Discussion

Can Claude Fly a Plane?

travisgriggs: The bit in the middle where it decides to make its control loop be pure P(roportional), presumably dropping the I and D parts, is interesting to me. Seems like a poor choice.I try to fly about once a week, I’ve never really tried to self analyze what my inputs are for what I do. My hunch is that there’s quite a bit of I(ntegral) damping I do to avoid over correcting, but also quite a bit of D(erivative) adjustments I do, especially on approach, in order to “skate to the puck”. Density going to have to take it up with some flight buddies. OR maybe those with drone software control loop experience can weigh in?

aetherspawn: Dumping the I part instead of just tuning it properly is kind of an insane thing to do … speaking as an actual controls engineer

userbinator: The real question is, can it keep the plane in one piece?

thewhitetulip: Humans can also fly. Once.

est: > main issue seemed to be delay from what it saw with screenshots and api data and changing course.This is where I think Taalas-style hardware AI may dominate in the future, especially for vehicle/plane autopilot, even it can't update weights. But determinism is actually a good thing.

sigmoid10: This is a limitation of LLM i/o which historically is a bit slow due to these sequential user vs assistant chat prompt formats they still train on. But in principle nothing stops you from feeding/retrieving realtime full duplex input/output from a transformer architecture. It will just get slower as you scale to billions or even trillions of parameters, to the point where running it in the cloud might offer faster end-to-end actions than running it locally. What I could imagine is a small local model running everyday tasks and a big remote model tuning in for messy situations where a remote human might have to take over otherwise.

alex1sa: LLMs seem more suited to planning the flight than actually flying it. Control loops need millisecond responses — not token streams.

leptons: Does Claude know the plane isn't at the car wash?

thewhitetulip: And which human will fly in an llm operated plane?!

ccozan: Please welcome aboard of Airthropic Lines!

edu: Besides the article, I think a big issue for this would be the speed of the input-decision-act loop as it should be pretty fast and Claude would introduce a lot of latency in it.

blitzar: Sky King managed it, no reason claude shouldnt be able to.

operatingthetan: We already have advanced autopilots that can fly commercial airliners. We just don't trust them enough to not have human pilots. I would trust the autopilot more than freaking Claude. We already do, every day.

Ekaros: I think we can trust them to not have human pilots. It is just that having human in loop is very useful in not that rare scenarios. Say airfield has too much wind or fog or another plane has crashed on all runways... Someone needs to make decision what to do next. Or when there is some system failure not thought about.And well if they are there they might as well fly for practise.And no. I would not allow LLM in to the loop of making any decision involving actual flying part.

dewey: I don't think anyone is suggesting we should do that...but it's still a fun project to play around with?

codingconstable: Agreed. I think thats a really fun way to test out Claude's ability to perform an abstract task it's probably not trained on, was nice to read

Markoff: I wouldn't really worry about flying, but more about taking off/landing.Related from December 2025: Garmin Emergency Autoland deployed for the first timehttps://www.flightradar24.com/blog/aviation-news/aviation-sa...

stinkbeetle: Autoland has been used for 60 years and on much more complicated aircraft than that Beechcraft B200.

jmward01: The question of 'can it fly' is clearly a 'yes, given a little bit of effort'. Flying isn't hard, autopilots have been around a long time. It is recognizing and dealing with things you didn't anticipate that is hard. I think it is more interesting to have 99% of flying done with automated systems but have an LLM focus on recognizing unanticipated situations and recovering or mitigating them.

stnikolauswagne: >I think it is more interesting to have 99% of flying done with automated systems but have an LLM focus on recognizing unanticipated situations and recovering or mitigating them.Seeing how Claude (or any current LLM) perform in even the most low-stake coding scenario I dont think I would ever set foot on a plane where the 1% of most risky scenarios are decided by one.

johntopia: If there's a timeline where claude can actually fly a plane, then operating nuclear reactors can be possible as well.

dist-epoch: try using codex-5.3-spark, it has much faster inference, might be able to keep up. and maybe a specialized different openrouter model for visual parsing.

