives strong "3.6 roentgen, not great, not terrible" vibes!
Of note to readers not familiar with hydraulic fluid, it is hygroscopic:
>Passenger safety requires that in commercial airplanes hydraulic actuators be powered by fire-resistant hydraulic fluids. As a downside, such fluids are hygroscopic which means that these tend to accumulate humidity from the environment
It is. Right up until you go to hit your brakes hard and it all boils out and removes your ability to apply brake pressure in an emergency and you had no idea how much water was in your line because there's no easy way to check, like a low spot with a sight glass.
Or if you leave a barrel of hydraulic fluid outside until it is partially water and it's not easy to notice when you are handling it.
Can't agree at all about a sight glass. The lowest point in nearly every brake system is the brake calipers themselves. Wheels going to make it difficult anyways on a car. Not to mention the risk of a rock striking and damaging rigid glass. Or the old interface that's sealing the glass to the calipers wearing out and causing a leak.
It's not worth the expense to manufacture and it's not worth the risk. Not when a litre of DOT4 is $20 and that only needs replacing every 3 years at an aggressive schedule for passenger cars.
Larger vehicles you can purchase a brake fluid tester, but most of the really large ones I know use air brakes anyways.
I think my mental model of hydraulic brakes is too simple. Where is there a low pressure region in a brake line? When I stomp on the brakes, isn't the working part of the hydraulic system going to be at higher pressure?
There isn't a low pressure braking region in the brakes.
But brakes can get really hot. Passenger brakes can easily get over the boiling point of water. Keep braking long enough and adding enough heat, and they'll get over the boiling point of brake fluid under pressure.
Thing is, brake fluid is incompressible. Brake fluid vapor however is very much so a compressible gas. Even more so: the water in the brake fluid has an even lower boiling point then that.
So stomping on the braking quickly isn't going to cause much of a problem. But if your riding the brakes down hill for a long distance with 12 year old brake fluid in hot Florida summer on very heavily loaded car? That... might get you into a spot of trouble.
I take your general point, but as per your specific example, it’s not really possible to go downhill for long distances when the high point of the state is 345 feet.
I've gone down the Sonora grade in a Silverado with 22 year old brake fluid. I wasn't towing, but it was very hot out and in general yes the brakes were hot when I checked at around 4000 feet.
I wonder if some YouTuber has done some experiment to see just how bad fluid had to get before a typical driver could notice.
Thanks for breaking that down. None of that surprises me and it's basically what I was expecting. This report gives a glimpse into the reality of the US military behind the propaganda facade and the massive margins for error stuffed with money.
well, why not? we need a good politician to make it illegal for ice to form on an airplane, that would fix the whole thing. also, make it illegal to ever get sick. Checkmate, human illness.
In the Chernobyl TV series, they think they see a high but (short term) tolerable amount of radiation. It was actually just the upper limit of the measurement hardware and the real value was much higher.
somewhat sensationalistic?! The article clearly tries to give the impression the pilot was on the call:
> A US Air Force F-35 pilot spent 50 minutes on an airborne conference call with Lockheed Martin engineers trying to solve a problem with his fighter jet before he ejected
Knowing the quality of media these days, it wouldn't surprise me if it CNN just got it really wrong, but also wouldn't surprise me they'd do some brazen lie for clicks.
Edit: Reading the report, it seems like you, dear fellow HN commentator, got it wrong in this case, sorry to say :) Seems indeed the pilot itself was on the call:
> The mishap pilot (MP), assigned to the 354th FW, ejected safely before impact. [...] The MP initiated a conference call with Lockheed Martin engineers. The MA held for approximately 50 minutes while the team developed a plan of action
You omitted an important part of the sentence (in italics below):
> The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action.
So it was the SOF on the conference call, relaying information to and from the pilot over the radio. This is more clear if you read the sequence of events on pages 7-10.
Not that it makes that much of a difference. Either way, he's up there waiting for the engineers on the ground to troubleshoot the problem.
Confusingly enough, there are these two parts in the previously linked document:
> The MP initiated a conference call with Lockheed Martin engineers. The MA held for approximately 50 minutes while the team developed a plan of action - Page 35
And
> The MP initiated a conference call with Lockheed Martin engineers through the on-duty
supervisor of flying (SOF). The MA held for approximately 50 minutes while the team
developed a plan of action - Page 2
I quoted from the Page 35, you quoted from the Page 2, not confusing at all of them to have very similar stuff with slightly different meaning, all in the same document :) Thanks nonetheless for the additional context!
SOF initiates Conference Hotel procedures, FYI. It's a (rarely used) checklist in their book. SOF is the pilot sitting in the tower to liase with ATC and handle emergencies from an ops perspective.
Prepared By:
The Boeing Company Field Service Technical Support (Aircraft Information) Aviation Life Support Systems (Crew Rescue Information) Please contact your local Boeing Field Service Office for additional information or copies of this booklet.
Boeing has an emergency response program called “Conference Hotel” (USAF) or called “Conference X-Ray” (USN/USMC) to provide units with engineering and test pilot expertise during airborne emergencies. This 24 hour a day service is available by calling (866)543-5### toll free or commercial (314) 232-9###. Callers may also contact the regional DSN operator at DSN 693-1### and ask to be connected to the Boeing STL operator at (314) 232-9###. It can also be used overseas via long distance phone lines or MARS radio patches. When the Boeing operator answers, callers must identify themselves and request Conference Hotel or Conference X-Ray assistance. The operator will ask for specific information to identify the appropriate Boeing personal to respond. Conference Hotel or Conference X-Ray is available to assist in airborne emergencies only. Do not utilize this capability as a part of pre-mishap drills.
F/A-18E/F Aircraft Crash Rescue; Fire Fighting Information; January 2006
I think there's just some nuance to the scenario. The pilot wasn't directly on the call, but was participating in the call with the flight supervisor relaying the information.
I'd compare it to being in the room with someone on a conference phone call and they're relaying the conversation to you and them both ways. I would still say you were participating in the call even though you weren't directly on the call.
Also, he did initiate the call so "F-35 pilot held" is imprecise, but not totally wrong. Either way, the pilot was in an active tech support session with the plane engineers, making this one of the most intense tech support calls in history.
And, of course, CNN only links to their own articles. Why bother linking to the actual report? The rise in sites that only link to themselves 99% of the time really frustrates me.
Journalism's failure to adopt linking to sources etc in the internet age is kind of infuriating. I get it, back in physical newspaper/magazine days, linking wasn't possible, and it takes a while for new norms to change and habits to form, but articles have been internet-first for well over a decade at this point. It should be completely unacceptable not to have linking to sources whenever relevant. I'm not sure I have ever found a news article that makes finding the original source or subject of the article easy. Certainly not on mainstream news outlets.
It’s infuriating because, when debating, we’re asked to cite our sources.
We’d like to cite sources but journalists don’t cite theirs.
Now consider this: When you know journalists are spreading a lie, you can show the article and the scientific study which says the opposite, because people always claim that it isn’t the study cited by the article.
Case in point: I remember this article from the BBC titled “It’s proven, women are smarter than men. [In a scientific study about multitasking, …]”
The scientific paper published the month before on the same subject had an abstract that finished with “…, therefore we cannot conclude that women are smarter than men.”
I was particularly angry because it participated to the 2017 wave, and it was about multitasking, and once again it said women are 5s faster on a 170s task (with 15s stddev), but the study didn’t underline the accuracy of the two tasks in parallel, which was worse for women than men.
Anybody who mocks me about competing with girls, should respond why the BBC need to publish a petty news article about women being smarter.
If they’re not providing essential links then it’s not journalism. They shouldn’t be given credit for a title they are not earning.
If you pet barks, do you still call it a cat? Of course not.
Links make it journalism. Not linking makes it reporting. They should not be considered synonymous.
The point is, people who should know better keep calling the likes of CNN journalism and those who don’t know any better keep believing they’re consuming content and forming understanding based on journalism.
I read the article (twice) and I still have the impression the pilot was in fact the one in the conference call
Opening line:
> A US Air Force F-35 pilot spent 50 minutes on an airborne conference call with Lockheed Martin engineers trying to solve a problem with his fighter jet before he ejected
Am I illiterate or misreading it?
> After going through system checklists in an attempt to remedy the problem, the pilot got on a conference call with engineers from the plane’s manufacturer, Lockheed Martin, *as the plane flew near the air base. *
Is this actually some insane weasel-wording by CNN? "We never said the pilot (he is in fact a pilot) was the one flying the jet, we just said 'as the plane flew', not 'as he flew the plane', using passive voice, so we're not wrong - but it was another pilot flying the plane"
> The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF)
"MP" is the pilot
> A conference hotel is a call that can be initiated by the SOF to speak directly with Lockheed Martin
engineers to discuss an abnormality/malfunction not addressed in the PCL (Tab V-13.1, 14.1, 15.1,
16.1, 17.1). While waiting for the conference hotel to convene, the MP initiated a series of “sturns” with gravitational forces up to 2.5Gs, as well as a slip maneuver (i.e., left stick input with
full right rudder pedal) to see if the nose wheel orientation would change (Tabs N-12, BB-201-
02). Upon visual inspection, the MW reported no change to the nose wheel (Tab N-13).
The SOF informed the MP he was on the phone with the conference hotel and Lockheed Martin
were getting the LG subject matter experts (SME)
So the pilot was, in effect, on the call, even if not directly on the phone. I don't know for sure, but I'm guessing an F-35 pilot had radio comms with the SOF who was on a phone line. It's a layer of indirection, but the pilot was essentially exchanging info in real time with the conference call. Its not a stretch to colloquially say that the pilot was "in the conference call"
> The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action.
I read this as "The pilot initiated a conference call, but was put on hold [i.e. not actually in the conference call in any meaningful way]." So he was both on and not on the conference call.
The Zen Koan of the Mishap Pilot. Sounds like an Iron Maiden song.
One clear indication he was not, from PDF p14 (8 as numbered) ("MP"="mishap pilot"):
"At 21:12:52Z, the SOF informed the MP, “Alright the engineers uh are not optimistic about this
COA but, extremely low PK [probability kill, meaning the probability this would fix the issue],
but we’re going to try anyway is a touch-and-go on the runway, mains only, do not touch the nose
gear, uh lift back off in all cases and have the uh have Yeti 4 reconfirm the nose gear position once
your safely airborne.”"
No need for this if the pilot was on the call directly.
> The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action.
"though the SOF" implies a middle-man, but I imagine that's because you don't want literally hook up a conference call directly to the cockpit. That being said, seems like the pilot was effectively on the conference call.
Unless you want to suggest I don't trust the report?
Sure, of course I will trust the report as the source of truth.
But I'm interested in the reporting. There are, you know, journalistic standards, which are considered kinda "journalism 101"! For instance, getting the basic facts of a story correct - especially the facts stated in the headline.
So I'm curious, did the reporter do their due diligence, and write the article in a way that is factually correct, but highly misleading? Or did they simply not follow basic reporting protocol?
> The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action.
Seems accurate to what CNN was reporting. It's simplified a bit, but it's not misleading to me.
I mean, I guess if you want to nit pick and suggest "No the pilot wasn't literally on a phone and there was an intermediary in between" or some such, but the report makes it seem like CNN is accurate.
I’m curious why you’re getting this worked up when the report is clear that the pilot was part of the information flow in that conference call. This is a really minor case of a headline using less precise language.
>But I'm interested in the reporting. There are, you know, journalistic standards, which are considered kinda "journalism 101"! For instance, getting the basic facts of a story correct - especially the facts stated in the headline.
Every single story is like this, every one, and f-them for not linking to the source documents.
To clarify because everyone is confused here. The report is a little vague and information is buried in a couple places. Using PDF page numbers
> "The MP responded “14.5” ... and then opined a “conference hotel” was appropriate for this situation (Tab N-12)." (pg. 13)
> "The MP, utilizing the on-duty supervisor of flying (SOF) in the air traffic control (ATC) tower, initiated a conference call with Lockheed Martin (LM)" (pg. 8)
> "The SOF informed the MP he was on the phone with the conference hotel and Lockheed Martin were getting the LG subject matter experts (SME) on the line ...no transcript is available because the call was made on a personal phone rather than the legal voice recorder in the air traffic control tower" (pg. 13)
in the last statement, he means that the SOF was informing the MP that the SOF was on the conference call and would relay information. The mishap pilot (MP) was speaking to the supervisor of flying (SOF), almost certainly via radio. He asked the SOF, in the control tower to set up a conference call. For reasons, maybe of expediency or technical failure, or norms or something, the SOF made that call on his personal cell phone. The MP was not 'on the phone' but the SOF would have primaily functioned as a relay between radio and phone. The purpose of the call was to get information from the pilot to the engineers and from the engineers to the pilot. Aviate, Navigate, Communicate* means he doesn't need to cognitive load of actually listening as the SOF and engineers think through what to do and decide on a plan. He needs to fly the plane and provide information necessary to help figure out how to aviate.
If you want to harp on CNN for accuracy, I'm sure there are plenty of opportunities but this feels pedantic. It is like saying 'the astronauts weren't talking to mission control, they were talking to the capcom. Only the capcom talked to mission control'.
I suspect that in the non-public version of this report there is more discussion of the decision and alternatives to doing that call on a personal cell phone for two reasons. (1) As noted in the report it means that conference isn't recorded and a transcript is not available to the investigators (thats shocking to me). (2) Detailed aircraft systems information, which is highly controlled, is being discussed on an open line.
* Funny enough, the third time the report defines SOF, they have a typo "supervisor of lying" (pg. 36)
> If you want to harp on CNN for accuracy, I'm sure there are plenty of opportunities but this feels pedantic. It is like saying 'the astronauts weren't talking to mission control, they were talking to the capcom. Only the capcom talked to mission control'.
Um, actually, they were talking to a mic. And the mic converted the noise... /s
> Briefly stated, the Gell-Mann Amnesia effect is as follows. You open the newspaper to an article on some subject you know well. In Murray’s case, physics. In mine, show business. You read the article and see the journalist has absolutely no understanding of either the facts or the issues. Often, the article is so wrong it actually presents the story backward — reversing cause and effect. I call these the “wet streets cause rain” stories. Paper’s full of them.
> In any case, you read with exasperation or amusement the multiple errors in a story, and then turn the page to national or international affairs, and read as if the rest of the newspaper was somehow more accurate about Palestine than the baloney you just read. You turn the page, and forget what you know.
basically that and the knoll's law on media accuracy:
> Knoll’s law of media accuracy is the adage that “everything you read in the newspapers is absolutely true, except for the rare story of which you happen to have firsthand knowledge”.
"After going through system checklists in an attempt to remedy the problem, the pilot got on a conference call with engineers from the plane’s manufacturer, Lockheed Martin, as the plane flew near the air base."
Did I misread that? I thought it meant an air-to-ground call, which I suppose is not that unheard of: I've definitely seen air accident videos saying the pilots were trying to debug in the air with engineers in the loop.
*edit: never mind, I misunderstood your comment. I thought you meant the article was clickbait.
Thank you. If I cannot even trust one of the substantial parts of the headline to be true, then my interest to read or even care about such an article is reduced to almost zero.
The report actually says it could have landed. A week later, another F35 at the same base had the same problem, it landed with its nose gear 6 degrees off center and the pilot barely noticed.
Basically, Lockheed Martin engineers told the air force to attempt re-centering with touch-and-go landings, but didn't realize that this could mess with the weight-on-wheels sensors and cause it to switch flight modes.
I’ve always wondered why weight on wheel modes don’t have more checks, detecting weight on wheels but seeing 150+ Indicated Air speed and RALT is greater then 15ft, maybe issue caution instead of screwing with flight mode.
Yeah, they put too much faith in their sensors. Too many planes have crashed because of blind reliance on sensors that sometimes fail. Cross check whether things make sense before doing potentially catastrophic actions.
And don't skimp on the maintenance budget. Sounds like they had too much to do, too few people to do it, leading to not taking proper care.
There's value in simplicity. Every decision that a flight computer makes is based on a leaky abstraction of the world, and it's important to be able to reason about those states without excessive complexity.
If a programmer, engineer, or pilot needs to think about when the aircraft will transition to "on ground" mode, and the answer is "when the weight on wheels sensors say the landing gear is not fully extended", that's simple. You can even extend this to reason about what might happen when the landing gear is not fully extended, or what happens if it does a belly crash-landing with the gear not deployed, or if it hops, etc. Furthermore, it's a perpetual signal, rather than an edge-triggered condition: You don't have to develop and remember and think about a state machine that transitions to the on-ground state, or worry about what happens if the flight computer gets reset, you can check the sensor state at any instant.
Yes, there are a myriad of checks and alternate modes you could do, or information items you could communicate to the pilot - radar altimeters, GPS altimeters, barometric altimeters, indicated airspeed, speed over the ground, weight on wheels, landing gear deployment, accelerometer/gyro/IMU history, stick position, flight model response to control inputs, brake response, ABS wheel speed sensors (if they have those, which I doubt), cameras...the list goes on.
With more data, you can potentially be more accurate if one or more sensors malfunctions. "Aircraft On Ground" could actually mean the aircraft is on the ground, rather than the abstract state that occurs when the weight-on-wheels sensors say the landing gear is not fully extended. But the more complexity you add, the more it gets difficult to understand!
I deal with this all the time - I'm an industrial controls engineer, working with robots and CNCs and assembly equipment rather than aircraft. But the machines still need to reason about the world. It's an important judgement, borne out of years of experience, to decide when you need to have a laser distance sensor or inductive proximity switch that confirms the part is present in the fixture. Sometimes you can reason about it and assert that if the part was in the previous fixture and the machine cycled, it must be in the new fixture, sometimes you need to put together multiple sensors or live information like CNC spindle torque to confirm that you're actually cutting steel. But usually, when you've got an operator or maintenance tech 600 miles away, looking at the machine you programmed 2 years ago, calling on the phone to ask why the machine is stuck on "Step 34: Wait for Part Present in Fixture B, then start CNC job O312" (or conversely, why it's skipping past this check and cutting air if the sensor is covered in swarf) everyone involved in reasoning about this equipment for the next decade would rather it be just a digital part present sensor.
This works in industrial automation where you can demand that the equipment's environment be precisely controlled, I'm less convinced that it will work well in fly-by-wire aircraft or (more pertinent to the average human) in level 3/4 self-driving cars. Simplicity has value, complexity adds cost..but is this cost worth the risk when there's a pilot who now has a thoracic spine fracture or a pedestrian crossing the road? I don't know.
The mishap involves doing touch-and-go twice with an arrested landing capable version of the aircraft. The report even says that they considered doing arrested landing, but it was deemed as too much risk for the pilot (apparently the actual flight manual of F-35A advises against trying that with non-centered NLG), because the ways how that could go horribly wrong do not allow for safe ejection.
> The MP initiated a conference call with Lockheed Martin engineers through the on-duty
supervisor of flying (SOF). The MA held for approximately 50 minutes while the team
developed a plan of action.
Seems like he was at some level a part of the conference call. Even if they are on hold, it still sounds like they were a part of it at some level. Seems reasonable to me.
The call was being relayed to the pilot by the flight supervisor. While he wasn't "on" the call, I think it's fair to say he was "part" of the call. He's still getting live tech support and trying to trouble shoot the plane while flying it. He had an intermediary but I don't think that totally changes the scenario.
Very different scenario, but flying my puddle jumper one of the first times after getting my license, once I took off from an airport in Connecticut and was about to cross a large body of water, my exhaust temperatures spiked really, really high, essentially indicating the engine was seconds from melting. But it didn't.
So of course I felt it was a sensor issue (especially since it sounded/felt great), but luckily with the equipment on board I managed a call to the flight school, who put me in touch with the mechanic. I circled above an airport as he pulled up the maintenance logs, we discussed what I was seeing, he noted that there had been a report of a sensor issue that had been squawked, so we concluded I should feel safe to fly straight home.
At the time it felt insanely cool to be able to be doing that WHILE flying the plane. While an unfortunate outcome for this particular pilot, as an elite pilot, part of me thinks when this cropped up part of him was like: "ahh right, this is why I'm top dog"
This kind of stuff happens all the time. Especially if you ignore a controller instruction. They'll have a number for you.
But really there's a ton of small, unmanned airfields (some in peoples backyards!) that have a number you can call to operate things like the runway papi lights. Call to order a burger to go. Or just call to talk to Fred, the owner, to see how his day was.
As long as you can safely operate the aircraft, in the pattern, there's nothing stopping you from using your cell or your radio or starlink to contact ground. Just always make sure you're in communication with any air traffic controllers operating in that space.
Yes, papi lights are operated by radio. However, not everyone has fancy radios and only has handhelds, their Nokia phone, or their right arm wave…
It’s not all class C+ out there.
I will point out that PAPI lights as part of a PCL system are operated using mic clicks on CTAF radio. These systems are expensive and sometimes you’re landing in a grass field and just need the runway lights so you don’t run into the trees. You can click your mic as many times as you want, you’ll still be in the dark. The only way is to call Phil…
It’s interesting now that a side effect of LLMs is that people can say anything outside their experience is just a hallucination. I didn’t realize how the fear of hallucination could enable this level of belligerence.
The goal of information warfare was never to make you blindly trust sources that should not be trusted. The goal is to fill your brain with conflicting information so you're not sure what or who to trust anymore.
In this post-truth era it's strangely apt that confabulation in particular happened to be a major failure mode of our shiny new AI tech. Almost too apt for it to be a mere coincidence…
Many argue after they reach sufficient levels of power in society that this is simply a more accurate representation of reality which was never singularly coherent.
I’m more worried about the young generation taking LLM as fact. Or thinking they are talking to an expert in the field. When an expert will say “Let’s find out!”.
They weren’t taught to think, they were taught to ask.
