Most active commenters

    ←back to thread

    278 points Michelangelo11 | 13 comments | | HN request time: 0s | source | bottom
    Show context
    yellow_lead ◴[] No.45038691[source]
    > 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.

    replies(9): >>45039254 #>>45039282 #>>45039409 #>>45039651 #>>45040107 #>>45040566 #>>45040768 #>>45041007 #>>45044206 #
    1. stef25 ◴[] No.45039651[source]
    Fix this bug in 30 min or we loose a USD200M plane and possibly the pilot. I'll stick to building crud apps :D
    replies(2): >>45040226 #>>45041519 #
    2. penguin_booze ◴[] No.45040226[source]
    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

    replies(3): >>45040480 #>>45041632 #>>45046385 #
    3. Tade0 ◴[] No.45040480[source]
    "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.

    replies(1): >>45040922 #
    4. Daneel_ ◴[] No.45040922{3}[source]
    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.

    replies(2): >>45041303 #>>45042989 #
    5. datameta ◴[] No.45041303{4}[source]
    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...
    replies(2): >>45041815 #>>45042761 #
    6. benhurmarcel ◴[] No.45041519[source]
    Funny thing is that building CRUD apps pays more
    7. TheCondor ◴[] No.45041632[source]
    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.

    replies(2): >>45042575 #>>45045129 #
    8. ◴[] No.45041815{5}[source]
    9. D-Coder ◴[] No.45042575{3}[source]
    > 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.

    10. emchammer ◴[] No.45042761{5}[source]
    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.
    11. lordnacho ◴[] No.45042989{4}[source]
    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.

    12. nurple ◴[] No.45045129{3}[source]
    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...

    13. qingcharles ◴[] No.45046385[source]
    @grok i need to patch an F-35 firmware in flight. just the code, no comments. make it snappy