LiamPowell: There's also the issue that when something goes wrong, many people will never trust an autopilot again. Just look at how people have reacted to a Waymo running over a cat in a scenario where most humans would have made the same error. There's now many people calling for self-driving cars to never be allowed on roads and citing that one incident.

girvo: Which makes sense: a robot can’t be responsible for anything, a human can be.

nairboon: Let's hope you don't reach Claude's session limit during approach, while trying to correct a slightly too steep descent angle.

chha: ...or that the satellite network connection disconnects for some reason.

vachina: Give a stochastic text generator to physics. What can go wrong.

boring-human: > We just don't trust them enough to not have human pilots.Much of the value of a human crew is as an implicit dogfooding warranty for the passengers. If it wasn't safe to fly, the pilots wouldn't risk it day after day.To think of it, it'd be nice if they posted anonymized third-party psych evaluations of the cockpit crew on the wall by the restrooms. The cabin crew would probably appreciate that too.

sandworm101: There are soooo many pilot decisions that AI is nowhere near making. Managing a flight is more than flying. It is about making safety decisions during crisis, from deciding when to abort an approach to deciding when to eject a passenger. Sure, someone on the ground could make many of those decisions, but i prefer such things be decided by someone with literal skin in the game, not a beancounter or lawyer in an office

razorbeamz: I'd imagine Claude is too slow to fly a plane above everything.

amelius: I see you are still in the stochastic parrot phase.

amelius: Using an LLM doesn't mean it has to take the final decision. You can also use it as a warning system.

stnikolauswagne: Is there any indication that current warning systems are insufficient in any way that would be improved by LLM involvement?

vidarh: We won't know that until someone has actually investigated how an LLM would do in those scenarios.

ButlerianJihad: I sincerely doubt that pilots decide "when to eject a passenger". Mostly it would be the cabin crew: the flight attendants are 100% in charge of flight safety, and they would be managing relationships with passengers, and they would be the ones to make the call. It would ultimately be them calling some kind of law enforcement. If an Air Marshal is onboard already, obviously they would be on the front line as well.Furthermore, the concept of "ejecting a passenger" from a flight would mostly not be something you do while in the air, unless you're nuts. Ejecting a passenger is either done before takeoff, or your crew decides to divert the flight, or continue to the destination and have law enforcement waiting on the tarmac.Naturally, pilots get involved when it's a question of where to fly the plane and when to divert, but ultimately the cabin crew is also involved in those decisions about problem passengers.

rounce: The Pilot in Command has ultimate legal responsibility over the operation of the flight, ICAO conventions explicitly state this. Whilst in practice the cabin crew will be the ones dealing with the passenger(s) and supplying information to the PIC , it won’t be them making the final decision.

Findecanor: Douglas Adams formulated how it would be possible for a human to fly continuously, though.http://extremelysmart.com/humor/howtofly.php

thewhitetulip: I have the hitchhikers guide to the galaxy but I never got around to reading it. I might have to read it next

nelox: So Claude crashed because it was busy figuring out how to fly the plane?

resiros: I think you gave someone an idea for a new RL environment :) Probably it will be able to fly it in the next iteration.

kqr: Lots of people commenting seem to have not read the article. The author didn't hook Claude up directly with the controls, asking it to one-shot a successful flight.The author tried getting Claude to develop an autopilot script while being able to observe the flight for nearly live feedback. It got three attempts, and did not manage autolanding. (There's a reason real autopilots do that assisted with ground-based aids.)

sandworm101: No. Cabin crew recommend. Pilots actually decide.

red_admiral: > Flying isn't hardMost of the time. Sometimes you get a double bird strike when you've barely cleared the Hudson river, or similar.

zenmac: It would be interesting to see if Claude can land and take off. Don't think the autopilot can do that yet.

alex_duf: Claude uses the wrong modality to be a piloting model. Latency is critical, and outputting tokens in the hope they take the action at the right time is kinda bonkers.You'd want all the data from the plane to be input neurons, and all the actions to be output neurons.

stnikolauswagne: That sounds like a solution looking for a problem though, i see plenty of arguments against throwing critical safety information that are in charge of peoples lives into an LLM "just in case the result is better than the result that the current battle-hardened systems already provide"

DoctorOetker: I doesn't sound ethical to eject passengers while aborting an approach, regardless of precise timing.

ButlerianJihad: Do the pilots also decide whether to issue a parachute to the ejected passenger?

stnikolauswagne: Pretty sure ejection here is meant as shorthand for "Transfer the passenger to an entity on the ground to proceed from there" whether that entity is emergency medical services or law enforcement is secondary.

KaiserPro: General LLMs I would say are uniquely bad at this sort of thing.I mean if you have a stable plane, then it'll do alright, as it'll mostly fly straight and level (assuming correct trim) reacting to turbulence however, the sampling rate would probably too slow, so you'd end up with oscillations.For recognising that you're in a shit situation, yeah, it'll probably do that fine, but won't be able to give the correct control inputs at the right time.

delta_p_delta_x: [delayed]