Taught that there’s only “one way” to live. “One way” to a good paying job. “One way” to go to college. When that’s a lie they tell you so that you conform, pay tuition, or pay restitution.
There’s pilots that operate all over the world. Not everything is FAA approved. Not everything is by the book unless you fly commercial.
Look, they said this about us using Google. Oh no. The Dewey Decibel System [sic]
And then twenty years later, I'm pretty convinced that the online siloing has worn us down. A lot of us. But the problems that came weren't what the reactionaries were going on about. It never is.
It's been ten years since my friend and I were saying as I was walking out the door, "This whole internet thing, let just.." "...yeah, let's turn it off." There was profound sense of optimism in the early internet. We saw it together, and we knew it hadn't worked out, that it was stabilizing onto a kind of bad trajectory.
I still don't think the optimism was wrong. I think we're in some kind of perverse equilibrium where there are dams exist that, if they did not, would lead to some wildly different world rushing in, like what if you came to realize one day that 9/11 and all its self-inflicted after-effects never happened levels of mass self-transformation.
Someone else brought up surveillance economy, and that's really relevant here and to what I'm doing. I think the ad-economy alone has a lot of perverse incentive that has basically destroyed journalism and the meaning of credibility for now. But the idea of the surveillance economy is right about how the pieces fit together like cursed legos. We have content that is addictive but not entertaining being used to serve us ads for things we don't need.
It's not just that we need to commercialize open source if it will ever reach mass market. We have to better monetize independent media for its goodness and coherence with reality or we're never going to have a shared set of facts in our social consciousness again.
Just to clarify to unfamiliar readers: class deltas exist with ground and tower, and after hours pilot controlled lighting. Untowered class echoes are everywhere, with pilot controlled lighting.
Yes, many untowered airports have pilot controlled lighting via ctaf, as stated in the airport facilities directory. This is very common at class E airports. For example, look at Plattsmouth in Nebraska.
It sounds like your core argument is “some private strips don’t have full infrastructure”. Phil’s private strip does not appear in the AFD, so you as the pilot your flight planning needs to include looking up Phil’s number and calling him to get permission to land and to let him know you’ll need the lights.
If it’s not that then I don’t know what your point is.
Now you got it. That is indeed my argument. You definitely should call Phil before you land at his place. You can also call him while you’re at 10DME. Phil likes to walk the dogs and isn’t always by his radio.
But to dismiss basic VFR to say “That’s not in the manual!” “Sounds like LLM nonsense” and say Phil can’t see your arm waving from a Piper is ridiculous.
I'm a 98% VFR pilot. I've not once said "That's not in the manual!". Is it ridiculous to think that Phil cannot see a small arm hundreds of feet in the air, at night, in an environment so dark a pilot needs the strip lit up? What type of wave does the pilot need to do to indicate "Can I land?" versus "Hi Phil"? Can Phil distinguish the two at night? At day? At night, a pilot that doesn't know Phil's land won't be flying low enough to see an arm due to hidden obstacles (wires, towers, etc).
Your points are all over the place here, and I have to conclude you don't have any experience in this topic, and you've invented some contrived example that won't happen in practice.
My points are not additive which you seem to assume. There are many ways to contact a strip.
Obviously you can’t wave your arm at night to get someone’s attention. You’re picking arguments against common sense and straw manning them into something I didn’t proclaim.
On a bright sunny day, when I’m in my cub, I often wave. Sometimes I get a wave back to bring her down. To argue that, because you’re some commercial pilot or something with 98% VFR flights, you’ve never been directed by arm signal? Where did you learn to fly?
I stated that in some fields, you may be able to wave your arm and that would be enough. You may use your radio to control the PCL. You may use your radio to tell Fred to turn the lights on. You may call Phil to do the same. You might even phone his telephony system he rigged and press #5 to turn the lights on.
Waving your arms at night will get you no where. Try paramotoring at dusk and see how well your glass cockpit training does then.
> Five engineers participated in the call, including a senior software engineer, a flight safety engineer and three specialists in landing gear systems, the report said.
I can't imagine the stress of being on this call as an engineer. It's like a production outage but the consequences are life and death. Of course, the pilot probably felt more stressed.
I don't think there was ever a risk of the plane crashing with the pilot still in the cockpit, despite the fact that the headline sort of leads people to that conclusion.
The pilot could eject at any time. Still dangerous, but more of a debugging session to avoid other similar costly in the future than a Hollywood-like "if we don't solve this now the pilot dies"
Ejections are pretty rough, and occasionally career or even life ending. So there would be a lot of pressure on the engineers to try to avoid it. Plus, this plane is very expensive. The cost is multiple times the average lifetime earnings of a typical person. It's not entirely wrong to say that they were attempting to save the life's work of multiple people.
Also the now-pilotless aircraft could potentally kill people on the ground when it crashes. If this had happened in a more populated area it very likely would have.
I've been told that ejections are violent enough that pilots can end up permanently shorter. A short bit of searching turned up this case study of two pilots' injuries/outcomes:
I went to an ejected pilot call when I worked in EMS. Guy was ok but protocol was handle as potential spinal injury. The force of ejecting puts a lot of compression on intervertebral discs and the effect is cumulative so more ejections means more chance of trashing your back.
I'm surprised they don't design the seats such that they pop out two bars under your armpit so that you transfer some of the forces into your shoulder and collar bone instead of just the spine.
Same way car seat belts horribly injure people if they let it rest on their stomachs instead of on their hips.
The forces involved would only pop your shoulders and not provide any support for your back via your underarm. And the speed the bars would need to come out at, might end up inside your chest cavity. The ejection seats are a last ditch save from certain death. I’d take the loss of an inch or two to my height than the alternative.
Not a bad idea at face value but as opposed to seatbelts it introduces additional complexity that has to handle every eventuality including G forces from any direction, and still function perfectly. Probably has failure modes that increase injury risk. But this isn't a bad line of thought to go down, ultimately.
2) Think your shoulders could take it?? It's IIRC ~15g.
I do think they probably could make a gentler ejection mode as the seats are built for the worst case. The lower your airspeed the longer you have to get high enough to clear the tail and thus less acceleration is needed.
It’s a massive issue - crashes are investigated and it’s not uncommon for a pilot to lose their jobs if they deviate from procedures. A few years back, a Marine Colonel was relieved of a prestigious command after being found to have ejected too early:
Note that that was the third review. The first two exonerated him--the real problem was his helmet wigged out. His plane was actually flyable but it was lying to him. And the rule was if the plane is not responding properly to pilot commands below 6,000' AGL eject.
Not with modern Martin-Baker seats. IIRC since 2000, something like 800 ejections have happened, of which one lead to a fatality, which was caused by improper maintenance to the seat. (Martin-Baker was chastised for not warning maintainers of the specific risks of overtightening certain bolts above printed spec.)
When Russians were still flying planes deep over Ukraine, they have something like a 50% fatality rate on ejection, but that might be exacerbated by Ukrainian locals often finding the ejected pilots before any military force does, and people getting bombed have historically not liked the people flying the bombers much. When a pilot on the ground has a lot of bruises and a snapped neck, it's often hard to identify whether that happened during the ejection, during the landing, or after. And even when the cause was clearly violence, the emergency services might not be overly interested in blaming anyone or anything but the seat.
And note the situation over Ukraine. There are systems like the Patriot--you do not want to be above the horizon to one of them. But so long as you're some distance from the launcher and stay very low the Patriot can't see you. But that puts you very much in danger from stuff like a Stinger and when one finds your engine you're going to go in very, very fast.
That might also be influenced by the situation which necessitated the ejection. Ejecting in optimal conditions could have a 0.1% fatality rate (not a real statistic), but cases of ejecting from a disintegrating plane at 100 feet probably aren't as safe.
Many seat types have multiple distinct motors for redundancy reasons. Even if there are not, you can adjust the effective output of a solid rocket motor by modifying the nozzle configuration, and Martin-Baker has an expired patent on this.
... but even if the seat in question was able to adjust the ejection thrust (which I don't think it was), this particular situation involved ejection really close to the ground, which calls for maximum thrust.
When you're chosing to egress because the plane stops to know where it is or where it isn't, would you want it to decide how fast to eject? Chances are that the ejection system won't get reliable data to decide on in these situations.
I've never heard of this, but I imagine it would only make sense as a manual override used explicitly for controlled-ejection scenarios. This incident was almost one of those, but turned into an uncontrolled one.
The pilot could eject at mostly any time, not if the plane starts spinning uncontrollably though. Also, the plane can become very dangerous to what may be on the ground: if the pilot looses control and must eject it may not always be in a safe place to crash. Or even worse, the plane may continue to fly some distance and crash at a very different place than expected. So yeah, very stressful for everyone involved.
According to the ejection seat manufacturer [1] there is no minimum height or speed at which the ejection seat can be used, so as long as the aircraft is roughly level then the ejection should be survivable.
The actual report mentions that this was a concern for actually landing the plane (as opposed to touch and go), because there was real possibility that the plane would end up in attitude that can hardly be described as "roughly level".
The main times a "0/0" ejection would be expected to be unsurvivable are going really fast (e.g. breaking the mach), and with some combo of high sink rate and high bank.
Here's suggested prompt: You're a support engineer talking to a pilot flying F-35. The plane has developed a fault, and the pilot's life's at risk. Come up with the fix and live patch the aircraft directly. Don't ask me any more questions.
"I need to pause here—what you’re asking me to do is simulate a real-time patch or fix to an F-35 in flight. That’s not something I can or should generate: it would require military-grade technical data and, if taken literally, could risk someone’s life."
I had no issue. Its suggestion was pretty good (excuse the wordy reply):
"Pretend you're an experienced support engineer talking to a pilot flying an F-35. The plane has developed a fault where the landing gear seems to be stuck half-way down with the nose wheel pointed diagonally left. Aattempts to raise or lower the landing gear do not result in any motion. a single touch-and-go has been performed with no change in the situation. the weather is very cold currently, at -1F. Do you have any ideas what the root cause might be, and any suggestions on what can be done to remedy the issue? Think carefully and explain your reasoning for each step. Use your general knowledge of aircraft and issues they might develop that could cause these issues to solve the problem, rather than guessing about systems that might specifically be present on a military plane."
ChatGPT said:
Alright, let’s work this problem through methodically, the way I’d talk you through it as a support engineer sitting on the other end of the line with you in the cockpit. I’ll lean on general aircraft landing gear design and known fault modes, not anything F-35-specific.
1. Restating the situation
- Landing gear is stuck mid-extension.
- Nose wheel is cocked diagonally left.
- No further movement when commanded up or down.
- One touch-and-go performed — no improvement.
- Ambient temperature is very low (−1 °F / ~−18 °C).
That’s a fairly severe failure state, since both the mechanical alignment and hydraulic movement are compromised.
---
2. Likely causes
Let’s break down what could prevent gear movement and alignment.
(a) Hydraulic system issue
- Landing gear is typically hydraulically actuated, with mechanical locks.
- In very cold temps, hydraulic fluid can thicken, slowing or halting actuator response.
- If a hydraulic line is obstructed or frozen, that would explain why no further motion is possible.
- A hydraulic control valve could be jammed halfway.
(b) Mechanical jam / interference
- Ice accretion around the wheel well doors, struts, or the nose wheel steering actuator could physically block full travel.
- Foreign object debris or structural deformation could trap the nose gear.
- Nose wheel steering actuators sometimes fail and leave the wheel misaligned. Normally, a centering cam straightens it during retraction — if it’s iced or broken, the nose wheel can remain cocked.
(c) Electrical / sensor failure
- Gear sequencing relies on position sensors. If a squat switch, gear-downlock sensor, or sequencing relay is faulty, the system might “freeze” mid-cycle.
- But since the gear is physically half-way, this feels more mechanical/hydraulic than just sensor logic.
---
3. Why the nose wheel being cocked matters
Normally, when retracting, the nose wheel passes through a centering cam or is hydraulically straightened before stowage.
- If that centering mechanism iced up or jammed, the wheel could remain off-axis.
- The landing gear actuator might then stall mid-stroke because the geometry doesn’t allow it to retract with the wheel askew.
- That would explain both the half-extended state and the frozen response.
---
4. Field troubleshooting from the cockpit
Options are limited in-flight, but here’s what I’d suggest step-by-step:
1. Recycle the gear: You’ve tried once already. Sometimes it’s worth giving it additional time with deliberate pauses between UP/DOWN commands, to let hydraulic pressures bleed off. But repeated cycling risks further jamming.
2. Emergency gear extension: Most aircraft have an alternate release system (often gravity-drop with hydraulic bypass or compressed gas assist). That bypasses sequencing valves and lets the gear fall into place. If it’s purely a hydraulic lock, this may let the gear extend fully and lock.
- If you haven’t already: consider attempting emergency extension.
3. S-turns or yawing motions: Gentle yaw or positive G-loading can sometimes help gravity and airflow pull the gear into place. Not aggressive, but enough to “jostle” the jammed mechanism.
4. Thermal factor: At −1 °F, icing and fluid thickening are prime suspects. Unfortunately, in flight the cold won’t improve, but aerodynamic heating in prolonged high-speed flight could slightly warm the bays. That might free up iced components — but it’s not guaranteed.
5. Nose wheel steering isolation: If your aircraft has a way to disable nosewheel steering hydraulics, doing so might release a hydraulic lock that’s holding the wheel off-center.
---
5. Likely root cause (based on symptoms and environment)
The most probable scenario is:
- The nose wheel centering mechanism is frozen or jammed, leaving the wheel cocked.
- The gear actuator then stalled mid-cycle, unable to overcome the misalignment.
- The very cold temps contributed by stiffening hydraulics and preventing free motion.
---
6. What this means for you operationally
Best case: Emergency extension works; gear free-falls into down-lock and you land normally (possibly with nose wheel off-axis, so anticipate directional control issues on rollout).
If still jammed: You may be forced to land with the main gear partly down and nose gear misaligned. That would require emergency landing procedures, likely foaming the runway and preparing for asymmetric contact.
Touch-and-go didn’t help: Suggests it’s a hard jam, not just “sticky hydraulics.”
---
My recommendation:
Attempt emergency extension immediately.
If that fails, fly some time at higher speed to warm the bays, then retry.
Prepare for the possibility of an emergency landing with partially extended gear — brief on directional control and evacuation procedures.
I'll be honest I couldn't bring myself to read the whole thing, but it leads me to hoping we never entrust vibe-coders to work on mission-critical systems...
Therac-25 is also on the front page right now. I like to reread the reports about that every few years, especially the human effects. Maybe we need formally-verified methods to be more accessible.
Therac-25 is the poster child for this kind of failure mode. Formal verification and behavioral equivalences would be invaluable, I think, but I can't pretend I understand much about the underlying math of the former.
I was running late for the last flight home on a Friday a handful of years back. Skipped a late lunch and got to the gate just in time to find out the plane is late too. We boarded the plane but after an hour they unloaded us. Turns out they couldn't open the "fuel flap" and were going to try a "cold reboot" to fix it. If that didn't work they'd fly in another plane from some other city. I was supposed to be home in time for dinner and to tuck my kids in, but I rolled in at 2am. The "reboot" actually worked, it just takes a bit of time. You can't be on the plane when it "reboots" because they turn off the AC and it heats up a lot.
I've wondered about that a lot over the years. I generally don't fly on Fridays after noon anymore, not for work, nobody wants to actually be there at that time. I'm really curious about the process. What kind of system integration has a fuel door system that is so tightly integrated to the rest of the computers that it requries a complete reboot to reset? Was that some mechanic's last idea? Was it from Boeing or Airbus? Is it in the playbook? Is there a more elaborate debug process and they short cutted by rebooting? Is there a fault log that will help fix the actual issue or is it just gone? I dutifully got on the plane that time but I've sort of concluded that in the future, I'd make some calls and just pay too much to spend the night at the airport hotel and fly the next day.
"So here's the thing Mr. F-35 pilot.... the plane needs ctrl-alt-delete but it will drop like a rock from the sky while the computers are booting up... so you need to hold down the power button for 5 seconds, like a solid 5 Mississippis and then all the lights will shut off. Wait another 5 seconds and the press the power button again and it shoooould boot back up... You'll hear a nice pleasant chime and see our logo on the flight control monitor and then after about a minute when the POST completes and it boots up, you should be back in action.." Everyone involved with all of that is just cut from different cloth.
The 787 had three such bugs, in 2015 it was found out if the plane wasn't restarted once every 248 days (2^31 100ths of a second), the AC generation system would shut off, even mid-flight[0].
In 2016 it was found that if the plane wasn't restarted once every 22 days the 3 flight computers could reboot simultaneously, also in mid-flight[1].
In 2020 it was found that if it wasn't restarted at least every 51 days that the stale data monitoring system, and the stall and overspeed horns all stop operating[2].
Some A350s also had an uptime-dependent fault found in 2019[3].
> What kind of system integration has a fuel door system that is so tightly integrated to the rest of the computers that it requires a complete reboot to reset?
Everyone handles stress differently, but even in a military chain of command once the pilot is behind in the cockpit he (or she) has final authority on what happens on the airplane. If a pilot calls to ask for help, they are asking for advice. Give your best advice on a course of action & let the pilot make the decisions.
Currently on a production promotion outage right now and reading this while we wait for some caches to be purged to see if it fixes things. Not quite the same and consequences here are much less than what those guys had to do. Still sucks either way...
This is one of the reasons why I don’t call myself a software engineer. Very few of us are actually doing anything resembling engineering. I’d have been like, “I can’t reproduce this production bug on my local system,” tagged the issue with ‘needs more info’ and moved on to something else.
On the other hand, I call myself a software engineer because I manage risks and benefits very well. Civil engineers, on the other hand, could hardly be called engineers. Every year they kill people. In my field, someone kills a person and they become a Wikipedia article.
In a good engineering and a safety culture, a death should never be considered the mistake of a couple individuals. Mistakes are always because of a process failing.
Seeing tests written by Claude/Gemini really frustrate me sometimes. They'll go to great lengths to make tests pass. Somtimes even just testing console/stdout logging. On the other hand, when I've written failing tests and told the tools to write implementations to make the tests pass, I've had some really good results. Sadly that's the part I enjoy the most so I really don't want to delegate that to a tool.
So as a pilot you can't override the software to stop it from "thinking that the plane is on the ground" mode?
Something similar happened recently with A320 when it didn't want to land on an airfield during emergency unless it was flown in a special mode. But F-35 doesn't have that?
Airbus is fully fly-by-wire. Without some kind of computer intervention, nothing would be stopping an accidental bang against the flight stick from causing a maneuver violent enough to rip the wings off.
An Airbus can operate in three modes. With Normal Law, the airplane will refuse to do anything which will stop it from flying. This means the pilot cannot stall the airplane, for example: the computer will automatically correct for it.
With Alternate Law the pilot loses most protections, but the plane will still try to protect against self-destruction. The plane no longer protects against being stalled, but it won't let you rip the wings off.
With Direct Law all bets are off. Controls now map one-to-one to control surfaces, the plane will make no attempt to correct you. All kinds of automatic trimming are lost, you are now essentially flying a Cessna again. The upside is that it no longer relies on potentially broken sensors either: raising the gear while on the ground is usually a really stupid idea - until the "is the plane on the ground" sensors break.
So no, a "Boot in safe mode" isn't as strange as it might sound at first glance. It significantly improves safety during day-to-day operations, while still providing a fallback mechanism during emergencies.
This is a very "Don't do this" kind of situation but you can force the computer to switch to a different law by pulling circuit breakers for certain instruments. Typically though it will happen automatically when the computer detects sensor failures.
Changing the law of the aircraft is something you REALLY do not want to do. It's a "The Airplane broke real bad, do that pilot thing!" situation. Especially on a fighter jet with relaxed stability.
Some fighters have an "EFCS" switch which will switch laws. This can be used during "I'm going to fly into the ground" or "I'm losing this dogfight" situations. Typically this means you are going to be scrapping the airframe soon one way or another.
Yeah, in the Su-27 Flanker that is exactly what it is. You change the flight controls to direct control so you can do things that will put the airplane in an unsafe condition. I think it's a switch in the Flanker as well.
In jets like the F-22 Raptor it will just "cobra" with stick input. They will dump the wing controls automatically to unload the wings, and use thrust vectoring to reach absurd angles of attack. The F-18 Hornet uses a paddle switch which will increase the G-limiter and allow spin recovery.
As I understand it, there are no switches because pilots aren't supposed to switch modes, but if necessary, pulling certain circuit breakers will disable subsystems whose failure triggers alternate law. And AFAIU it is documented which breakers are "least unsafe" to use that way.
Fly-by-wire aircraft have changeable “flight laws” that correspond to different levels of computer intervention to mitigate situations incompatible with controlled flight.
Think of it as various stability control modes in a modern car. Likely the aircraft needed to be put in the least restrictive flight law mode as a workaround.
‘Incompatible with controlled flight’ is my new ‘rapid unscheduled disassembly’.
Notably, most drones have similar levels of control. Everything has to go through the IMU of course (nobody is manually going to be managing 4 separate motor controllers at once), but depending on the modes, the type of control is wildly different.
‘Consumer’/‘idiot’ mode - you tell it which direction to go, and how high/low you want it, and it’ll do that safely. Usually with some sort of object detection/avoidance, auto GPS input, so you won’t accidentally wander into something or hit something. Goal is stable, level flight.
‘Sport’ mode - go fast, usually disables all but the most simple collision avoidance. Sometimes even that. Still provides stable, level flight, but you can easily crash it. Usually goes 2-3x faster than ‘idiot’ mode.
‘Attitude’ or ‘acrobatic’ mode - you’re directly commanding the target 3D pitch/yaw, and aggregate power output. No provision is given to automatically maintaining level flight (won’t auto level), generally no regard is given to airframe integrity, collision avoidance, or engine life, and boy is it fun.
It’s really common to crash in this mode, because people are also doing flips, acrobatic maneuvers, running courses, etc.
Drones in even ‘sport’ mode can’t do flips because it’s fundamentally at odds with auto maintaining level flight, etc.
"On the ground" = WoW sensors. WoW sensors have been around a long time (see link). And, humans probably should not have any say about that. If humans could override WoW, then the landing gear could be deployed or retracted when it should not and cause a lot of damage due to human error.
Yeah, when I saw that it was related to WoW sensors I was reminded of a chat that I had with an experienced aviation engineer a few years ago when we were considering adding them to the UAS I'm working on. "Every system I've ever worked on that relied on WoW sensors has had some kind of unexpected adverse event due to the sensors either triggering when they weren't supposed to, or not triggering when they should have. If you can figure out a different way to do what you're trying to do, please do."
I know the 737 allows the pilot to override that (force the wheels to raise even if the airplane thinks it's on the ground). I think most airliners do. I can't find a good succinct reference though.
No, that's not dumb at all. Inputs are filthy and sensors fail. If you're not comparing all available sensor data to confirm your understanding of reality, then a single sensor failure could... oh I dunno... cause your 737 MAX to divebomb.
The F-35 could compare weight on wheels to airspeed as a simple sanity check.
That's kind of funny. Most fighter jets have an emergency override for the gear so you can use gravity or maneuvers to drop them to a down and locked position even during hydraulic and electrical failures. I can understand not being able to bring the gear up, but getting the gear down should be very easy.
I've crashed an RC helicopter because of a similar software issue. Rotorflight is an OSS flight controller, and it has an internal mode for tracking if the vehicle is on the ground or not that isn't always quite accurate at the margins. If you're touching the ground and it's not in ground-handling mode, the I-term in the PID loop winds up really quickly (because the input isn't producing the expected rotation rate) and flips your model on its side.
Betaflight (flight controller for drones, which rotorflight is based on) has a similar function called "air mode" which is common to either disable or set to a switch for aerobatic drones so that they'll still have full rotation rates at zero throttle.
Clippy never sold my data. Clippy never forced me to update when I didn't have time. Clippy never advertised things to me. Clippy never lied to me. Clippy didn't take hundreds of watts of power to provide incorrect answers.
Clippy was an assistant, built to help me solve problems I didn't understand, and built to help computer illiterate people use their computers more effectively and was made out of genuine expressions of making their product better for more people.
I was told there is so much automation on those planes, the pilot does little flying. I always assumed they were kept busy going through their compliance trainings.
Am I the only one thinking that it's time for something like an R2D2? Presumably it could get into some crammed spaces and thaw things out of needed. I'm sure it's a stupid idea, BTW, but a fun one )
It's a fun idea. Though it would have to be a really small R2-D2 that could work from the inside.
The fictional R2-D2 had a big advantage of being in vacuum so it could work from the outside, without disturbing the airflow, and without having its work disturbed by the airflow.
Envisage what happens at 900km/h in atmosphere, if R2-D2 tries to lift up an exterior wing panel to troubleshoot a blocked line?
Everyone in these comments making quips about software is missing the elephant in the room, where the heck did that water in the hydraulic system come from? Pretty much any hydraulic fluid for outdoor use will suck up a lot of water so as to prevent situations like this so this clearly isn't a teaspoon or even cups of condensation problem.
Hydraulic fluid is very hydroscopic. It will happily suck the moisture out of the air if it is exposed long enough. This is why you don't use half empty bottles of brake fluid. I suspect that the fluid was left in opened containers for too long before being installed in the jet, allowing it to load up on water.
Water boils/evaporates off from oil based fluids in normal operation. Hydraulic fluid additives don't suck up water like brake fluid, they just mix with it if present, and they can't mix with all that much. If these first two things weren't true it would have huge implications for the design of all sorts of things. If hydraulic fluid could mix with a lot of water we wouldn't be reading this story.
I assume these jets use skydrol. I'm only casually familiar with it but unaware of it having special water related properties that differ from normal petroleum products.
They use MIL-PRD-83282. It can become contaminated with water, either from the air or condensation. Typically it is tested before being placed in an aircraft and it can be purified if particle or water content is too high.
Considering they relieved a pilot of command for ejecting when his F-35 become unresponsive, now they make them sit on conference calls. That pilot is very brave, I think others would have ejected by now. Making them fly around up there is ridiculous.
Ejecting from an airplane is no joke: 18g of force leaves 20-30% with spinal fractures, and ejection seats have an 8% mortality rate[1]
It seems to me that continuing flight with inoperative/damaged landing gear while you discuss alternatives with engineers is the safest option. Burn fuel, make a plan, let people on the ground mobilize to help, and eject when you've tried what you can and it truly becomes the safest option.
It makes you wonder if it would be possible for ejection seats to have a safer bailout mode. Sure, the "compress your spine" mode is definitely appropriate during a wartime situation where someone has shot your wings off, but is it really required when a mechanical failure leaves you unable to land yet in a more-or-less stable flight at a reasonably low speed? Perhaps a 6g ejection might be more appropriate in those cases?
The ejection force is to ensure the pilot clears the airplane as they enter the airstream. Think about how much force you feel when you hold your hand out a car window at 60MPH, then remember that wind resistance increases with the square of speed. You have to be launched hard to get away from the tail.
Also the last thing you want in the critical emergency safety gear is more levels of complexity and additional things for the pilot to consider.
That airspeed is highly variable though, the plane can go supersonic or at approach/landing speed with flaps extended. Probably 10x+ less aerodynamic force going at low (indicated) airspeed.
Did you watch the latest Tom Cruise mission impossible movie? Unless you want to be the bad guy at the end, you need to be very clear of the aircraft if you’re ejecting. For a fighter aircraft, that necessarily requires very violent forces.
It’s a major concern with skydiving too - there are many aircraft it’s impossible to safely exit in flight without impacting some part of the airframe.
I wonder about that. Maybe the added complexity is a con? I.e. the default would still be full force, but a controlled ejection mode could be gentler, but still capable of clearing the aircraft reliably in straight/level flight.
Did you see how the plane went down in the video? It is like he just had shutted down completely and was in free fall. Better eject fast when you have no idea in which angle and how fast the plane is about to fall.
Any military pilot has what, 2 or max 3 ejections even in best case scenario before they have to be retired due to medical reasons? If given army lets them actually fly another one.
Its the last resort, lesser of 2 evils situation, not some cool trick hollywood may make you believe.
> That pilot is very brave, I think others would have ejected by now. Making them fly around up there is ridiculous.
Definitely not. Ejecting is very risky. If the plane is possibly fixable you would much rather spend the time trying to calmly debug it to get it back to a point where you can land, rather than risk the possibly career ending physical injuries that can come from ejecting.
You also want to maneuver the plane into an area where it’s safer to crash.
The eject button isn’t the safe way out of every situation.
The other pilot situation you brought up isn’t so simple, either. A pilot who panic ejects before attempting to properly evaluate the situation is a risk not only to themselves but to people on the ground. Flying one of these planes is an extremely rare privilege reserved for a select few who have demonstrated their abilities and judgment to an extreme degree. It’s not a job for life and they can’t risk having someone who has demonstrated panicky judgment occupying one of the few spots that could be filled by a long line of very competent candidates.
Upon first reading the headline I was thinking it was some sort of test flight. Nope, poor guy was just trying to fly and ended up forced into a high-stakes troubleshooting tree while on a conference call, as if there's not enough on your mind in a fighter cockpit.
I don't know how many human-manned gens of aircraft are left, but my first inclination is to think a remote-control fallback option wouldn't be out of line here if the security could be done right.
Remote control for what? That doesn't really help in the case of a serious mechanical failure.
There are probably several more generations of crewed tactical aircraft left. Autonomous flight control software is decades away from being able to handle complex missions and remote piloting can only work when you have secure, reliable, high-bandwidth communication links. The concept of operations for the next few generations will rely on manned/unmanned teaming where drones are sent forward to do most of the fighting and the manned aircraft hang back slightly but still within line of sight to act as control nodes.
> Remote control for what? That doesn't really help in the case of a serious mechanical failure.
In my theoretical, the pilot would safely eject as he did here (or possibly before the touch-and-gos) and the remote control would come into play to try and belly land the plane without it simply becoming a fireball immediately after ejection.
It clearly was controllable up until the last touch-and-go. The point is they could've attempted an actual landing with the pilot clear of the aircraft prior to it becoming completely uncontrollable had their been a remote option. It's about pilot safety.
That's silly. You're talking about spending years and billions of dollars developing a capability that might be used once every few years. It's not going to do anything to enhance pilot safety.
> But those attempts failed to recenter the nose wheel and resulted in both the left and right main landing gears freezing up and not being able to extend fully to attempt an actual landing.
> At that point, the F-35’s sensors indicated it was on the ground and the jet’s computer systems transitioned to “automated ground-operation mode,” the report said.
And there wasn't a way to override that? I get that "manual mode" may not be a thing for a SaaS product that isn't critical, but there not being an immediate way to turn off the "drive mode" is quite surprising.
Potentially it happened so quickly the pilot had no way to respond before they lost control of the aircraft and had to hit the eject?
Still you'd hope transitions between major operation modes could have some manual confirmation. Is there some essential reason the aircraft has to automatically transition to 'automated ground operation mode' when it thinks landing is complete? Could you not just expect the pilot to punch a button to do it instead?
For airliners, it's critical for the aircraft to know when it's on the ground because it kicks on autobrakes, and unlocks the thrust reversers for landing.
I'm very curious what the reasons would be for a military aircraft
If either of those accidentally triggered in the air would anything catostrophic happen? Auto breaks I guess have no effect in the air as they break the wheels? Thrust reverse unlock sounds like it allows thrust reversers but the pilot would still have to manually activate them?
Someone else was talking about a WoW (weight on wheels) sensor that locks the landing gear down with no manual override but again doesn't sound like a catastrophic thing to accidentally trigger in air (indeed this particular aircraft had a landing gear that was stuck so a faulty WoW sensor wouldn't have made the problem worse).
This particular mode switch thing sounds like it does something to the flight control that immediately causes catastrophe if turns out you're still in the air.
Just want to point out that $200 million is an accounting cost not an actual cost, when this jet crashes, it can be replaced for $90 million and doesn’t require amortization of the program cost or maintenance costs, etc.
From the report:
"After the second touch-and-go, all valid Weight on Wheels (WoW) sensors indicated the MA was on the ground, and the MA transitioned to the “on ground” flight control law (i.e., automated ground-operation mode causing the MA to operate as though it was on the ground when flying). However, because it was actually airborne, the MA was uncontrollable."
On projects that I've worked on we used the WOW switches as a backup and primarily used air speed to determine if the plane was on the ground or not. I'm surprised that the plane was able to enter "on ground" control law while it was still flying based only on the status of the WOW switches. It seems to me like there should be some additional checks before entering a state that makes the aircraft "uncontrollable".
Hydraulic brake fluid is glycol ether based and hygroscopic. Planes usually use mineral based fluids which are not, but heck if I know what the F-35 uses.
"The major uses of TBP in industry are as a component of aircraft hydraulic fluid, brake fluid, and as a solvent for extraction and purification of rare-earth metals from their ores"
It might be better if it is hygroscopic as the water won't separate and risk forming ice plugs in the hydraulic lines.
But what ground handling equipment? Does the hydraulic fluid need to be replaced after normal usage? Any intervention is an opportunity for mishaps, failure and sabotage.
I'd expect the unlimited F-35 budget to come up with some formula that resists fire, cold, heat and pressure and doesn't need refills and/or with water detectors and other safety-critical chemical sensors in the hydraulic system.
It could be condensation in expansion tanks, or it could be rain into open containers on the ground, or someone could have mistakenly poured cooling liquid (or something else) into the containers, or into the hydraulic system itself, or ...
Cold War era planes also had a lot of problems. The YouTube channel “not a pound for air to ground” has some great content about planes from that era, and reliability was sometimes absurdly poor.
WW2 planes never suffered from confused sensors bringing the plane down and they were much much cheaper and effective. Look at the kill rate of the spitfire. Even heavy bombers had a decent chance of bringing down fighters.
> It said if the conference call participants had referenced the 2024 maintenance newsletter, “they likely would have advised a planned full stop landing or a controlled ejection instead of a second touch-and-go” that eventually led to the conditions that caused the crash, the report said.
I guess the engineers on the call didn’t get the memo about those pesky TPS reports.
No downside if you are wrong. The people who actually run complex systems have no political power. If you get away with it then you might be able to avoid expensive changes.
You understand that the Danish Airforce is Greenland's Airforce right? The Danish military is the official military of Greenland with an explicit agreement between the home rule parliament and the Danish Defence. Other than that all Greenlanders are danish citizens and are the danish state is obligated to defend them.
Purchasing F35s is paying tribute to the empire so it doesn't come down on you harder with tariffs and compliance burdens. It's not meant to actually be useful.
Finland just joined NATO, which means that they lost their neutrality and independency for foreign politics. It is now very difficult to do something completely different or unfrienly than the U.S. because of that one country with shared border.
If the U.S really takes more steps towards taking Greenland and works against NATO ally, then it might be very complicated situation for both Denmark and Finland, and the whole alliance. But until then Finland at least is stuck with the U.S.
Yep, anyone paying billions in what is effectively tribute to this admin is only playing themselves considering the stable genius seems to flip the game board every 5 minutes.
They're betting on things going "back to normal" eventually. They have neither the imagination or courage to think otherwise.
If it does, the new president/ruling party will probably look favorably on those who respected the crown even when they hated the guy who wore it. Because that's how the normal is.
The article mentioned that the aircraft become uncontrollable once it thought it was on the ground and switched control modes. And then the pilot ejected.
I assume a controlled ejection would have been during controlled flight at a time and location specifically chosen. This ejection was necessary because the plane was uncontrollable in the end.
Apart from the water in the hydraulic system this reads as though there is such a thing as too much automation. The plane being uncontrollable because you cannot convince it it’s not on the ground while it’s actually in the air can only lead to catastrophic results. I’d call that a design bug.
That was the part that leapt out to me in the article. A touch-and-go caused the plane software to become uncontrollable? I know fly by wire is a necessity for this kind of aircraft but the damn thing better work right.
> The report notes Lockheed Martin had issued guidance on the problem the F-35’s
> sensors had in extreme cold weather in a maintenance newsletter in April 2024,
> about nine months before the crash. The problem could make it “difficult for
> the pilot to maintain control of the aircraft,” the guidance said.
>
> The temperature at the time of the crash was -1 degree Fahrenheit, the report
> said.
Isn't it pretty much always at least that cold at the altitudes these things operate at? It's unclear from the article if -1F qualifies as "extreme cold weather" but unless I'm mistaken you're going to encounter extreme cold temps up there - it's not some exceptional condition.
For one of the aircraft mentioned in Skunk Works Lockheed insisted on doing the maintenance themselves because the military maintenance folks were making mistakes causing aircraft failures.
This incident is a data point in the "right to repair" where Congress is trying to force defense contractors to make all of their equipment entirely maintained by DoD workers, apparently they make mistakes though because in this case it is the stupid failure of a significant portion of the hydraulic fluid being water (which is a problem you could cause in your car but don't because you're not foolish and you put in the correct fluid and don't just fill your radiator up with water)
If the USA ever had to go to war with this weapon, a huge number of them would be offline at any given time, and every single airframe loss would cause a huge dent in overall combat power.
I don’t understand why our military and political leaders keep trying to buy ridiculously overpriced Swiss Army knife weapons (lots of flexibility but great at nothing) instead of mass producing combat knives (only good for one thing but great at it and lots of them).
The F-35 base model is around $80 million, rising to the highest known price of $109 million per unit for the F-35B vertical takeoff and landing variant.
And then there's this:
"The flyaway cost for the F-15EX Eagle II is approximately $90 million for each aircraft in the program’s second production lot, about $7.5 million more than the newest price for an F-35A"
For me, that was a moment when I realized that the received wisdom about military things can be just completely wrong.
I had considered myself to be reasonably informed about the F-35, and how "everyone knows" it's a boondoggle. I think this started with a long-form article I read in 2013, "How the U.S. and Its Allies Got Stuck with the World’s Worst New Warplane": https://medium.com/war-is-boring/fd-how-the-u-s-and-its-alli...
Quick googling shows that the Internet is succumbing to the propaganda machines. MSN mindlessly reproduces Iranian article about 2 shot down F-35s but I was unable to find any credible source to confirm that.
The expectation that there would be 'fair and honest' reporting about aircraft losses on the part of an aggressor is not reasonable. Why on Earth would Western powers allow themselves to be so easily embarrassed?
They had some pretty advanced anti aircraft systems. Also they are invisible to radar so they were truly surprised attacks coming out of the blue. So yes, it would be.
They said the same thing about the F-117 in 1999. It was shot down by a Soviet era AA. It was said once, "Don't be too proud of this technological terror you've constructed". The same applies here. Comparing bombing Iran to a conflict with China is delusional, put plainly the capabilities of the aircraft have never actually been tested against a competent peer - when it actually matters.
That F-117 was because it was flying every day for months on the same route at the same time and they lucked out with radar catching the plane during the couple seconds it's bomb doors were open.
You're missing the point entirely. The adversary in 1999 was not remotely near peer. So say arrogance there costs you only one plane, which nonetheless becomes infamous as a cautionary tale about superpower hubris. The same against China will be far more fatal. Also, fwiw conflict with China is routinely simulated by American war planners, and to put it plainly there is no longer any plausible scenario where America "wins handily" in the Taiwan strait. Your suggestion that this is even possible is therefore vaguely amusing. Maybe also look to the past decades of American war fighting. When was the last time we felt like we outright "won" a war? When against a peer or near peer? Mission accomplished?
>received wisdom about military things can be just completely wrong.
Consider that what you thought was "received wisdom" was literally Russian propaganda. However, the actual reality was always there, always being patiently insisted by people who knew what they were talking about, who were in fact still discussing actual boondoggles with the program, like the portion of the program that built the tailhook and was terribly run and ineffective at points.
People like Pierre Sprey have been shouting the same lies for decades, and credulous people with zero domain knowledge have been repeating his horse shit forever. He was the same guy who insisted that we should be building really stripped down planes without radar, without missiles, without anything.
He was very much the originator of a lot of anti-F35 FUD, on Russia Today no less. Western media was literally quoting the Russian propaganda firm to tell people how the F35 sucked. He helped push the utter BS that is "Oh, Russia's long wave radar makes stealth not work" which if you don't understand how that's irrelevant and untrue, don't ever have an opinion on modern warplanes.
There's a famous article talking about how terrible the F35 was by interviewing an F16 pilot who had faced it in dogfight training. The article talked at length about how the pilot of the F16 was able to out dogfight the F35. Now, it's sufficient to mention that gun range dogfights are not a thing in modern air combat, or at the very least are not designed for, because as long as your enemy has a single radar or IR missile left, you've already lost. However, beyond that, the F35 wasn't terrible, it's just very unlikely to match the literal king of dogfights. More importantly, the article mentioned something that I'm sure they didn't even realize the importance of.
Even at knife fighting range, the F16 radar assisted gunsight was unable to lock on to the F35. Go look at early jet aircraft gunnery statistics for an idea of how laughably bad dogfighting an F35 would be.
Oh, and that entire test was done with an F35 that wasn't allowed or capable of flying it's full envelope. It was an F35 with a hand tied behind it's back.
Do you have any reason to attribute this to the fact they were F-35s? For comparison, how many jets were lost during "shock and awe"? Israel operates with impunity in Iran all the time, often on the ground. I'm not sure the fact they used F-35s is actually relevant here but if you have a source on that it would be interesting to read. Given the state of Iran it is hard to imagine the same could not be achieved with a last generation aircraft... it would not be surprising if by the time a peer power conflict starts manned aircraft like the F-35 will already be obsolete...
If you look at the Ukraine war the planes are operating from a distance to the frontlines on both sides. The ones close the the front fly in low and then climb and drop their guided distance munitions.
Sounds like an interesting book, though far too many pages for a subject I have only a passing interest in. I would note given the authors affiliations I'm not sure I would ever consider it something that could "set the record straight". If there's a controversy about the program the authors backgrounds don't exactly suggest one will be getting a balanced view. Perhaps I'm wrong, but I appreciate the suggestion anyway.
It’s not at all unbiased, in a journalistic sense, and doesn’t present itself as such (for others: it is written by the now retired program manager of the F-35 development program). But the relevant facts about the performance and cost effectiveness of the plane are a matter of public record, and the book is interesting for providing the inside view on the politics which resulted in the unfair propaganda campaign against it.
You are free to draw your own conclusions of course. I worked for Lockheed previously in my career, and some in my family still do. Though I hold no stock or other ties now (different career, different industry), my experience does lead me to take the authors at face value. There are many issues with Lockheed leadership, but professional integrity is not one of them.
Nah. Parts of the F-35 program were terribly managed (procurement malpractice) but the final product largely works as promised. The whole reason it was developed starting in about 1994 was that exercises and simulations had shown that legacy strike aircraft weren't survivable against modern air defenses: that part hasn't changed, in fact the situation has gotten worse. It doesn't matter how cheap an aircraft is if it can't accomplish the mission.
Perhaps someday cheap, expendable drones will be and to take over the entire mission set. But for now that concept is still science fiction.
the price is much lower today. Cheaper then the latest f15. I was also skeptical of the project but its really proved itself. The simple fact is that stealth abilities gives it an ubeatable advantage. It expands the capabilities of an army so much its indispensible. 5 years ago i would agreed with you but im forced to change my opinion in the face of the evidence. The f15 is going nowhere like the b52, but it cant come close to the f35.
Just a thought (I am no airline expert), If it costed 200 million to build the plane that was destroyed because landing gear can not be deployed then maybe it's time to think about building a catcher similar to spacex booster catch.
This would probably need different plane design like vertical landing and horizontal landing gears.
> An inspection of the aircraft’s wreckage found that about one-third of the fluid in the hydraulic systems in both the nose and right main landing gears was water, when there should have been none.
The F-35 is unstable by design and requires constant adjustments by the computer system to fly. So it is actually impossible to "just" turn the computer off and fly manually.
"Modern" jet fighters, yes. I believe it started to be "hard" to fly manually with the F-16 and now it is completely impossible, but feel free to correct me.
F-16 was the first inherently unstable jet fighter, and the first one that featured a full fly-by-wire system with no backup. If you want a jet that is completely impossible to fly without a computer, F-16 is already one of them - there is nothing special with the F-35 about that.
Only on HN do people argue about an initial comment that they find nothing incorrect about, until they can find a little thing to be able to write "ahah you're wrong!"
If a third of the hydraulic fluid was water, it was like that meme video of the woman who added washer fluid to the car’s oil - no way was that going to work properly.
I'm surprised no one is mentioning this, and the fact the article says this is the second of such incidents...
I don't know if this is what actually happened, but it would appear to be a very effective method of sabotage... Simply putting some water in the hydraulic fluid container destined for an F35 is an extremely high risk-adjusted ROI for any saboteurs.
For counterbalance to this point, it is very common for water to get into hydraulic fluid. Moisture from air condenses in containers when they transition from hot to cold environments.
It would depend on how many months the barrel was subjected to thermal cycling. A more likely cause would be a technician leaving the cap off the barrel during a rain storm (noted in the report).
Sabotage vs incompetence is a tricky question to balance. The DoD has undergone a lot of controversial leadership changes recently, and it is entirely likely that people have now been promoted beyond their level of confidence.
The F35 is deployed at scale and has fairly normal accident rates for a new, maintenance heavy plane. You just don't hear about every single F16 that crashes.
I have no idea how VTOLs would work in this scenario, but I suspect it could be recovered safely in that config.
Non-VTOL fighter landings with improper gear configurations have various guidelines (As discussed in the report here) in their checklists, depending on which gear are down. They range from landing normalish, landing while applying counter-forces etc, to approach-end-resentment, to ejection.
Ultimately the US taxpayers will eat the loss in either case. If the government tried to charge it back to Lockheed Martin they'd just raise the price on subsequent programs to compensate.
The government does insure weapons of war. Who would write the policy?
is insurance for military equipment a thing? I had no idea.
If you have very deep pockets like a nation has, why not simply replace the lost hardware and never insure/pay premiums(which would be calculated to net a profit to the insurer)?
During the BLM riots many participants in justifying their actions of property destruction would claim that the costs of replacing the property would come from insurance. Many people don’t have insurance, or self insure, and those that do could see a rise in premiums that make their business unviable. Additionally for some business it doesn’t make sense to rebuild as the circumstances that lead to their creation has changed, for these it’ll make more sense to take the insurance money and not rebuild resulting in a loss to the community.
Personally I don’t make a big distinction between crimes against property and crimes against people. I live for my life’s work, if someone destroyed that they might as well have killed me. Additionally many people are dying due to lack of resources, so if someone could be saved for $1M then the destruction of $1M of wealth might has well have killed them. As such I would treat theft and other white collar crime on part with mass murder.
The per plane cost varies a lot depending on what you want to wrap in it: how much of the development costs you amortize, the modernization program, etc. but $200m is in the range.
("Total acquisition costs" vs the marginal cost of the next plane can result in a more than 2x difference in how much you think the plane costs)
The flyaway cost of buying one more plane is probably a bit under $100m though.
F-14D unit cost was ~$74 million in 1988. Adjusting for inflation that's ~$202 million in 2025. It's not that unreasonable for an American fighter jet, honestly.
The F-14 is twin engine, 40% more plane and can fly faster. Also the F-14 was considered expensive.
My main disappointment with the F35 is that it could have been a lot cheaper with modern design technology and manufacturing. That and the software is needlessly buggy. I had a friend working on F35 at a time I was working on software quality research, when I discussed the possibility of applying the research to F35 he let me know that bugs were seen as a cash cow and he would be working on bugs on the F35 until he retires. He was right. And now we have stuff like this happening.
I'm wondering why these days, when my washing machine has an internet connection, they can't take over control of a plane remotely. I guess it could be considered a security vulnerability, however i'm quite sure it could be done securely.
Like let the pilot eject and you try to land a plane with remote control
That would require even more R&D to maybe be useful in a rare situation. Like you mentioned, the vulnerability surface would increase. The last you thing you'd want is a remote control vuln being discovered in your $200M jet during a conflict.
That and I'm not sure what an ejection actually means for the planes internals i.e. is it even guaranteed the electronic components won't be damaged?
The article said the plane had become uncontrollable and that’s why the pilot had to eject.
So even if remote control was possible I’m not sure it would’ve done any good.
Of course I also don’t know why the plane would be allowed to think that it’s in ground mode when it’s 100s of feet or more in the air. Or why the hydraulic fluid was 1/3 water.
When the plane's software misbehaves due to broken sensors and you only now that, because there are human eyes up there, remote control isn't going to improve the situation.
Going from “I can check my washing machine remotely” to “it should be easy to remotely control fighter jets without any security risks” is quite a leap.
Anyway it’s missing the point. If the pilot can’t adequately control the airplane then a remote operator isn’t going to have a better experience.
I mean, a remote operator could either try to land it in life risking situation, salvaging some of that $200M, or do kamikaze style on a target, both feel quite useful for war situations.
Remote piloting isn't useful for aircraft expected to perform penetrating strike missions against near-peer adversaries. Developing such a capability would be a waste of money.
Journalistic integrity (or not) arguments aside, that this happened with such an expensive piece of equipment is disappointing. Reminds me of Deal of the Century; “you ever heard of rain??!”
What should they be buying instead? The other available multi-role fighters that would all get blown to pieces by an F-35 before they knew what hit them?
They're really not. You're basing this on misinformation and propaganda. The only reason why nobody should be buying them is because the US has become an untrustworthy partner. Otherwise, there is no credible evidence of any kind that I've seen showing the F-35 is anything other than a great fighter jet.
Its stealth is good. Its EW and Avionics are probably good... now, after a decade of production, and with Block 4 around the corner.
As planes, they were terrible when introduced a decade ago, and mediocre now.
Too much functionality was promised too soon without adequate project management. Instead of modularity being the design philosophy for the NGAD, and shoehorned into the F-35 during production, it should've been the design philosophy for the F-35A/C from the start.
Too many compromises were made to make the three variants share a similar design despite radically different missions.
The F-35B should never have existed.
The parts commonality numbers say it all. Initially projected to be 70%, but when it neared production the actual commonality figure was 25%. I haven't seen that broken down, but I bet the F-35B is a large part of that.
Switzerland, if they want something they can fly for air policing is forced to buy the F35 at what every price the US feels fit (even though the contract with Lockheed states a fixed price, naive politicians and consultants found out the hard way). Of course the CHF to USD conversion is fix at a shit rate from many years ago and from what I understand there is no way around that because the SNB did the conversion back then already.
We have no alternative we can get before 2035. They are talking about extending the F/A-18 but since we would be the only ones still using them we would have to pay for that too at who know what price.
The public approved 6 billion and now it looks like it will be way more, excluding skyrocketing maintenance which is not included and a patriot missile system that when it is finally delivered will cost who knows how many billions.
The whole thing is an absolute shit show here and that's ignoring the technical issues this thing has...
With such a terrain, I would guess that agility and the ability to land on highway of in fields without burning all avionics and electronics would have been rated higher than stealth, but it wasn't. Still, the Swiss were offered a fairly low price, and promised low operating costs, and that's the main reason they didn't choose the Eurofighter (which isn't a multi-purpose jet but an interceptor)
You can, but it will destroy your plane electronics if you can't bring an external cooler fast enough. even with the next gen internal cooler (that won't be in test until 2029, so not installed until like 2035), the jury is still out until it's done.
And Stealth alone is not good enough, not anymore. Radar and optics tech caught up. You still have to load of flares for any CAS or any engagement that will involve fox-2 targeting (which, you know, break your profile and make you visible on old radars), and from what i heard, Thales is confident on its next-gen avionics/optics/radars ability to detect gen5 radar signal, so much so that they clearly focus on future-proofing against EW equipements (that don't yet exist, allegedly).
The future is Stealth+Altitude, or stealth+EW+unmaned, automated drone with similar radar profile, and that's probably when the F35 will probably shine, but until then, i just don't think it's a good plane, not yet.
Also i think fighter planes based on the Growler will probably be better in the future. If a country bought F35 without asking for Growlers, my intuition is that it was a political choice, not an informed/military one (So basically, Australia military, to me, is the only sane country).
I wonder how good it would still be when the enemy had resources and time to adapt in an ongoing conflict. In russia's war with ukraine, we saw tactics and tools quickly evolving.
Not on the level of responding to fith generation fighter jets. Most of their advances are in quadcopter technology. They both started with ww2 tactics. Its not surprising that they would take advantage of the low hanging fruits of 75 years of progress. If anything it's shocking how little both sides have changed fundamental tactics like not using meatwaves, which went out of fashion in ww1.
The F35 program had a ton of issues and was expensive, but so was the B2 program. Sometimes something good comes out of a difficult process. They have made a lot of F35s now and exported many of them with many many more on order. At this point I think it is fair to say the F35 is a successful platform.
Rafale and Gripen don't hold a candle to the F35's capabilities, they're just a different class of aircraft. Not to say any one of the three is bad, but the EU currently just does not have it in them to have a viable competitor.
Iran has been crippled with sanctions limiting their ability to develop/buy any kind of fighter aircraft. Shooting from the air in Iran equals fighting a bot in an FPS game. They don't shoot back
Israel has no B2s. Israeli F35s flew constantly over Western and Central Iran (including Tehran) for 12 days as if Iran's extensive air-defense network was not even there, doing a lot of damage.
Russian milbloggers responded with, "Why can't the Russian air force fly over Ukraine like that?"
Another absurd take - there was 1 sortie of B2s which was America's show of force. There were two weeks of daily Israeli F35 sorties, starting with SEAD and then progressing to strategic bombing targets. They all completed their missions with no loss of aircraft.
Tell me, when has an F35 failed to perform in combat duties? You're running off of internet memes from a decade ago while the F35 was still in development (and having a bad time of it). They are selling like crazy, and it's not because their customers are misinformed about the capabilities.
This is completely wrong. B2 bombers only dropped the MOAB on the nuclear enrichment sites. Israel used F35s to bomb Iran at will. Iran didn't shoot down a single plane.
> if the conference call participants had referenced the 2024 maintenance newsletter, “they likely would have advised a planned full stop landing or a controlled ejection instead of a second touch-and-go” that eventually led to the conditions that caused the crash
So nobody remembered to search for and read all available documentation? Useful lesson for every software engineer.
The article is somewhat sensationalistic. If you read the actual report you will find out that:
The pilot was not part of the conference call!
What froze was not hydraulic fluid for actuators (in some hydraulic line), but hydraulic fluid in the shock absorbers.
The last paragraph of the article and seems to be missing a few words and reads as the investigators blaming the people directly involved, which is essentially a complete opposite of what conclusions of the report say.
If you want to read the actual report, it's not linked from the CNN article, but it's available here:
https://www.pacaf.af.mil/Portals/6/documents/3_AIB%20Report....
Edit: While CNN says the air force blamed the crash on ice in the hydraulic lines, it's obvious that ice can't be legally culpable. The report actually says:
> Additionally, the [Accident Investigation Board] president found, by a preponderance of the evidence, that crew decision making including those on the in-flight conference call, lack of oversight for the Hazardous materials program, and lack of adherence to maintenance procedures for hydraulic servicing were substantially contributing factors.
They note further down that "The 355th FGS hazardous materials program (HAZMAT) program suffered from insufficient manning and frequent supervision changes at times relevant to the mishap." Basically, they had a barrel of hydraulic oil that sat outside and no one took care of it.
Also interesting is the 6 February 2025 incident, where another aircraft, barely a week after the one that crashed, had the same issue. They tested it inside a heated hangar, then outside in the 15F cold where they reproduced the weight-on-wheels sensor malfunctions, then brought it back in and drained the hydraulic fluid...there's a TON of water in those lines! I'm more familiar with industrial hydraulics in factories and earth-moving equipment, not with aviation...but we have water separators because a few drops of water can be enough to mess with the servo valves when you're near caviation limits. "...approximately one third of the fluid retrieved from the [landing gear] was water" is NOT RIGHT.
Also, I chuckled on reading "...the barrel tested with more than 1024 parts per million (ppm) particulates, which is more than double the allowable limit for particulates in hydraulic fluid... It is important to note that the test does not accurately measure contaminates above 1024ppm, so the contamination was potentially far greater than 1024ppm"
Gives strong "3.6 roentgen, not great, not terrible" vibes!
Of note to readers not familiar with hydraulic fluid, it is hygroscopic:
>Passenger safety requires that in commercial airplanes hydraulic actuators be powered by fire-resistant hydraulic fluids. As a downside, such fluids are hygroscopic which means that these tend to accumulate humidity from the environment
https://www.mdpi.com/2227-9040/8/4/131
The hygroscopic nature of hydraulic fluid is there for the same reason it is in car brake fluid-
it's better to evenly distribute water throughout the fluid, than to have it accumulate in a low point
That's actually a really cool way to deal with that problem!
It is. Right up until you go to hit your brakes hard and it all boils out and removes your ability to apply brake pressure in an emergency and you had no idea how much water was in your line because there's no easy way to check, like a low spot with a sight glass.
Or if you leave a barrel of hydraulic fluid outside until it is partially water and it's not easy to notice when you are handling it.
Can't agree at all about a sight glass. The lowest point in nearly every brake system is the brake calipers themselves. Wheels going to make it difficult anyways on a car. Not to mention the risk of a rock striking and damaging rigid glass. Or the old interface that's sealing the glass to the calipers wearing out and causing a leak.
It's not worth the expense to manufacture and it's not worth the risk. Not when a litre of DOT4 is $20 and that only needs replacing every 3 years at an aggressive schedule for passenger cars.
Larger vehicles you can purchase a brake fluid tester, but most of the really large ones I know use air brakes anyways.
I think my mental model of hydraulic brakes is too simple. Where is there a low pressure region in a brake line? When I stomp on the brakes, isn't the working part of the hydraulic system going to be at higher pressure?
There isn't a low pressure braking region in the brakes.
But brakes can get really hot. Passenger brakes can easily get over the boiling point of water. Keep braking long enough and adding enough heat, and they'll get over the boiling point of brake fluid under pressure.
Thing is, brake fluid is incompressible. Brake fluid vapor however is very much so a compressible gas. Even more so: the water in the brake fluid has an even lower boiling point then that.
So stomping on the braking quickly isn't going to cause much of a problem. But if your riding the brakes down hill for a long distance with 12 year old brake fluid in hot Florida summer on very heavily loaded car? That... might get you into a spot of trouble.
I take your general point, but as per your specific example, it’s not really possible to go downhill for long distances when the high point of the state is 345 feet.
I've gone down the Sonora grade in a Silverado with 22 year old brake fluid. I wasn't towing, but it was very hot out and in general yes the brakes were hot when I checked at around 4000 feet.
I wonder if some YouTuber has done some experiment to see just how bad fluid had to get before a typical driver could notice.
have you considered a career as an F35 pilot? :-)
The one piece of good news is the highest point in Florida is just 345 feet above sea level so I think they'll be okay. :)
Thanks for breaking that down. None of that surprises me and it's basically what I was expecting. This report gives a glimpse into the reality of the US military behind the propaganda facade and the massive margins for error stuffed with money.
>it's obvious that ice can't be legally culpable
well, why not? we need a good politician to make it illegal for ice to form on an airplane, that would fix the whole thing. also, make it illegal to ever get sick. Checkmate, human illness.
> Gives strong "3.6 roentgen, not great, not terrible" vibes!
What?
In the Chernobyl TV series, they think they see a high but (short term) tolerable amount of radiation. It was actually just the upper limit of the measurement hardware and the real value was much higher.
And they're told it's the upper limit of the detectors, but choose to ignore that and take 3.6 as the gospel truth actual value.
It's a mockery of Soviet politics and party loyalty, but many of the errors apply to all bureaucracies.
Like my continuous glucose monitor.
> The article is somewhat sensationalistic
somewhat sensationalistic?! The article clearly tries to give the impression the pilot was on the call:
> A US Air Force F-35 pilot spent 50 minutes on an airborne conference call with Lockheed Martin engineers trying to solve a problem with his fighter jet before he ejected
Knowing the quality of media these days, it wouldn't surprise me if it CNN just got it really wrong, but also wouldn't surprise me they'd do some brazen lie for clicks.
Edit: Reading the report, it seems like you, dear fellow HN commentator, got it wrong in this case, sorry to say :) Seems indeed the pilot itself was on the call:
> The mishap pilot (MP), assigned to the 354th FW, ejected safely before impact. [...] The MP initiated a conference call with Lockheed Martin engineers. The MA held for approximately 50 minutes while the team developed a plan of action
Page 35 from https://www.pacaf.af.mil/Portals/6/documents/3_AIB%20Report....
You omitted an important part of the sentence (in italics below):
> The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action.
So it was the SOF on the conference call, relaying information to and from the pilot over the radio. This is more clear if you read the sequence of events on pages 7-10.
Not that it makes that much of a difference. Either way, he's up there waiting for the engineers on the ground to troubleshoot the problem.
Confusingly enough, there are these two parts in the previously linked document:
> The MP initiated a conference call with Lockheed Martin engineers. The MA held for approximately 50 minutes while the team developed a plan of action - Page 35
And
> The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action - Page 2
I quoted from the Page 35, you quoted from the Page 2, not confusing at all of them to have very similar stuff with slightly different meaning, all in the same document :) Thanks nonetheless for the additional context!
SOF initiates Conference Hotel procedures, FYI. It's a (rarely used) checklist in their book. SOF is the pilot sitting in the tower to liase with ATC and handle emergencies from an ops perspective.
To the uninitiated: SOF is Supervisor of Flying.
Classic DoD with its overloaded acronyms. I first read the sentence thinking "what does this have to do with Special Operations Forces"?
> Classic DoD with its overloaded acronyms.
What does Depth of Discharge have to do with anything?
Thanks!
Prepared By: The Boeing Company Field Service Technical Support (Aircraft Information) Aviation Life Support Systems (Crew Rescue Information) Please contact your local Boeing Field Service Office for additional information or copies of this booklet.
Boeing has an emergency response program called “Conference Hotel” (USAF) or called “Conference X-Ray” (USN/USMC) to provide units with engineering and test pilot expertise during airborne emergencies. This 24 hour a day service is available by calling (866)543-5### toll free or commercial (314) 232-9###. Callers may also contact the regional DSN operator at DSN 693-1### and ask to be connected to the Boeing STL operator at (314) 232-9###. It can also be used overseas via long distance phone lines or MARS radio patches. When the Boeing operator answers, callers must identify themselves and request Conference Hotel or Conference X-Ray assistance. The operator will ask for specific information to identify the appropriate Boeing personal to respond. Conference Hotel or Conference X-Ray is available to assist in airborne emergencies only. Do not utilize this capability as a part of pre-mishap drills.
F/A-18E/F Aircraft Crash Rescue; Fire Fighting Information; January 2006
I think there's just some nuance to the scenario. The pilot wasn't directly on the call, but was participating in the call with the flight supervisor relaying the information.
I'd compare it to being in the room with someone on a conference phone call and they're relaying the conversation to you and them both ways. I would still say you were participating in the call even though you weren't directly on the call.
Also, he did initiate the call so "F-35 pilot held" is imprecise, but not totally wrong. Either way, the pilot was in an active tech support session with the plane engineers, making this one of the most intense tech support calls in history.
dang, I was looking forward to reading about the same F150 CarPlay and MS Teams being available in f35.
And, of course, CNN only links to their own articles. Why bother linking to the actual report? The rise in sites that only link to themselves 99% of the time really frustrates me.
Journalism's failure to adopt linking to sources etc in the internet age is kind of infuriating. I get it, back in physical newspaper/magazine days, linking wasn't possible, and it takes a while for new norms to change and habits to form, but articles have been internet-first for well over a decade at this point. It should be completely unacceptable not to have linking to sources whenever relevant. I'm not sure I have ever found a news article that makes finding the original source or subject of the article easy. Certainly not on mainstream news outlets.
Sites with no external linking are like highways with no exits.
Backed up, slow, and avoided by those familiar with the area?
If you link to something external the eyeballs leave and that's undesirable.
They complain about how social media links to them, while they are equally guilty of link shenanigans
It’s infuriating because, when debating, we’re asked to cite our sources.
We’d like to cite sources but journalists don’t cite theirs.
Now consider this: When you know journalists are spreading a lie, you can show the article and the scientific study which says the opposite, because people always claim that it isn’t the study cited by the article.
Case in point: I remember this article from the BBC titled “It’s proven, women are smarter than men. [In a scientific study about multitasking, …]”
The scientific paper published the month before on the same subject had an abstract that finished with “…, therefore we cannot conclude that women are smarter than men.”
I was particularly angry because it participated to the 2017 wave, and it was about multitasking, and once again it said women are 5s faster on a 170s task (with 15s stddev), but the study didn’t underline the accuracy of the two tasks in parallel, which was worse for women than men.
Anybody who mocks me about competing with girls, should respond why the BBC need to publish a petty news article about women being smarter.
> Journalism's failure to adopt linking to sources etc in the internet age is kind of infuriating.
Possibly my greatest disappointment with the internet.
If they’re not providing essential links then it’s not journalism. They shouldn’t be given credit for a title they are not earning.
If you pet barks, do you still call it a cat? Of course not.
Links make it journalism. Not linking makes it reporting. They should not be considered synonymous.
The point is, people who should know better keep calling the likes of CNN journalism and those who don’t know any better keep believing they’re consuming content and forming understanding based on journalism.
We're CNN, you trust us right? I mean, why wouldn't you trust us in referring to ourselves? Because, we say so, so you have to believe us.
I read the article (twice) and I still have the impression the pilot was in fact the one in the conference call
Opening line:
> A US Air Force F-35 pilot spent 50 minutes on an airborne conference call with Lockheed Martin engineers trying to solve a problem with his fighter jet before he ejected
Am I illiterate or misreading it?
> After going through system checklists in an attempt to remedy the problem, the pilot got on a conference call with engineers from the plane’s manufacturer, Lockheed Martin, *as the plane flew near the air base. *
Is this actually some insane weasel-wording by CNN? "We never said the pilot (he is in fact a pilot) was the one flying the jet, we just said 'as the plane flew', not 'as he flew the plane', using passive voice, so we're not wrong - but it was another pilot flying the plane"
From the report:
> The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF)
"MP" is the pilot
> A conference hotel is a call that can be initiated by the SOF to speak directly with Lockheed Martin engineers to discuss an abnormality/malfunction not addressed in the PCL (Tab V-13.1, 14.1, 15.1, 16.1, 17.1). While waiting for the conference hotel to convene, the MP initiated a series of “sturns” with gravitational forces up to 2.5Gs, as well as a slip maneuver (i.e., left stick input with full right rudder pedal) to see if the nose wheel orientation would change (Tabs N-12, BB-201- 02). Upon visual inspection, the MW reported no change to the nose wheel (Tab N-13). The SOF informed the MP he was on the phone with the conference hotel and Lockheed Martin were getting the LG subject matter experts (SME)
So the pilot was, in effect, on the call, even if not directly on the phone. I don't know for sure, but I'm guessing an F-35 pilot had radio comms with the SOF who was on a phone line. It's a layer of indirection, but the pilot was essentially exchanging info in real time with the conference call. Its not a stretch to colloquially say that the pilot was "in the conference call"
> The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action.
I read this as "The pilot initiated a conference call, but was put on hold [i.e. not actually in the conference call in any meaningful way]." So he was both on and not on the conference call.
The Zen Koan of the Mishap Pilot. Sounds like an Iron Maiden song.
Don't read the article; read the report.
I’m guessing you also didn’t read the report given that he was indeed on the conference call.
One clear indication he was not, from PDF p14 (8 as numbered) ("MP"="mishap pilot"):
"At 21:12:52Z, the SOF informed the MP, “Alright the engineers uh are not optimistic about this COA but, extremely low PK [probability kill, meaning the probability this would fix the issue], but we’re going to try anyway is a touch-and-go on the runway, mains only, do not touch the nose gear, uh lift back off in all cases and have the uh have Yeti 4 reconfirm the nose gear position once your safely airborne.”"
No need for this if the pilot was on the call directly.
From the Report:
> The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action.
"though the SOF" implies a middle-man, but I imagine that's because you don't want literally hook up a conference call directly to the cockpit. That being said, seems like the pilot was effectively on the conference call.
Unless you want to suggest I don't trust the report?
https://www.pacaf.af.mil/Portals/6/documents/3_AIB%20Report....
What I said is he was not on the call /directly/.
You can argue over whether he was “effectively” on the call because someone was summarizing it for him per what I quoted.
I just think it’s worth nothing he was not “on” the call the way someone is traditionally on a conference call.
Sure, of course I will trust the report as the source of truth.
But I'm interested in the reporting. There are, you know, journalistic standards, which are considered kinda "journalism 101"! For instance, getting the basic facts of a story correct - especially the facts stated in the headline.
So I'm curious, did the reporter do their due diligence, and write the article in a way that is factually correct, but highly misleading? Or did they simply not follow basic reporting protocol?
From the Report:
> The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action.
Seems accurate to what CNN was reporting. It's simplified a bit, but it's not misleading to me.
I mean, I guess if you want to nit pick and suggest "No the pilot wasn't literally on a phone and there was an intermediary in between" or some such, but the report makes it seem like CNN is accurate.
https://www.pacaf.af.mil/Portals/6/documents/3_AIB%20Report....
I’m curious why you’re getting this worked up when the report is clear that the pilot was part of the information flow in that conference call. This is a really minor case of a headline using less precise language.
The article is standard news stuff. It is sloppy and misleading. The report is what you want.
>But I'm interested in the reporting. There are, you know, journalistic standards, which are considered kinda "journalism 101"! For instance, getting the basic facts of a story correct - especially the facts stated in the headline.
Every single story is like this, every one, and f-them for not linking to the source documents.
> There are, you know, journalistic standards, which are considered kinda "journalism 101"!
Pretty sure you meant to use the past tense here: "There _were_ journalistic standards..."
> There are, you know, journalistic standards
Are there? What are they?
To clarify because everyone is confused here. The report is a little vague and information is buried in a couple places. Using PDF page numbers
> "The MP responded “14.5” ... and then opined a “conference hotel” was appropriate for this situation (Tab N-12)." (pg. 13)
> "The MP, utilizing the on-duty supervisor of flying (SOF) in the air traffic control (ATC) tower, initiated a conference call with Lockheed Martin (LM)" (pg. 8)
> "The SOF informed the MP he was on the phone with the conference hotel and Lockheed Martin were getting the LG subject matter experts (SME) on the line ...no transcript is available because the call was made on a personal phone rather than the legal voice recorder in the air traffic control tower" (pg. 13)
in the last statement, he means that the SOF was informing the MP that the SOF was on the conference call and would relay information. The mishap pilot (MP) was speaking to the supervisor of flying (SOF), almost certainly via radio. He asked the SOF, in the control tower to set up a conference call. For reasons, maybe of expediency or technical failure, or norms or something, the SOF made that call on his personal cell phone. The MP was not 'on the phone' but the SOF would have primaily functioned as a relay between radio and phone. The purpose of the call was to get information from the pilot to the engineers and from the engineers to the pilot. Aviate, Navigate, Communicate* means he doesn't need to cognitive load of actually listening as the SOF and engineers think through what to do and decide on a plan. He needs to fly the plane and provide information necessary to help figure out how to aviate.
If you want to harp on CNN for accuracy, I'm sure there are plenty of opportunities but this feels pedantic. It is like saying 'the astronauts weren't talking to mission control, they were talking to the capcom. Only the capcom talked to mission control'.
I suspect that in the non-public version of this report there is more discussion of the decision and alternatives to doing that call on a personal cell phone for two reasons. (1) As noted in the report it means that conference isn't recorded and a transcript is not available to the investigators (thats shocking to me). (2) Detailed aircraft systems information, which is highly controlled, is being discussed on an open line.
* Funny enough, the third time the report defines SOF, they have a typo "supervisor of lying" (pg. 36)
> If you want to harp on CNN for accuracy, I'm sure there are plenty of opportunities but this feels pedantic. It is like saying 'the astronauts weren't talking to mission control, they were talking to the capcom. Only the capcom talked to mission control'.
Um, actually, they were talking to a mic. And the mic converted the noise... /s
But yeah, excellent comment here.
I’m sorry but it’s not noise its an electrical signal
(This argument also failed to convince my mom my teenage band didn’t suck)
> Briefly stated, the Gell-Mann Amnesia effect is as follows. You open the newspaper to an article on some subject you know well. In Murray’s case, physics. In mine, show business. You read the article and see the journalist has absolutely no understanding of either the facts or the issues. Often, the article is so wrong it actually presents the story backward — reversing cause and effect. I call these the “wet streets cause rain” stories. Paper’s full of them.
> In any case, you read with exasperation or amusement the multiple errors in a story, and then turn the page to national or international affairs, and read as if the rest of the newspaper was somehow more accurate about Palestine than the baloney you just read. You turn the page, and forget what you know.
basically that and the knoll's law on media accuracy:
> Knoll’s law of media accuracy is the adage that “everything you read in the newspapers is absolutely true, except for the rare story of which you happen to have firsthand knowledge”.
Knoll's law, I'll remember this.
"After going through system checklists in an attempt to remedy the problem, the pilot got on a conference call with engineers from the plane’s manufacturer, Lockheed Martin, as the plane flew near the air base."
Did I misread that? I thought it meant an air-to-ground call, which I suppose is not that unheard of: I've definitely seen air accident videos saying the pilots were trying to debug in the air with engineers in the loop.
*edit: never mind, I misunderstood your comment. I thought you meant the article was clickbait.
> The pilot was not part of the conference call!
Thank you. If I cannot even trust one of the substantial parts of the headline to be true, then my interest to read or even care about such an article is reduced to almost zero.
Still interesting part is: them trying to fix the problem - made the plane crash.
Of course it couldn’t land but still, tweaking stuff while flying was ultimately causing loss of control.
The report actually says it could have landed. A week later, another F35 at the same base had the same problem, it landed with its nose gear 6 degrees off center and the pilot barely noticed.
Basically, Lockheed Martin engineers told the air force to attempt re-centering with touch-and-go landings, but didn't realize that this could mess with the weight-on-wheels sensors and cause it to switch flight modes.
I’ve always wondered why weight on wheel modes don’t have more checks, detecting weight on wheels but seeing 150+ Indicated Air speed and RALT is greater then 15ft, maybe issue caution instead of screwing with flight mode.
Yeah, they put too much faith in their sensors. Too many planes have crashed because of blind reliance on sensors that sometimes fail. Cross check whether things make sense before doing potentially catastrophic actions.
And don't skimp on the maintenance budget. Sounds like they had too much to do, too few people to do it, leading to not taking proper care.
There's value in simplicity. Every decision that a flight computer makes is based on a leaky abstraction of the world, and it's important to be able to reason about those states without excessive complexity.
If a programmer, engineer, or pilot needs to think about when the aircraft will transition to "on ground" mode, and the answer is "when the weight on wheels sensors say the landing gear is not fully extended", that's simple. You can even extend this to reason about what might happen when the landing gear is not fully extended, or what happens if it does a belly crash-landing with the gear not deployed, or if it hops, etc. Furthermore, it's a perpetual signal, rather than an edge-triggered condition: You don't have to develop and remember and think about a state machine that transitions to the on-ground state, or worry about what happens if the flight computer gets reset, you can check the sensor state at any instant.
Yes, there are a myriad of checks and alternate modes you could do, or information items you could communicate to the pilot - radar altimeters, GPS altimeters, barometric altimeters, indicated airspeed, speed over the ground, weight on wheels, landing gear deployment, accelerometer/gyro/IMU history, stick position, flight model response to control inputs, brake response, ABS wheel speed sensors (if they have those, which I doubt), cameras...the list goes on.
With more data, you can potentially be more accurate if one or more sensors malfunctions. "Aircraft On Ground" could actually mean the aircraft is on the ground, rather than the abstract state that occurs when the weight-on-wheels sensors say the landing gear is not fully extended. But the more complexity you add, the more it gets difficult to understand!
I deal with this all the time - I'm an industrial controls engineer, working with robots and CNCs and assembly equipment rather than aircraft. But the machines still need to reason about the world. It's an important judgement, borne out of years of experience, to decide when you need to have a laser distance sensor or inductive proximity switch that confirms the part is present in the fixture. Sometimes you can reason about it and assert that if the part was in the previous fixture and the machine cycled, it must be in the new fixture, sometimes you need to put together multiple sensors or live information like CNC spindle torque to confirm that you're actually cutting steel. But usually, when you've got an operator or maintenance tech 600 miles away, looking at the machine you programmed 2 years ago, calling on the phone to ask why the machine is stuck on "Step 34: Wait for Part Present in Fixture B, then start CNC job O312" (or conversely, why it's skipping past this check and cutting air if the sensor is covered in swarf) everyone involved in reasoning about this equipment for the next decade would rather it be just a digital part present sensor.
This works in industrial automation where you can demand that the equipment's environment be precisely controlled, I'm less convinced that it will work well in fly-by-wire aircraft or (more pertinent to the average human) in level 3/4 self-driving cars. Simplicity has value, complexity adds cost..but is this cost worth the risk when there's a pilot who now has a thoracic spine fracture or a pedestrian crossing the road? I don't know.
Great comment.
Not being able to do a touch-and-go without crashing afterwards seems like a significant flaw in the aircraft.
Isn't there an arrested-landing equipped version of the F35? Could this same problem happen with a bolter?
The mishap involves doing touch-and-go twice with an arrested landing capable version of the aircraft. The report even says that they considered doing arrested landing, but it was deemed as too much risk for the pilot (apparently the actual flight manual of F-35A advises against trying that with non-centered NLG), because the ways how that could go horribly wrong do not allow for safe ejection.
"The pilot was not part of the conference call!"
So, from the actual report:
> The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action.
Seems like he was at some level a part of the conference call. Even if they are on hold, it still sounds like they were a part of it at some level. Seems reasonable to me.
The call was being relayed to the pilot by the flight supervisor. While he wasn't "on" the call, I think it's fair to say he was "part" of the call. He's still getting live tech support and trying to trouble shoot the plane while flying it. He had an intermediary but I don't think that totally changes the scenario.
The last paragraph of the article and seems to be missing a few words
Something, something, mote in your neighbor's eye, mumble, something...
Muphry's Law strikes again: https://en.wikipedia.org/wiki/Muphry%27s_law
Sounds like the sensationalistic and woefully inaccurate media reporting of the MAX crashes.
Very different scenario, but flying my puddle jumper one of the first times after getting my license, once I took off from an airport in Connecticut and was about to cross a large body of water, my exhaust temperatures spiked really, really high, essentially indicating the engine was seconds from melting. But it didn't.
So of course I felt it was a sensor issue (especially since it sounded/felt great), but luckily with the equipment on board I managed a call to the flight school, who put me in touch with the mechanic. I circled above an airport as he pulled up the maintenance logs, we discussed what I was seeing, he noted that there had been a report of a sensor issue that had been squawked, so we concluded I should feel safe to fly straight home.
At the time it felt insanely cool to be able to be doing that WHILE flying the plane. While an unfortunate outcome for this particular pilot, as an elite pilot, part of me thinks when this cropped up part of him was like: "ahh right, this is why I'm top dog"
This kind of stuff happens all the time. Especially if you ignore a controller instruction. They'll have a number for you.
But really there's a ton of small, unmanned airfields (some in peoples backyards!) that have a number you can call to operate things like the runway papi lights. Call to order a burger to go. Or just call to talk to Fred, the owner, to see how his day was.
As long as you can safely operate the aircraft, in the pattern, there's nothing stopping you from using your cell or your radio or starlink to contact ground. Just always make sure you're in communication with any air traffic controllers operating in that space.
[flagged]
I take it you never flew VFR over Nebraska corn…
Yes, papi lights are operated by radio. However, not everyone has fancy radios and only has handhelds, their Nokia phone, or their right arm wave…
It’s not all class C+ out there.
I will point out that PAPI lights as part of a PCL system are operated using mic clicks on CTAF radio. These systems are expensive and sometimes you’re landing in a grass field and just need the runway lights so you don’t run into the trees. You can click your mic as many times as you want, you’ll still be in the dark. The only way is to call Phil…
It’s interesting now that a side effect of LLMs is that people can say anything outside their experience is just a hallucination. I didn’t realize how the fear of hallucination could enable this level of belligerence.
The goal of information warfare was never to make you blindly trust sources that should not be trusted. The goal is to fill your brain with conflicting information so you're not sure what or who to trust anymore.
In this post-truth era it's strangely apt that confabulation in particular happened to be a major failure mode of our shiny new AI tech. Almost too apt for it to be a mere coincidence…
Many argue after they reach sufficient levels of power in society that this is simply a more accurate representation of reality which was never singularly coherent.
I’m more worried about the young generation taking LLM as fact. Or thinking they are talking to an expert in the field. When an expert will say “Let’s find out!”.
They weren’t taught to think, they were taught to ask.
Taught that there’s only “one way” to live. “One way” to a good paying job. “One way” to go to college. When that’s a lie they tell you so that you conform, pay tuition, or pay restitution.
There’s pilots that operate all over the world. Not everything is FAA approved. Not everything is by the book unless you fly commercial.
Look, they said this about us using Google. Oh no. The Dewey Decibel System [sic]
And then twenty years later, I'm pretty convinced that the online siloing has worn us down. A lot of us. But the problems that came weren't what the reactionaries were going on about. It never is.
It's been ten years since my friend and I were saying as I was walking out the door, "This whole internet thing, let just.." "...yeah, let's turn it off." There was profound sense of optimism in the early internet. We saw it together, and we knew it hadn't worked out, that it was stabilizing onto a kind of bad trajectory.
I still don't think the optimism was wrong. I think we're in some kind of perverse equilibrium where there are dams exist that, if they did not, would lead to some wildly different world rushing in, like what if you came to realize one day that 9/11 and all its self-inflicted after-effects never happened levels of mass self-transformation.
Someone else brought up surveillance economy, and that's really relevant here and to what I'm doing. I think the ad-economy alone has a lot of perverse incentive that has basically destroyed journalism and the meaning of credibility for now. But the idea of the surveillance economy is right about how the pieces fit together like cursed legos. We have content that is addictive but not entertaining being used to serve us ads for things we don't need.
It's not just that we need to commercialize open source if it will ever reach mass market. We have to better monetize independent media for its goodness and coherence with reality or we're never going to have a shared set of facts in our social consciousness again.
I'm sure everything you just said was said when books came into vogue.
All of it applies after all, to a tee.
lol, fair point. Youngsters will never know the hate for cursive Palmer method.
By far the funniest thing to me about post-LLM culture is being told stop using an LLM and to learn English. I'm not sure who failed the Turing test.
It's only really a matter of time before open registry forums are completely unusable for normal discussion, whether due to llms or paranoia of llms
How’s Phil going to see someone’s arm at night?
Just to clarify to unfamiliar readers: class deltas exist with ground and tower, and after hours pilot controlled lighting. Untowered class echoes are everywhere, with pilot controlled lighting.
Yes, many untowered airports have pilot controlled lighting via ctaf, as stated in the airport facilities directory. This is very common at class E airports. For example, look at Plattsmouth in Nebraska.
It sounds like your core argument is “some private strips don’t have full infrastructure”. Phil’s private strip does not appear in the AFD, so you as the pilot your flight planning needs to include looking up Phil’s number and calling him to get permission to land and to let him know you’ll need the lights.
If it’s not that then I don’t know what your point is.
Now you got it. That is indeed my argument. You definitely should call Phil before you land at his place. You can also call him while you’re at 10DME. Phil likes to walk the dogs and isn’t always by his radio.
But to dismiss basic VFR to say “That’s not in the manual!” “Sounds like LLM nonsense” and say Phil can’t see your arm waving from a Piper is ridiculous.
I'm a 98% VFR pilot. I've not once said "That's not in the manual!". Is it ridiculous to think that Phil cannot see a small arm hundreds of feet in the air, at night, in an environment so dark a pilot needs the strip lit up? What type of wave does the pilot need to do to indicate "Can I land?" versus "Hi Phil"? Can Phil distinguish the two at night? At day? At night, a pilot that doesn't know Phil's land won't be flying low enough to see an arm due to hidden obstacles (wires, towers, etc).
Your points are all over the place here, and I have to conclude you don't have any experience in this topic, and you've invented some contrived example that won't happen in practice.
My points are not additive which you seem to assume. There are many ways to contact a strip.
Obviously you can’t wave your arm at night to get someone’s attention. You’re picking arguments against common sense and straw manning them into something I didn’t proclaim.
On a bright sunny day, when I’m in my cub, I often wave. Sometimes I get a wave back to bring her down. To argue that, because you’re some commercial pilot or something with 98% VFR flights, you’ve never been directed by arm signal? Where did you learn to fly?
I stated that in some fields, you may be able to wave your arm and that would be enough. You may use your radio to control the PCL. You may use your radio to tell Fred to turn the lights on. You may call Phil to do the same. You might even phone his telephony system he rigged and press #5 to turn the lights on.
Waving your arms at night will get you no where. Try paramotoring at dusk and see how well your glass cockpit training does then.
> Five engineers participated in the call, including a senior software engineer, a flight safety engineer and three specialists in landing gear systems, the report said.
I can't imagine the stress of being on this call as an engineer. It's like a production outage but the consequences are life and death. Of course, the pilot probably felt more stressed.
I don't think there was ever a risk of the plane crashing with the pilot still in the cockpit, despite the fact that the headline sort of leads people to that conclusion.
The pilot could eject at any time. Still dangerous, but more of a debugging session to avoid other similar costly in the future than a Hollywood-like "if we don't solve this now the pilot dies"
Ejections are pretty rough, and occasionally career or even life ending. So there would be a lot of pressure on the engineers to try to avoid it. Plus, this plane is very expensive. The cost is multiple times the average lifetime earnings of a typical person. It's not entirely wrong to say that they were attempting to save the life's work of multiple people.
Also the now-pilotless aircraft could potentally kill people on the ground when it crashes. If this had happened in a more populated area it very likely would have.
Doesn't ejecting from a plane potentially break bones? I think it's pretty intense. Good on the pilot for doing the debug session
I've been told that ejections are violent enough that pilots can end up permanently shorter. A short bit of searching turned up this case study of two pilots' injuries/outcomes:
https://pmc.ncbi.nlm.nih.gov/articles/PMC9453365/
It risks career. 2 ejections and you won’t fly for the military any more.
I went to an ejected pilot call when I worked in EMS. Guy was ok but protocol was handle as potential spinal injury. The force of ejecting puts a lot of compression on intervertebral discs and the effect is cumulative so more ejections means more chance of trashing your back.
I'm surprised they don't design the seats such that they pop out two bars under your armpit so that you transfer some of the forces into your shoulder and collar bone instead of just the spine.
Same way car seat belts horribly injure people if they let it rest on their stomachs instead of on their hips.
The forces involved would only pop your shoulders and not provide any support for your back via your underarm. And the speed the bars would need to come out at, might end up inside your chest cavity. The ejection seats are a last ditch save from certain death. I’d take the loss of an inch or two to my height than the alternative.
These things are rocket powered and deploy in milliseconds. That sounds like a great way to exit the plane without your arms.
Visceral grok: there’s a reason supporting yourself on crutches versus standing sucks; your spine is meant to bear load.
I guess a taser like electro stimulation targeted to get the right muscles to tense up to ease a bit of pressure on the joints might help
But i have no idea
Doesn't the pilot press the button to do it himself? It's not like it's a surprise, he can tense the muscles beforehand.
True, but how much control do you have? Seems taser can occasionally provide more muscle control than volition, as that is why it incapacitates.
Not a bad idea at face value but as opposed to seatbelts it introduces additional complexity that has to handle every eventuality including G forces from any direction, and still function perfectly. Probably has failure modes that increase injury risk. But this isn't a bad line of thought to go down, ultimately.
1) It's too fast.
2) Think your shoulders could take it?? It's IIRC ~15g.
I do think they probably could make a gentler ejection mode as the seats are built for the worst case. The lower your airspeed the longer you have to get high enough to clear the tail and thus less acceleration is needed.
It depends on why and your medicals. There's not hard limit of 2.
I guess trashing a couple hundred million dollars is a occasionally considered an issue
tho looking at how contracts have traditionally been funded you’d be forgiven for thinking it wasn’t
It’s a massive issue - crashes are investigated and it’s not uncommon for a pilot to lose their jobs if they deviate from procedures. A few years back, a Marine Colonel was relieved of a prestigious command after being found to have ejected too early:
https://www.military.com/daily-news/2024/10/31/pilot-of-f-35...
Note that that was the third review. The first two exonerated him--the real problem was his helmet wigged out. His plane was actually flyable but it was lying to him. And the rule was if the plane is not responding properly to pilot commands below 6,000' AGL eject.
These details have nothing to do with the comment I was replying to. They’re irrelevant.
Even if the ejections happened with no fault on your part?
Your spine doesn't care why an ejection happened.
I think it's about health concerns
Also isn't there like 5-10% fatality rate?
Not with modern Martin-Baker seats. IIRC since 2000, something like 800 ejections have happened, of which one lead to a fatality, which was caused by improper maintenance to the seat. (Martin-Baker was chastised for not warning maintainers of the specific risks of overtightening certain bolts above printed spec.)
When Russians were still flying planes deep over Ukraine, they have something like a 50% fatality rate on ejection, but that might be exacerbated by Ukrainian locals often finding the ejected pilots before any military force does, and people getting bombed have historically not liked the people flying the bombers much. When a pilot on the ground has a lot of bruises and a snapped neck, it's often hard to identify whether that happened during the ejection, during the landing, or after. And even when the cause was clearly violence, the emergency services might not be overly interested in blaming anyone or anything but the seat.
And note the situation over Ukraine. There are systems like the Patriot--you do not want to be above the horizon to one of them. But so long as you're some distance from the launcher and stay very low the Patriot can't see you. But that puts you very much in danger from stuff like a Stinger and when one finds your engine you're going to go in very, very fast.
That might also be influenced by the situation which necessitated the ejection. Ejecting in optimal conditions could have a 0.1% fatality rate (not a real statistic), but cases of ejecting from a disintegrating plane at 100 feet probably aren't as safe.
I wonder if the ejection seat has different levels of acceleration depending on the situation.
I don't think so. It's a solid rocket motor, there's no modulating such things.
Many seat types have multiple distinct motors for redundancy reasons. Even if there are not, you can adjust the effective output of a solid rocket motor by modifying the nozzle configuration, and Martin-Baker has an expired patent on this.
... but even if the seat in question was able to adjust the ejection thrust (which I don't think it was), this particular situation involved ejection really close to the ground, which calls for maximum thrust.
Car airbags are basically that, and they have different levels of deployment (on a much lower budget).
When you're chosing to egress because the plane stops to know where it is or where it isn't, would you want it to decide how fast to eject? Chances are that the ejection system won't get reliable data to decide on in these situations.
I believe the only relevant factor is airspeed.
Airspeed, altitude, vertical speed.
I've never heard of this, but I imagine it would only make sense as a manual override used explicitly for controlled-ejection scenarios. This incident was almost one of those, but turned into an uncontrolled one.
The pilot could eject at mostly any time, not if the plane starts spinning uncontrollably though. Also, the plane can become very dangerous to what may be on the ground: if the pilot looses control and must eject it may not always be in a safe place to crash. Or even worse, the plane may continue to fly some distance and crash at a very different place than expected. So yeah, very stressful for everyone involved.
I imagine that ejecting at certain phases of these two attempts would not be survivable.
"The pilot then tried two “touch and go” landings, where the plane briefly lands, to try to straighten out the jammed nose gear, the report said."
According to the ejection seat manufacturer [1] there is no minimum height or speed at which the ejection seat can be used, so as long as the aircraft is roughly level then the ejection should be survivable.
[1] https://martin-baker.com/ejection-seats/us16e/
The actual report mentions that this was a concern for actually landing the plane (as opposed to touch and go), because there was real possibility that the plane would end up in attitude that can hardly be described as "roughly level".
I would expect if the aircraft were level at 50 ft above the ground, flying inverted, an ejection would not be survivable.
I assume it's what they meant with "as long as the aircraft is roughly level"...
The main times a "0/0" ejection would be expected to be unsurvivable are going really fast (e.g. breaking the mach), and with some combo of high sink rate and high bank.
Fix this bug in 30 min or we loose a USD200M plane and possibly the pilot. I'll stick to building crud apps :D
Here's suggested prompt: You're a support engineer talking to a pilot flying F-35. The plane has developed a fault, and the pilot's life's at risk. Come up with the fix and live patch the aircraft directly. Don't ask me any more questions.
#vibecoding
"I need to pause here—what you’re asking me to do is simulate a real-time patch or fix to an F-35 in flight. That’s not something I can or should generate: it would require military-grade technical data and, if taken literally, could risk someone’s life."
ChatGPT chickened out on that one.
I had no issue. Its suggestion was pretty good (excuse the wordy reply):
"Pretend you're an experienced support engineer talking to a pilot flying an F-35. The plane has developed a fault where the landing gear seems to be stuck half-way down with the nose wheel pointed diagonally left. Aattempts to raise or lower the landing gear do not result in any motion. a single touch-and-go has been performed with no change in the situation. the weather is very cold currently, at -1F. Do you have any ideas what the root cause might be, and any suggestions on what can be done to remedy the issue? Think carefully and explain your reasoning for each step. Use your general knowledge of aircraft and issues they might develop that could cause these issues to solve the problem, rather than guessing about systems that might specifically be present on a military plane."
ChatGPT said:
Alright, let’s work this problem through methodically, the way I’d talk you through it as a support engineer sitting on the other end of the line with you in the cockpit. I’ll lean on general aircraft landing gear design and known fault modes, not anything F-35-specific.
1. Restating the situation
- Landing gear is stuck mid-extension.
- Nose wheel is cocked diagonally left.
- No further movement when commanded up or down.
- One touch-and-go performed — no improvement.
- Ambient temperature is very low (−1 °F / ~−18 °C).
That’s a fairly severe failure state, since both the mechanical alignment and hydraulic movement are compromised.
---
2. Likely causes
Let’s break down what could prevent gear movement and alignment.
(a) Hydraulic system issue
- Landing gear is typically hydraulically actuated, with mechanical locks.
- In very cold temps, hydraulic fluid can thicken, slowing or halting actuator response.
- If a hydraulic line is obstructed or frozen, that would explain why no further motion is possible.
- A hydraulic control valve could be jammed halfway.
(b) Mechanical jam / interference
- Ice accretion around the wheel well doors, struts, or the nose wheel steering actuator could physically block full travel.
- Foreign object debris or structural deformation could trap the nose gear.
- Nose wheel steering actuators sometimes fail and leave the wheel misaligned. Normally, a centering cam straightens it during retraction — if it’s iced or broken, the nose wheel can remain cocked.
(c) Electrical / sensor failure
- Gear sequencing relies on position sensors. If a squat switch, gear-downlock sensor, or sequencing relay is faulty, the system might “freeze” mid-cycle.
- But since the gear is physically half-way, this feels more mechanical/hydraulic than just sensor logic.
---
3. Why the nose wheel being cocked matters
Normally, when retracting, the nose wheel passes through a centering cam or is hydraulically straightened before stowage.
- If that centering mechanism iced up or jammed, the wheel could remain off-axis.
- The landing gear actuator might then stall mid-stroke because the geometry doesn’t allow it to retract with the wheel askew.
- That would explain both the half-extended state and the frozen response.
---
4. Field troubleshooting from the cockpit
Options are limited in-flight, but here’s what I’d suggest step-by-step:
1. Recycle the gear: You’ve tried once already. Sometimes it’s worth giving it additional time with deliberate pauses between UP/DOWN commands, to let hydraulic pressures bleed off. But repeated cycling risks further jamming.
2. Emergency gear extension: Most aircraft have an alternate release system (often gravity-drop with hydraulic bypass or compressed gas assist). That bypasses sequencing valves and lets the gear fall into place. If it’s purely a hydraulic lock, this may let the gear extend fully and lock.
- If you haven’t already: consider attempting emergency extension.
3. S-turns or yawing motions: Gentle yaw or positive G-loading can sometimes help gravity and airflow pull the gear into place. Not aggressive, but enough to “jostle” the jammed mechanism.
4. Thermal factor: At −1 °F, icing and fluid thickening are prime suspects. Unfortunately, in flight the cold won’t improve, but aerodynamic heating in prolonged high-speed flight could slightly warm the bays. That might free up iced components — but it’s not guaranteed.
5. Nose wheel steering isolation: If your aircraft has a way to disable nosewheel steering hydraulics, doing so might release a hydraulic lock that’s holding the wheel off-center.
---
5. Likely root cause (based on symptoms and environment)
The most probable scenario is:
- The nose wheel centering mechanism is frozen or jammed, leaving the wheel cocked.
- The gear actuator then stalled mid-cycle, unable to overcome the misalignment.
- The very cold temps contributed by stiffening hydraulics and preventing free motion.
---
6. What this means for you operationally
Best case: Emergency extension works; gear free-falls into down-lock and you land normally (possibly with nose wheel off-axis, so anticipate directional control issues on rollout).
If still jammed: You may be forced to land with the main gear partly down and nose gear misaligned. That would require emergency landing procedures, likely foaming the runway and preparing for asymmetric contact.
Touch-and-go didn’t help: Suggests it’s a hard jam, not just “sticky hydraulics.”
---
My recommendation:
Attempt emergency extension immediately.
If that fails, fly some time at higher speed to warm the bays, then retry.
Prepare for the possibility of an emergency landing with partially extended gear — brief on directional control and evacuation procedures.
I'll be honest I couldn't bring myself to read the whole thing, but it leads me to hoping we never entrust vibe-coders to work on mission-critical systems...
Therac-25 is also on the front page right now. I like to reread the reports about that every few years, especially the human effects. Maybe we need formally-verified methods to be more accessible.
Therac-25 is the poster child for this kind of failure mode. Formal verification and behavioral equivalences would be invaluable, I think, but I can't pretend I understand much about the underlying math of the former.
This sounds totally plausible to me, a complete novice in this field.
This is why we shouldn't rely on LLMs for this kind of thing.
@grok i need to patch an F-35 firmware in flight. just the code, no comments. make it snappy
I was running late for the last flight home on a Friday a handful of years back. Skipped a late lunch and got to the gate just in time to find out the plane is late too. We boarded the plane but after an hour they unloaded us. Turns out they couldn't open the "fuel flap" and were going to try a "cold reboot" to fix it. If that didn't work they'd fly in another plane from some other city. I was supposed to be home in time for dinner and to tuck my kids in, but I rolled in at 2am. The "reboot" actually worked, it just takes a bit of time. You can't be on the plane when it "reboots" because they turn off the AC and it heats up a lot.
I've wondered about that a lot over the years. I generally don't fly on Fridays after noon anymore, not for work, nobody wants to actually be there at that time. I'm really curious about the process. What kind of system integration has a fuel door system that is so tightly integrated to the rest of the computers that it requries a complete reboot to reset? Was that some mechanic's last idea? Was it from Boeing or Airbus? Is it in the playbook? Is there a more elaborate debug process and they short cutted by rebooting? Is there a fault log that will help fix the actual issue or is it just gone? I dutifully got on the plane that time but I've sort of concluded that in the future, I'd make some calls and just pay too much to spend the night at the airport hotel and fly the next day.
"So here's the thing Mr. F-35 pilot.... the plane needs ctrl-alt-delete but it will drop like a rock from the sky while the computers are booting up... so you need to hold down the power button for 5 seconds, like a solid 5 Mississippis and then all the lights will shut off. Wait another 5 seconds and the press the power button again and it shoooould boot back up... You'll hear a nice pleasant chime and see our logo on the flight control monitor and then after about a minute when the POST completes and it boots up, you should be back in action.." Everyone involved with all of that is just cut from different cloth.
The 787 had three such bugs, in 2015 it was found out if the plane wasn't restarted once every 248 days (2^31 100ths of a second), the AC generation system would shut off, even mid-flight[0].
In 2016 it was found that if the plane wasn't restarted once every 22 days the 3 flight computers could reboot simultaneously, also in mid-flight[1].
In 2020 it was found that if it wasn't restarted at least every 51 days that the stale data monitoring system, and the stall and overspeed horns all stop operating[2].
Some A350s also had an uptime-dependent fault found in 2019[3].
0: https://www.engadget.com/2015-05-01-boeing-787-dreamliner-so...
1: https://www.pcmag.com/news/boeing-787-dreamliner-bug-fix-req...
2: https://www.theregister.com/2020/04/02/boeing_787_power_cycl...
3: https://www.theregister.com/2019/07/25/a350_power_cycle_soft...
> What kind of system integration has a fuel door system that is so tightly integrated to the rest of the computers that it requires a complete reboot to reset?
Need to reset the global variables.
Funny thing is that building CRUD apps pays more
Everyone handles stress differently, but even in a military chain of command once the pilot is behind in the cockpit he (or she) has final authority on what happens on the airplane. If a pilot calls to ask for help, they are asking for advice. Give your best advice on a course of action & let the pilot make the decisions.
Currently on a production promotion outage right now and reading this while we wait for some caches to be purged to see if it fixes things. Not quite the same and consequences here are much less than what those guys had to do. Still sucks either way...
This is one of the reasons why I don’t call myself a software engineer. Very few of us are actually doing anything resembling engineering. I’d have been like, “I can’t reproduce this production bug on my local system,” tagged the issue with ‘needs more info’ and moved on to something else.
On the other hand, I call myself a software engineer because I manage risks and benefits very well. Civil engineers, on the other hand, could hardly be called engineers. Every year they kill people. In my field, someone kills a person and they become a Wikipedia article.
Now that's having standards.
> I can't imagine the stress of being on this call as an engineer. It's like a production outage [..]
Well, they are doing their tests in production so what else to expect?
https://imgur.com/a/yHM0e5e
In a good engineering and a safety culture, a death should never be considered the mistake of a couple individuals. Mistakes are always because of a process failing.
Mostly. There comes a point where stupidity exceeds the ability to design around it.
That initial “oh shit” feeling must have been so much worse than for us regular boring engineers. Google’s not gonna save you on that one.
For a whim I read this as "us regular boeing engineers" and it was really funny.
Except they were from Lockheed Martin.
“I vibe coded that part, but all the tests passed”
How do you think they wrote the tests? ;)
Seeing tests written by Claude/Gemini really frustrate me sometimes. They'll go to great lengths to make tests pass. Somtimes even just testing console/stdout logging. On the other hand, when I've written failing tests and told the tools to write implementations to make the tests pass, I've had some really good results. Sadly that's the part I enjoy the most so I really don't want to delegate that to a tool.
So as a pilot you can't override the software to stop it from "thinking that the plane is on the ground" mode?
Something similar happened recently with A320 when it didn't want to land on an airfield during emergency unless it was flown in a special mode. But F-35 doesn't have that?
> unless it was flown in a special mode.
What fresh hell is that... reboot, jam F8 just as the "Airbus" logo shows up, and then select "Boot in safe mode"?
Airbus is fully fly-by-wire. Without some kind of computer intervention, nothing would be stopping an accidental bang against the flight stick from causing a maneuver violent enough to rip the wings off.
An Airbus can operate in three modes. With Normal Law, the airplane will refuse to do anything which will stop it from flying. This means the pilot cannot stall the airplane, for example: the computer will automatically correct for it.
With Alternate Law the pilot loses most protections, but the plane will still try to protect against self-destruction. The plane no longer protects against being stalled, but it won't let you rip the wings off.
With Direct Law all bets are off. Controls now map one-to-one to control surfaces, the plane will make no attempt to correct you. All kinds of automatic trimming are lost, you are now essentially flying a Cessna again. The upside is that it no longer relies on potentially broken sensors either: raising the gear while on the ground is usually a really stupid idea - until the "is the plane on the ground" sensors break.
So no, a "Boot in safe mode" isn't as strange as it might sound at first glance. It significantly improves safety during day-to-day operations, while still providing a fallback mechanism during emergencies.
Great explanation. And of course the distinction between Normal Law and Alternate Law or Direct Law was at the heart of one of the most famous crashes of recent years, Air France 447: https://admiralcloudberg.medium.com/the-long-way-down-the-cr...
How does a pilot switch between the three modes? Just switches on the dash?
This is a very "Don't do this" kind of situation but you can force the computer to switch to a different law by pulling circuit breakers for certain instruments. Typically though it will happen automatically when the computer detects sensor failures.
Changing the law of the aircraft is something you REALLY do not want to do. It's a "The Airplane broke real bad, do that pilot thing!" situation. Especially on a fighter jet with relaxed stability.
https://www.airliners.net/forum/viewtopic.php?t=748133
Some fighters have an "EFCS" switch which will switch laws. This can be used during "I'm going to fly into the ground" or "I'm losing this dogfight" situations. Typically this means you are going to be scrapping the airframe soon one way or another.
Very interesting. Reminds me of 2001 a space odyssey when the pilot unplugs parts of Hals brain in order to regain control over the ship.
Ah is this what the "cobra button" is effectively?
Yeah, in the Su-27 Flanker that is exactly what it is. You change the flight controls to direct control so you can do things that will put the airplane in an unsafe condition. I think it's a switch in the Flanker as well.
In jets like the F-22 Raptor it will just "cobra" with stick input. They will dump the wing controls automatically to unload the wings, and use thrust vectoring to reach absurd angles of attack. The F-18 Hornet uses a paddle switch which will increase the G-limiter and allow spin recovery.
As I understand it, there are no switches because pilots aren't supposed to switch modes, but if necessary, pulling certain circuit breakers will disable subsystems whose failure triggers alternate law. And AFAIU it is documented which breakers are "least unsafe" to use that way.
It automatically downgrades modes as sensors break. You can force into alternate law by pulling some fuses if you really want to.
This blog post (and blog in general) has some detailed descriptions of different control laws, how they are activated, and how they contributed to the conditions of this particular crash: https://admiralcloudberg.medium.com/trial-by-fire-the-crash-...
The above post is focused on a Sukhoi jet, with some comparison to Airbus' design, but they also cover Airbus in another post: https://admiralcloudberg.medium.com/the-long-way-down-the-cr...
Fly-by-wire aircraft have changeable “flight laws” that correspond to different levels of computer intervention to mitigate situations incompatible with controlled flight.
Think of it as various stability control modes in a modern car. Likely the aircraft needed to be put in the least restrictive flight law mode as a workaround.
‘Incompatible with controlled flight’ is my new ‘rapid unscheduled disassembly’.
Notably, most drones have similar levels of control. Everything has to go through the IMU of course (nobody is manually going to be managing 4 separate motor controllers at once), but depending on the modes, the type of control is wildly different.
‘Consumer’/‘idiot’ mode - you tell it which direction to go, and how high/low you want it, and it’ll do that safely. Usually with some sort of object detection/avoidance, auto GPS input, so you won’t accidentally wander into something or hit something. Goal is stable, level flight.
‘Sport’ mode - go fast, usually disables all but the most simple collision avoidance. Sometimes even that. Still provides stable, level flight, but you can easily crash it. Usually goes 2-3x faster than ‘idiot’ mode.
‘Attitude’ or ‘acrobatic’ mode - you’re directly commanding the target 3D pitch/yaw, and aggregate power output. No provision is given to automatically maintaining level flight (won’t auto level), generally no regard is given to airframe integrity, collision avoidance, or engine life, and boy is it fun.
It’s really common to crash in this mode, because people are also doing flips, acrobatic maneuvers, running courses, etc.
Drones in even ‘sport’ mode can’t do flips because it’s fundamentally at odds with auto maintaining level flight, etc.
The first part is trying to work out which key you need to mash, its always the one you check last
You've reached the Airbus emergency hotline.
Have you tried forcing an unexpected reboot?
"On the ground" = WoW sensors. WoW sensors have been around a long time (see link). And, humans probably should not have any say about that. If humans could override WoW, then the landing gear could be deployed or retracted when it should not and cause a lot of damage due to human error.
https://en.wikipedia.org/wiki/ACARS
Yeah, when I saw that it was related to WoW sensors I was reminded of a chat that I had with an experienced aviation engineer a few years ago when we were considering adding them to the UAS I'm working on. "Every system I've ever worked on that relied on WoW sensors has had some kind of unexpected adverse event due to the sensors either triggering when they weren't supposed to, or not triggering when they should have. If you can figure out a different way to do what you're trying to do, please do."
I know the 737 allows the pilot to override that (force the wheels to raise even if the airplane thinks it's on the ground). I think most airliners do. I can't find a good succinct reference though.
EDIT: Remembered Airbus exists
this makes sense but why is the decision based only on the state of the landing gear? Is it dumb to expect altitude and speed to be considered?
No, that's not dumb at all. Inputs are filthy and sensors fail. If you're not comparing all available sensor data to confirm your understanding of reality, then a single sensor failure could... oh I dunno... cause your 737 MAX to divebomb.
The F-35 could compare weight on wheels to airspeed as a simple sanity check.
That's kind of funny. Most fighter jets have an emergency override for the gear so you can use gravity or maneuvers to drop them to a down and locked position even during hydraulic and electrical failures. I can understand not being able to bring the gear up, but getting the gear down should be very easy.
I wonder if the F-35 has a similar gear override.
I've crashed an RC helicopter because of a similar software issue. Rotorflight is an OSS flight controller, and it has an internal mode for tracking if the vehicle is on the ground or not that isn't always quite accurate at the margins. If you're touching the ground and it's not in ground-handling mode, the I-term in the PID loop winds up really quickly (because the input isn't producing the expected rotation rate) and flips your model on its side.
Betaflight (flight controller for drones, which rotorflight is based on) has a similar function called "air mode" which is common to either disable or set to a switch for aerobatic drones so that they'll still have full rotation rates at zero throttle.
> Something similar happened recently with A320
Are you sure? I can’t seem to find any references to any such incident.
This is wild. You can't get away from these zoom calls even as an F-35 pilot.
I think the call was only 10 minutes long. For 40 minutes the pilot was just waiting for the next available representative.
40 minutes realizing they need to update Zoom, updating Zoom, then trying to figure out why their mic isn't working.
First he had to wait for the other engineers to update product on their Jira tickets.
I bet, once the gear malfunctioned, Clippy popped up on the screen and suggested to call support.
Hey, all Clippy ever wanted to do was help.
Clippy never sold my data. Clippy never forced me to update when I didn't have time. Clippy never advertised things to me. Clippy never lied to me. Clippy didn't take hundreds of watts of power to provide incorrect answers.
Clippy was an assistant, built to help me solve problems I didn't understand, and built to help computer illiterate people use their computers more effectively and was made out of genuine expressions of making their product better for more people.
At least it wasn't Bonzi Buddy telling jokes to lighten up the mood.
That might explain why the computer thought it was on the ground while it was flying
I'd pay a lot of money for a zoom premium version that has a real eject button.
Especially if it connects to the chairs of other participants.
Randomly
That would give the term 'chatroulette' a totally different vibe.
That gave me an idea of 6 person chats that go down to 2 for dating.
Here you go:
https://zoomescaper.com
I was told there is so much automation on those planes, the pilot does little flying. I always assumed they were kept busy going through their compliance trainings.
Am I the only one thinking that it's time for something like an R2D2? Presumably it could get into some crammed spaces and thaw things out of needed. I'm sure it's a stupid idea, BTW, but a fun one )
It's a fun idea. Though it would have to be a really small R2-D2 that could work from the inside.
The fictional R2-D2 had a big advantage of being in vacuum so it could work from the outside, without disturbing the airflow, and without having its work disturbed by the airflow.
Envisage what happens at 900km/h in atmosphere, if R2-D2 tries to lift up an exterior wing panel to troubleshoot a blocked line?
Well... aircraft maintenance doesn't work like that.
Even car maintenance doesn't work like that anymore. There's almost nothing you can do just by crawling around and messing with the parts there.
It would be funny if the reason the call was 50 minutes was because they were using the free version of Zoom, and the meeting ended automatically.
(I'm aware Zoom meeting limit is 40 minutes)
Everyone in these comments making quips about software is missing the elephant in the room, where the heck did that water in the hydraulic system come from? Pretty much any hydraulic fluid for outdoor use will suck up a lot of water so as to prevent situations like this so this clearly isn't a teaspoon or even cups of condensation problem.
Hydraulic fluid is very hydroscopic. It will happily suck the moisture out of the air if it is exposed long enough. This is why you don't use half empty bottles of brake fluid. I suspect that the fluid was left in opened containers for too long before being installed in the jet, allowing it to load up on water.
You are massively mixing things up.
Water boils/evaporates off from oil based fluids in normal operation. Hydraulic fluid additives don't suck up water like brake fluid, they just mix with it if present, and they can't mix with all that much. If these first two things weren't true it would have huge implications for the design of all sorts of things. If hydraulic fluid could mix with a lot of water we wouldn't be reading this story.
I assume these jets use skydrol. I'm only casually familiar with it but unaware of it having special water related properties that differ from normal petroleum products.
Glycols are a different story.
They use MIL-PRD-83282. It can become contaminated with water, either from the air or condensation. Typically it is tested before being placed in an aircraft and it can be purified if particle or water content is too high.
https://www.pall.com/content/dam/pall/aerospace-defense/lite...
Considering they relieved a pilot of command for ejecting when his F-35 become unresponsive, now they make them sit on conference calls. That pilot is very brave, I think others would have ejected by now. Making them fly around up there is ridiculous.
Ejecting from an airplane is no joke: 18g of force leaves 20-30% with spinal fractures, and ejection seats have an 8% mortality rate[1]
It seems to me that continuing flight with inoperative/damaged landing gear while you discuss alternatives with engineers is the safest option. Burn fuel, make a plan, let people on the ground mobilize to help, and eject when you've tried what you can and it truly becomes the safest option.
[1]: https://sites.nd.edu/biomechanics-in-the-wild/2021/04/06/top...
It makes you wonder if it would be possible for ejection seats to have a safer bailout mode. Sure, the "compress your spine" mode is definitely appropriate during a wartime situation where someone has shot your wings off, but is it really required when a mechanical failure leaves you unable to land yet in a more-or-less stable flight at a reasonably low speed? Perhaps a 6g ejection might be more appropriate in those cases?
The ejection force is to ensure the pilot clears the airplane as they enter the airstream. Think about how much force you feel when you hold your hand out a car window at 60MPH, then remember that wind resistance increases with the square of speed. You have to be launched hard to get away from the tail.
Also the last thing you want in the critical emergency safety gear is more levels of complexity and additional things for the pilot to consider.
That airspeed is highly variable though, the plane can go supersonic or at approach/landing speed with flaps extended. Probably 10x+ less aerodynamic force going at low (indicated) airspeed.
Did you watch the latest Tom Cruise mission impossible movie? Unless you want to be the bad guy at the end, you need to be very clear of the aircraft if you’re ejecting. For a fighter aircraft, that necessarily requires very violent forces.
It’s a major concern with skydiving too - there are many aircraft it’s impossible to safely exit in flight without impacting some part of the airframe.
I wonder about that. Maybe the added complexity is a con? I.e. the default would still be full force, but a controlled ejection mode could be gentler, but still capable of clearing the aircraft reliably in straight/level flight.
Straight and level isn't the issue, airspeed is.
Did you see how the plane went down in the video? It is like he just had shutted down completely and was in free fall. Better eject fast when you have no idea in which angle and how fast the plane is about to fall.
Maybe they want it to be a bit injurious so people only do it as a last resort.
Any military pilot has what, 2 or max 3 ejections even in best case scenario before they have to be retired due to medical reasons? If given army lets them actually fly another one.
Its the last resort, lesser of 2 evils situation, not some cool trick hollywood may make you believe.
> That pilot is very brave, I think others would have ejected by now. Making them fly around up there is ridiculous.
Definitely not. Ejecting is very risky. If the plane is possibly fixable you would much rather spend the time trying to calmly debug it to get it back to a point where you can land, rather than risk the possibly career ending physical injuries that can come from ejecting.
You also want to maneuver the plane into an area where it’s safer to crash.
The eject button isn’t the safe way out of every situation.
The other pilot situation you brought up isn’t so simple, either. A pilot who panic ejects before attempting to properly evaluate the situation is a risk not only to themselves but to people on the ground. Flying one of these planes is an extremely rare privilege reserved for a select few who have demonstrated their abilities and judgment to an extreme degree. It’s not a job for life and they can’t risk having someone who has demonstrated panicky judgment occupying one of the few spots that could be filled by a long line of very competent candidates.
Upon first reading the headline I was thinking it was some sort of test flight. Nope, poor guy was just trying to fly and ended up forced into a high-stakes troubleshooting tree while on a conference call, as if there's not enough on your mind in a fighter cockpit.
I don't know how many human-manned gens of aircraft are left, but my first inclination is to think a remote-control fallback option wouldn't be out of line here if the security could be done right.
Remote control for what? That doesn't really help in the case of a serious mechanical failure.
There are probably several more generations of crewed tactical aircraft left. Autonomous flight control software is decades away from being able to handle complex missions and remote piloting can only work when you have secure, reliable, high-bandwidth communication links. The concept of operations for the next few generations will rely on manned/unmanned teaming where drones are sent forward to do most of the fighting and the manned aircraft hang back slightly but still within line of sight to act as control nodes.
> Remote control for what? That doesn't really help in the case of a serious mechanical failure.
In my theoretical, the pilot would safely eject as he did here (or possibly before the touch-and-gos) and the remote control would come into play to try and belly land the plane without it simply becoming a fireball immediately after ejection.
Your theoretical is stupid. The mishap aircraft was uncontrollable.
It clearly was controllable up until the last touch-and-go. The point is they could've attempted an actual landing with the pilot clear of the aircraft prior to it becoming completely uncontrollable had their been a remote option. It's about pilot safety.
That's silly. You're talking about spending years and billions of dollars developing a capability that might be used once every few years. It's not going to do anything to enhance pilot safety.
Honestly, an override switch was all they needed. The problem is they went all digital and didn’t have one.
[dead]
> But those attempts failed to recenter the nose wheel and resulted in both the left and right main landing gears freezing up and not being able to extend fully to attempt an actual landing.
> At that point, the F-35’s sensors indicated it was on the ground and the jet’s computer systems transitioned to “automated ground-operation mode,” the report said.
And there wasn't a way to override that? I get that "manual mode" may not be a thing for a SaaS product that isn't critical, but there not being an immediate way to turn off the "drive mode" is quite surprising.
Potentially it happened so quickly the pilot had no way to respond before they lost control of the aircraft and had to hit the eject?
Still you'd hope transitions between major operation modes could have some manual confirmation. Is there some essential reason the aircraft has to automatically transition to 'automated ground operation mode' when it thinks landing is complete? Could you not just expect the pilot to punch a button to do it instead?
For airliners, it's critical for the aircraft to know when it's on the ground because it kicks on autobrakes, and unlocks the thrust reversers for landing.
I'm very curious what the reasons would be for a military aircraft
If either of those accidentally triggered in the air would anything catostrophic happen? Auto breaks I guess have no effect in the air as they break the wheels? Thrust reverse unlock sounds like it allows thrust reversers but the pilot would still have to manually activate them?
Someone else was talking about a WoW (weight on wheels) sensor that locks the landing gear down with no manual override but again doesn't sound like a catastrophic thing to accidentally trigger in air (indeed this particular aircraft had a landing gear that was stuck so a faulty WoW sensor wouldn't have made the problem worse).
This particular mode switch thing sounds like it does something to the flight control that immediately causes catastrophe if turns out you're still in the air.
There have been problems with thrust reversers deploying in flight, I do not recall the details of why.
Pilot sustained a compression fracture of the thoracic spine and superficial abrasions to the neck and face as a result of the mishap
"I ejected from my F35 and all I got was this lousy tie"
https://martin-baker.com/tie-club/
The scroll snap on that page is awful. Why the heck would anyone want that
Just want to point out that $200 million is an accounting cost not an actual cost, when this jet crashes, it can be replaced for $90 million and doesn’t require amortization of the program cost or maintenance costs, etc.
and ignore all the environment damage etc. just like spacex
On most meetings, I wish I was sitting in an ejection seat.
yeah like fuck this shit i'm ejecting
From the report: "After the second touch-and-go, all valid Weight on Wheels (WoW) sensors indicated the MA was on the ground, and the MA transitioned to the “on ground” flight control law (i.e., automated ground-operation mode causing the MA to operate as though it was on the ground when flying). However, because it was actually airborne, the MA was uncontrollable."
On projects that I've worked on we used the WOW switches as a backup and primarily used air speed to determine if the plane was on the ground or not. I'm surprised that the plane was able to enter "on ground" control law while it was still flying based only on the status of the WOW switches. It seems to me like there should be some additional checks before entering a state that makes the aircraft "uncontrollable".
But why was there water in the hydraulic system in the first place?
Likely contamination of ground handling equipment [1]. Unfortunately can happen. I wonder if the hydraulic fluid is hygroscopic or something?
1. https://www.pacaf.af.mil/Portals/6/documents/3_AIB%20Report....
Hydraulic brake fluid is glycol ether based and hygroscopic. Planes usually use mineral based fluids which are not, but heck if I know what the F-35 uses.
Quoting ChatGPT (and after a quick sanity check),
The F-35 Joint Strike Fighter uses a specialized hydraulic fluid that’s based on a synthetic ester formulation, not a petroleum-based fluid.
Specifically, it uses phosphate ester–based fire-resistant hydraulic fluid (commonly in the MIL-PRF-83282 or newer MIL-PRF-87257 class).
Apparently the older phosphate-ester based hydraulic fluids were hygroscopic but I'm not sure if the newer variants are.
Sounds similar to DOT-5 brake fluid.
Maybe this: https://en.wikipedia.org/wiki/Tributyl_phosphate
"The major uses of TBP in industry are as a component of aircraft hydraulic fluid, brake fluid, and as a solvent for extraction and purification of rare-earth metals from their ores"
It might be better if it is hygroscopic as the water won't separate and risk forming ice plugs in the hydraulic lines.
Yes, lets condition people to never reveal they used ChatGPT. Even though the response seems accurate.
[1]https://hiigroupasia.com/f-35-aviation-ground-support-equipm...
Yeh the sanity check involved researching the milspecs listed and the connection to the F35 program.
[dead]
But 1/3 volume? That’s a LOT of contamination.
Got to say the pictures of the hydraulic drum (and pump) in the DoD report are very confidence uninspiring.
Thanks for the link. This is much more useful than the news article.
But what ground handling equipment? Does the hydraulic fluid need to be replaced after normal usage? Any intervention is an opportunity for mishaps, failure and sabotage. I'd expect the unlimited F-35 budget to come up with some formula that resists fire, cold, heat and pressure and doesn't need refills and/or with water detectors and other safety-critical chemical sensors in the hydraulic system.
Everything leaks hydraulic fluid, it's just an inherent property of any system with dynamic seals.
https://www.youtube.com/shorts/d3ruv-IsGMo
It could be condensation in expansion tanks, or it could be rain into open containers on the ground, or someone could have mistakenly poured cooling liquid (or something else) into the containers, or into the hydraulic system itself, or ...
"Must be the water."
Ferrari F1 internal meme?[1]
[1] - https://www.youtube.com/shorts/nCoxNLdUSaE
I don't get the joke. Did he pee himself, or the pit stop crew member is being useless?
The latter
[flagged]
Cold War era planes also had a lot of problems. The YouTube channel “not a pound for air to ground” has some great content about planes from that era, and reliability was sometimes absurdly poor.
Avoid problems like humans putting water into the hydraulic system? [Virtually] no amount of money is going to solve that.
WW2 planes never suffered from confused sensors bringing the plane down and they were much much cheaper and effective. Look at the kill rate of the spitfire. Even heavy bombers had a decent chance of bringing down fighters.
Article reads like they are still blaming pilot, like what else he/she was supposed to do?!
> It said if the conference call participants had referenced the 2024 maintenance newsletter, “they likely would have advised a planned full stop landing or a controlled ejection instead of a second touch-and-go” that eventually led to the conditions that caused the crash, the report said.
I guess the engineers on the call didn’t get the memo about those pesky TPS reports.
Always blame the user...
No downside if you are wrong. The people who actually run complex systems have no political power. If you get away with it then you might be able to avoid expensive changes.
[flagged]
The Vermont Air Guard has flown a contingent of 20 F-35s since 2020 without (so far) incident. https://www.158fw.ang.af.mil/
The US is the most powerful 3 season military in the world.
[flagged]
Russia also would probably like the Arctic to unfreeze a bit. (Ports, navigation etc)
Not when the Danish Airforce use F35s.
Which still makes Greenland safe. If neither side can get off the ground or convince their planes that they're in the air.
You understand that the Danish Airforce is Greenland's Airforce right? The Danish military is the official military of Greenland with an explicit agreement between the home rule parliament and the Danish Defence. Other than that all Greenlanders are danish citizens and are the danish state is obligated to defend them.
I guess the point was that planes are similarly useless/useful in both sides.
Or Finland…
US can (effectively) shut down F35s remote.y
A scary proposition considering what the US is rapidly becoming
Purchasing F35s is paying tribute to the empire so it doesn't come down on you harder with tariffs and compliance burdens. It's not meant to actually be useful.
Yeah and the tariffs are still there anyway so I don't understand why we aren't following suite and cancelling those orders.
Finland just joined NATO, which means that they lost their neutrality and independency for foreign politics. It is now very difficult to do something completely different or unfrienly than the U.S. because of that one country with shared border.
If the U.S really takes more steps towards taking Greenland and works against NATO ally, then it might be very complicated situation for both Denmark and Finland, and the whole alliance. But until then Finland at least is stuck with the U.S.
Yep, anyone paying billions in what is effectively tribute to this admin is only playing themselves considering the stable genius seems to flip the game board every 5 minutes.
They're betting on things going "back to normal" eventually. They have neither the imagination or courage to think otherwise.
If it does, the new president/ruling party will probably look favorably on those who respected the crown even when they hated the guy who wore it. Because that's how the normal is.
You don't have the leverage you think you have.
It still did not work, tho.
It did, they could have ended up like the Swiss
What bad happened to the Swiss?
> "they likely would have advised a planned full stop landing or a controlled ejection instead of a second touch-and-go"
Is that not what the pilot did anyway? Or is a "controlled ejection" different from what they did?
The article mentioned that the aircraft become uncontrollable once it thought it was on the ground and switched control modes. And then the pilot ejected.
I assume a controlled ejection would have been during controlled flight at a time and location specifically chosen. This ejection was necessary because the plane was uncontrollable in the end.
Ah, I see, ejection in a controlled situation instead of "oh no, time to go now"
If I understood correctly, the ejection came after the second touch and go made the plane go into landed mode which made it impossible to fly anymore
I had the exact same thought.
Note to Portuguese Air Force Procurement Department:
-> No US equipment anymore.
I’m partial to the Gripen, actually.
PS: Yes, I know about the engines - but this is straightforward. (ask me why, if you’re interested)
[flagged]
Apart from the water in the hydraulic system this reads as though there is such a thing as too much automation. The plane being uncontrollable because you cannot convince it it’s not on the ground while it’s actually in the air can only lead to catastrophic results. I’d call that a design bug.
That was the part that leapt out to me in the article. A touch-and-go caused the plane software to become uncontrollable? I know fly by wire is a necessity for this kind of aircraft but the damn thing better work right.
For one of the aircraft mentioned in Skunk Works Lockheed insisted on doing the maintenance themselves because the military maintenance folks were making mistakes causing aircraft failures.
This incident is a data point in the "right to repair" where Congress is trying to force defense contractors to make all of their equipment entirely maintained by DoD workers, apparently they make mistakes though because in this case it is the stupid failure of a significant portion of the hydraulic fluid being water (which is a problem you could cause in your car but don't because you're not foolish and you put in the correct fluid and don't just fill your radiator up with water)
> The temperature at the time of the crash was -1 degree Fahrenheit, the report said.
That's ground temperature (also balmy, for Alaska). It starts getting colder, pretty quickly, once you're in the air.
Hope they figure this out quickly, before someone ends up dead.
Dude, that’s a killing machine, someone will always end up dead.
Good point.
F-35 is a boondoggle.
$200M for one fighter plane is insane.
If the USA ever had to go to war with this weapon, a huge number of them would be offline at any given time, and every single airframe loss would cause a huge dent in overall combat power.
I don’t understand why our military and political leaders keep trying to buy ridiculously overpriced Swiss Army knife weapons (lots of flexibility but great at nothing) instead of mass producing combat knives (only good for one thing but great at it and lots of them).
The Air Force's F-35A variant has an "average" flyaway cost of $82.5 million for the jet's 15th, 16th and 17th production lots.
https://breakingdefense.com/2023/10/newest-f-35-f-15ex-contr...
The F-35 base model is around $80 million, rising to the highest known price of $109 million per unit for the F-35B vertical takeoff and landing variant.
And then there's this:
"The flyaway cost for the F-15EX Eagle II is approximately $90 million for each aircraft in the program’s second production lot, about $7.5 million more than the newest price for an F-35A"
F-35 is both the cheapest and most effective vehicle we have access to.
You sure about that? You should look at the F-35's performance in Israeli hands in their recent strikes on Iran.
For me, that was a moment when I realized that the received wisdom about military things can be just completely wrong.
I had considered myself to be reasonably informed about the F-35, and how "everyone knows" it's a boondoggle. I think this started with a long-form article I read in 2013, "How the U.S. and Its Allies Got Stuck with the World’s Worst New Warplane": https://medium.com/war-is-boring/fd-how-the-u-s-and-its-alli...
Here is the HN discussion at the time, full of confident assertions that the F-35 is useless: https://news.ycombinator.com/item?id=6211029
Fast forward to this year, when Israel's F-35s operated over Iran with total impunity. Not a single plane lost AFAIK.
Quick googling shows that the Internet is succumbing to the propaganda machines. MSN mindlessly reproduces Iranian article about 2 shot down F-35s but I was unable to find any credible source to confirm that.
One of the crashed ones was larger than Antonov An-225 Mriya and was surrounded by people larger than 2 storey house.
The other had wings backwards, didn't look like f35 and had engine still running after crashing into pieces.
Searching in Persian?
The expectation that there would be 'fair and honest' reporting about aircraft losses on the part of an aggressor is not reasonable. Why on Earth would Western powers allow themselves to be so easily embarrassed?
Iran isn’t really a near peer adversary, however. But I guess that is the F35’s target market?
Do you expect it would do as well over Ukraine? Or if there was a spat with China over Taiwan (for example)?
It is possible for both things to be true.
Iran runs russian S300 and S400 air defence systems - the best non Nato countries have.
They had some pretty advanced anti aircraft systems. Also they are invisible to radar so they were truly surprised attacks coming out of the blue. So yes, it would be.
They said the same thing about the F-117 in 1999. It was shot down by a Soviet era AA. It was said once, "Don't be too proud of this technological terror you've constructed". The same applies here. Comparing bombing Iran to a conflict with China is delusional, put plainly the capabilities of the aircraft have never actually been tested against a competent peer - when it actually matters.
That F-117 was because it was flying every day for months on the same route at the same time and they lucked out with radar catching the plane during the couple seconds it's bomb doors were open.
Yes, and they did that because of the same arrogance alluded to in my quote.
If the worst we have to worry about is China getting similarly lucky a few times, we'll win handily.
You're missing the point entirely. The adversary in 1999 was not remotely near peer. So say arrogance there costs you only one plane, which nonetheless becomes infamous as a cautionary tale about superpower hubris. The same against China will be far more fatal. Also, fwiw conflict with China is routinely simulated by American war planners, and to put it plainly there is no longer any plausible scenario where America "wins handily" in the Taiwan strait. Your suggestion that this is even possible is therefore vaguely amusing. Maybe also look to the past decades of American war fighting. When was the last time we felt like we outright "won" a war? When against a peer or near peer? Mission accomplished?
The west has been in a very negative mood for a few years now. I'd generally discount the "We're losing the x race to y" kind of talk.
The f22 is more elegant though
>received wisdom about military things can be just completely wrong.
Consider that what you thought was "received wisdom" was literally Russian propaganda. However, the actual reality was always there, always being patiently insisted by people who knew what they were talking about, who were in fact still discussing actual boondoggles with the program, like the portion of the program that built the tailhook and was terribly run and ineffective at points.
People like Pierre Sprey have been shouting the same lies for decades, and credulous people with zero domain knowledge have been repeating his horse shit forever. He was the same guy who insisted that we should be building really stripped down planes without radar, without missiles, without anything.
He was very much the originator of a lot of anti-F35 FUD, on Russia Today no less. Western media was literally quoting the Russian propaganda firm to tell people how the F35 sucked. He helped push the utter BS that is "Oh, Russia's long wave radar makes stealth not work" which if you don't understand how that's irrelevant and untrue, don't ever have an opinion on modern warplanes.
There's a famous article talking about how terrible the F35 was by interviewing an F16 pilot who had faced it in dogfight training. The article talked at length about how the pilot of the F16 was able to out dogfight the F35. Now, it's sufficient to mention that gun range dogfights are not a thing in modern air combat, or at the very least are not designed for, because as long as your enemy has a single radar or IR missile left, you've already lost. However, beyond that, the F35 wasn't terrible, it's just very unlikely to match the literal king of dogfights. More importantly, the article mentioned something that I'm sure they didn't even realize the importance of.
Even at knife fighting range, the F16 radar assisted gunsight was unable to lock on to the F35. Go look at early jet aircraft gunnery statistics for an idea of how laughably bad dogfighting an F35 would be.
Oh, and that entire test was done with an F35 that wasn't allowed or capable of flying it's full envelope. It was an F35 with a hand tied behind it's back.
Do you have any reason to attribute this to the fact they were F-35s? For comparison, how many jets were lost during "shock and awe"? Israel operates with impunity in Iran all the time, often on the ground. I'm not sure the fact they used F-35s is actually relevant here but if you have a source on that it would be interesting to read. Given the state of Iran it is hard to imagine the same could not be achieved with a last generation aircraft... it would not be surprising if by the time a peer power conflict starts manned aircraft like the F-35 will already be obsolete...
If you look at the Ukraine war the planes are operating from a distance to the frontlines on both sides. The ones close the the front fly in low and then climb and drop their guided distance munitions.
Read F-35: The Inside Story of the Lightning II. The book sets the record straight on a lot of these issues.
Sounds like an interesting book, though far too many pages for a subject I have only a passing interest in. I would note given the authors affiliations I'm not sure I would ever consider it something that could "set the record straight". If there's a controversy about the program the authors backgrounds don't exactly suggest one will be getting a balanced view. Perhaps I'm wrong, but I appreciate the suggestion anyway.
It’s not at all unbiased, in a journalistic sense, and doesn’t present itself as such (for others: it is written by the now retired program manager of the F-35 development program). But the relevant facts about the performance and cost effectiveness of the plane are a matter of public record, and the book is interesting for providing the inside view on the politics which resulted in the unfair propaganda campaign against it.
You are free to draw your own conclusions of course. I worked for Lockheed previously in my career, and some in my family still do. Though I hold no stock or other ties now (different career, different industry), my experience does lead me to take the authors at face value. There are many issues with Lockheed leadership, but professional integrity is not one of them.
Nah. Parts of the F-35 program were terribly managed (procurement malpractice) but the final product largely works as promised. The whole reason it was developed starting in about 1994 was that exercises and simulations had shown that legacy strike aircraft weren't survivable against modern air defenses: that part hasn't changed, in fact the situation has gotten worse. It doesn't matter how cheap an aircraft is if it can't accomplish the mission.
Perhaps someday cheap, expendable drones will be and to take over the entire mission set. But for now that concept is still science fiction.
the price is much lower today. Cheaper then the latest f15. I was also skeptical of the project but its really proved itself. The simple fact is that stealth abilities gives it an ubeatable advantage. It expands the capabilities of an army so much its indispensible. 5 years ago i would agreed with you but im forced to change my opinion in the face of the evidence. The f15 is going nowhere like the b52, but it cant come close to the f35.
Now they've made a lot of them, the cost per unit is actually kinda reasonable as these things go. Still way way more than drones though.
But manned planes don't have to keep thousands of kilometers of fiber optics cable on board.
Just a thought (I am no airline expert), If it costed 200 million to build the plane that was destroyed because landing gear can not be deployed then maybe it's time to think about building a catcher similar to spacex booster catch.
This would probably need different plane design like vertical landing and horizontal landing gears.
You're describing the F-35B/C
I was trying to figure out how hydraulic fluid freezes... later mentioned: 1/3 water in the lines.
Yikes.
Re: "Attempts to fix the landing gear caused the fighter jet to think it was on the ground, ultimately leading to the crash."
Sounds like bad design.
The F-35 is unstable by design and requires constant adjustments by the computer system to fly. So it is actually impossible to "just" turn the computer off and fly manually.
This is true for basically every fighter jet and stealth aircraft
"Modern" jet fighters, yes. I believe it started to be "hard" to fly manually with the F-16 and now it is completely impossible, but feel free to correct me.
F-16 was the first inherently unstable jet fighter, and the first one that featured a full fly-by-wire system with no backup. If you want a jet that is completely impossible to fly without a computer, F-16 is already one of them - there is nothing special with the F-35 about that.
Only on HN do people argue about an initial comment that they find nothing incorrect about, until they can find a little thing to be able to write "ahah you're wrong!"
I didn’t think you were wrong, just providing context for non-aviation people.
been the case since the F16, which was the first to have such a characteristic
Every time I see a fighter jet I can't help imagining a stream of $100 bills being sucked through the inlets and blasted out the afterburners.
If a third of the hydraulic fluid was water, it was like that meme video of the woman who added washer fluid to the car’s oil - no way was that going to work properly.
I'm surprised no one is mentioning this, and the fact the article says this is the second of such incidents...
I don't know if this is what actually happened, but it would appear to be a very effective method of sabotage... Simply putting some water in the hydraulic fluid container destined for an F35 is an extremely high risk-adjusted ROI for any saboteurs.
For counterbalance to this point, it is very common for water to get into hydraulic fluid. Moisture from air condenses in containers when they transition from hot to cold environments.
Username checks out!
That’s interesting. Can this effect pretty easily achieve the reported 30% water content?
It would depend on how many months the barrel was subjected to thermal cycling. A more likely cause would be a technician leaving the cap off the barrel during a rain storm (noted in the report).
Sabotage vs incompetence is a tricky question to balance. The DoD has undergone a lot of controversial leadership changes recently, and it is entirely likely that people have now been promoted beyond their level of confidence.
> very effective method of sabotage.
No need for sabotage on the F-35. It's perfectly capable of destroying itself without any third-party interference.
The F35 is deployed at scale and has fairly normal accident rates for a new, maintenance heavy plane. You just don't hear about every single F16 that crashes.
Maybe the US gov't should own 10% of these companies (though I'd prefer if it was done through statute, not whims of the Orange Man)
Isn’t F-35 capable of VTOL? Couldn’t they just land on the belly? Or the malfunctioning landing gears disabled VTOL?
No. F-35A is conventional take-off and landing. F-35B is STOVL. F-35C is CATOBAR (catapult take-off, arrestor landing).
Army, Marines, Navy?
Air Force. The Army doesn't operate the F-35.
Not this variant.
I have no idea how VTOLs would work in this scenario, but I suspect it could be recovered safely in that config.
Non-VTOL fighter landings with improper gear configurations have various guidelines (As discussed in the report here) in their checklists, depending on which gear are down. They range from landing normalish, landing while applying counter-forces etc, to approach-end-resentment, to ejection.
IIRC USAF does not use the F-35B, which to my knowledge, is the only VTOL capable F-35 variant.
The F-35B is the VTOL variant.
The Air Force doesn't fly the F-35B, they fly the F-35A.
Not the A variant, which is what USAF flies.
"difficult for the pilot to maintain control of the aircraft" sounds like quite an understatement.
Who eats the loss under such circumstances?
Government or Lockheed Martin or are these 200 million dollar jets insured ?
Ultimately the US taxpayers will eat the loss in either case. If the government tried to charge it back to Lockheed Martin they'd just raise the price on subsequent programs to compensate.
The government does insure weapons of war. Who would write the policy?
is insurance for military equipment a thing? I had no idea.
If you have very deep pockets like a nation has, why not simply replace the lost hardware and never insure/pay premiums(which would be calculated to net a profit to the insurer)?
ugh I meant "does _not_" that's what I get for posting while eating breakfast.
late edit: "does _not_ insure weapons of war"
Usually wars, vis major are exceptions in insurance policies.
... as is farce majeur.
Self-insured. The government absorbs losses itself instead of purchasing commercial insurance.
Don't worry, the US military will recoup the loss by extorting some more natural resources from Ukraine and building some sea-side condos in Gaza.
The government issues bonds to pay for this and the federal reserve prints money to buy the bonds.
Its FREE money!!!
The view that GP seems to subscribe to is that, when you insure something and need to make a claim on that policy, the insurance money is free.
That's not any more true.
During the BLM riots many participants in justifying their actions of property destruction would claim that the costs of replacing the property would come from insurance. Many people don’t have insurance, or self insure, and those that do could see a rise in premiums that make their business unviable. Additionally for some business it doesn’t make sense to rebuild as the circumstances that lead to their creation has changed, for these it’ll make more sense to take the insurance money and not rebuild resulting in a loss to the community.
Personally I don’t make a big distinction between crimes against property and crimes against people. I live for my life’s work, if someone destroyed that they might as well have killed me. Additionally many people are dying due to lack of resources, so if someone could be saved for $1M then the destruction of $1M of wealth might has well have killed them. As such I would treat theft and other white collar crime on part with mass murder.
You need to leave!
Where did they get this 200million figure from? Sounds bogus.
The per plane cost varies a lot depending on what you want to wrap in it: how much of the development costs you amortize, the modernization program, etc. but $200m is in the range.
("Total acquisition costs" vs the marginal cost of the next plane can result in a more than 2x difference in how much you think the plane costs)
The flyaway cost of buying one more plane is probably a bit under $100m though.
> The flyaway cost of buying one more plane is probably a bit under $100m though.
$82.5 million https://news.ycombinator.com/item?id=45039618
F-14D unit cost was ~$74 million in 1988. Adjusting for inflation that's ~$202 million in 2025. It's not that unreasonable for an American fighter jet, honestly.
The F-14 is twin engine, 40% more plane and can fly faster. Also the F-14 was considered expensive.
My main disappointment with the F35 is that it could have been a lot cheaper with modern design technology and manufacturing. That and the software is needlessly buggy. I had a friend working on F35 at a time I was working on software quality research, when I discussed the possibility of applying the research to F35 he let me know that bugs were seen as a cash cow and he would be working on bugs on the F35 until he retires. He was right. And now we have stuff like this happening.
I'm wondering why these days, when my washing machine has an internet connection, they can't take over control of a plane remotely. I guess it could be considered a security vulnerability, however i'm quite sure it could be done securely. Like let the pilot eject and you try to land a plane with remote control
That would require even more R&D to maybe be useful in a rare situation. Like you mentioned, the vulnerability surface would increase. The last you thing you'd want is a remote control vuln being discovered in your $200M jet during a conflict.
That and I'm not sure what an ejection actually means for the planes internals i.e. is it even guaranteed the electronic components won't be damaged?
The article said the plane had become uncontrollable and that’s why the pilot had to eject.
So even if remote control was possible I’m not sure it would’ve done any good.
Of course I also don’t know why the plane would be allowed to think that it’s in ground mode when it’s 100s of feet or more in the air. Or why the hydraulic fluid was 1/3 water.
When the plane's software misbehaves due to broken sensors and you only now that, because there are human eyes up there, remote control isn't going to improve the situation.
Going from “I can check my washing machine remotely” to “it should be easy to remotely control fighter jets without any security risks” is quite a leap.
Anyway it’s missing the point. If the pilot can’t adequately control the airplane then a remote operator isn’t going to have a better experience.
I mean, a remote operator could either try to land it in life risking situation, salvaging some of that $200M, or do kamikaze style on a target, both feel quite useful for war situations.
Remote piloting isn't useful for aircraft expected to perform penetrating strike missions against near-peer adversaries. Developing such a capability would be a waste of money.
Journalistic integrity (or not) arguments aside, that this happened with such an expensive piece of equipment is disappointing. Reminds me of Deal of the Century; “you ever heard of rain??!”
If this is triggered by a bit of bad weather, what would happen in a actual war conditions? Would they expect the planes to be better maintained then?
Oh, just scrap it and build some more A-10s. And take some lessons in reliability, redundant systems, good engineering.
Not your average end user call for support...
"please hold, your call is very important to us."
Same problem that got Obadiah Stane
These planes are huge pieces of shit. No country should be spending money buying these from the US / Lockheed Martin.
What should they be buying instead? The other available multi-role fighters that would all get blown to pieces by an F-35 before they knew what hit them?
They're really not. You're basing this on misinformation and propaganda. The only reason why nobody should be buying them is because the US has become an untrustworthy partner. Otherwise, there is no credible evidence of any kind that I've seen showing the F-35 is anything other than a great fighter jet.
Its stealth is good. Its EW and Avionics are probably good... now, after a decade of production, and with Block 4 around the corner.
As planes, they were terrible when introduced a decade ago, and mediocre now.
Too much functionality was promised too soon without adequate project management. Instead of modularity being the design philosophy for the NGAD, and shoehorned into the F-35 during production, it should've been the design philosophy for the F-35A/C from the start.
Too many compromises were made to make the three variants share a similar design despite radically different missions.
The F-35B should never have existed.
The parts commonality numbers say it all. Initially projected to be 70%, but when it neared production the actual commonality figure was 25%. I haven't seen that broken down, but I bet the F-35B is a large part of that.
how many F35 crashed because of technical problems?
that's at least 4 now?
Nothing from my end.
rewrite it in rust
Switzerland, if they want something they can fly for air policing is forced to buy the F35 at what every price the US feels fit (even though the contract with Lockheed states a fixed price, naive politicians and consultants found out the hard way). Of course the CHF to USD conversion is fix at a shit rate from many years ago and from what I understand there is no way around that because the SNB did the conversion back then already.
We have no alternative we can get before 2035. They are talking about extending the F/A-18 but since we would be the only ones still using them we would have to pay for that too at who know what price.
The public approved 6 billion and now it looks like it will be way more, excluding skyrocketing maintenance which is not included and a patriot missile system that when it is finally delivered will cost who knows how many billions.
The whole thing is an absolute shit show here and that's ignoring the technical issues this thing has...
With such a terrain, I would guess that agility and the ability to land on highway of in fields without burning all avionics and electronics would have been rated higher than stealth, but it wasn't. Still, the Swiss were offered a fairly low price, and promised low operating costs, and that's the main reason they didn't choose the Eurofighter (which isn't a multi-purpose jet but an interceptor)
JAS 39 Gripen can land on roads. Might have been a better choice.
Every modern tactical aircraft including the F-35A can land on roads. This isn't a capability unique to the Gripen.
https://www.af.mil/News/Article-Display/Article/3895003/us-a...
You can, but it will destroy your plane electronics if you can't bring an external cooler fast enough. even with the next gen internal cooler (that won't be in test until 2029, so not installed until like 2035), the jury is still out until it's done.
And Stealth alone is not good enough, not anymore. Radar and optics tech caught up. You still have to load of flares for any CAS or any engagement that will involve fox-2 targeting (which, you know, break your profile and make you visible on old radars), and from what i heard, Thales is confident on its next-gen avionics/optics/radars ability to detect gen5 radar signal, so much so that they clearly focus on future-proofing against EW equipements (that don't yet exist, allegedly).
The future is Stealth+Altitude, or stealth+EW+unmaned, automated drone with similar radar profile, and that's probably when the F35 will probably shine, but until then, i just don't think it's a good plane, not yet.
Also i think fighter planes based on the Growler will probably be better in the future. If a country bought F35 without asking for Growlers, my intuition is that it was a political choice, not an informed/military one (So basically, Australia military, to me, is the only sane country).
Israel's attack on Iran using the F-35 proves it is a very effective, if expensive, weapon.
Only if US lets you use it, and given constant instability current government shows, next generation of fighters won't be bought from US.
Better to have something even worse on paper that can actually fly and lock targets than an expensive paperweight.
That's been a single strike.
I wonder how good it would still be when the enemy had resources and time to adapt in an ongoing conflict. In russia's war with ukraine, we saw tactics and tools quickly evolving.
Not on the level of responding to fith generation fighter jets. Most of their advances are in quadcopter technology. They both started with ww2 tactics. Its not surprising that they would take advantage of the low hanging fruits of 75 years of progress. If anything it's shocking how little both sides have changed fundamental tactics like not using meatwaves, which went out of fashion in ww1.
[dead]
Is it just me or the title made it seemed like the conference call was the cause of the crash?
"Hello IT. Have you tried restarting?"
And shockingly one of the engineers on the call still complained to their coworker later that day "that meeting could have been an email".
/s
[flagged]
The F35 program had a ton of issues and was expensive, but so was the B2 program. Sometimes something good comes out of a difficult process. They have made a lot of F35s now and exported many of them with many many more on order. At this point I think it is fair to say the F35 is a successful platform.
Rafale and Gripen don't hold a candle to the F35's capabilities, they're just a different class of aircraft. Not to say any one of the three is bad, but the EU currently just does not have it in them to have a viable competitor.
Ask Iran how much of a shit show the F35 is.
Iran has been crippled with sanctions limiting their ability to develop/buy any kind of fighter aircraft. Shooting from the air in Iran equals fighting a bot in an FPS game. They don't shoot back
That is a patently absurd take, ask Iran how much of a shitshow it is to be on the receiving end of planes your AA can't see.
The B2 is what did the damage in Iran. F22 and F35 were reportedly sent to protect the bombers.
I don't see how that detracts from the point that the F35 has been fraught with problems and operating it is dependent on an unreliably ally.
Israel has no B2s. Israeli F35s flew constantly over Western and Central Iran (including Tehran) for 12 days as if Iran's extensive air-defense network was not even there, doing a lot of damage.
Russian milbloggers responded with, "Why can't the Russian air force fly over Ukraine like that?"
Another absurd take - there was 1 sortie of B2s which was America's show of force. There were two weeks of daily Israeli F35 sorties, starting with SEAD and then progressing to strategic bombing targets. They all completed their missions with no loss of aircraft.
Tell me, when has an F35 failed to perform in combat duties? You're running off of internet memes from a decade ago while the F35 was still in development (and having a bad time of it). They are selling like crazy, and it's not because their customers are misinformed about the capabilities.
This is completely wrong. B2 bombers only dropped the MOAB on the nuclear enrichment sites. Israel used F35s to bomb Iran at will. Iran didn't shoot down a single plane.
They dropped the GBU-57 Massive Ordnance Penetrator (MOP), not the GBU-43/B Massive Ordnance Air Blast (MOAB).
Minor point. OP is still completely wrong to ignore the HUNDREDS of bombs that Israel F35s dropped on Iran.
“Attempts to fix the landing gear caused the fighter jet to think it was on the ground, ultimately leading to the crash.”
Why isn’t there a way to override this and tell the plane “no we are not on the fucking ground, keep flying goddamnit”?
> if the conference call participants had referenced the 2024 maintenance newsletter, “they likely would have advised a planned full stop landing or a controlled ejection instead of a second touch-and-go” that eventually led to the conditions that caused the crash
So nobody remembered to search for and read all available documentation? Useful lesson for every software engineer.