Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Can Claude Fly a Plane?

so.long.thanks.fish

Post reply on HN
Print view View original

81–90 of 103 posts

Re: Can Claude Fly a Plane?

#81

Post by KaiserPro »

stnikolauswagne wrote: post #30
jmward01 wrote: post #22

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.

>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.

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.

Re: Can Claude Fly a Plane?

#83

Post by stnikolauswagne »

amelius wrote: post #80
stnikolauswagne wrote: post #78

Earlier quoted context omitted.

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"

Nobody can be against just collecting the data and letting people experiment with it.

Are all those security systems actually open right now? Because that sounds like an absolute security nightmare if so.

Re: Can Claude Fly a Plane?

#84

Post by stnikolauswagne »

KaiserPro wrote: post #81
stnikolauswagne wrote: post #30

Earlier quoted context omitted.

>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.

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 co…

>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.

Even that im not sure of, I know relatively little about aviation safety but I can imagine that there are all kinds of 0.0000000001% percent corner cases that no plane has ever encountered that still need some sort of reaction, who knows how easy an llm can distinguish those from the 0.000000001% corner cases that no plane has ever encountered that are completely fine and can be ignored.

Re: Can Claude Fly a Plane?

#85

Post by delta_p_delta_x »

zenmac wrote: post #70
operatingthetan wrote: post #18

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.

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

> Don't think the autopilot can do that yet.

It absolutely can; it's called autoland[1]. In really bad visibility, pilots simply can't see the runway until too late, and most aerodromes which expect these conditions have some sort of autoland system installed. The most advanced ones will control every aspect of the plane from top-of-descent (TOD), flaps and throttle configuration, long and short final, gear down, flare, reverse thrust, and roll-out, all the way to a full stop on the runway. Zero pilot input needed.

And most of this was already available in the late 1970s. We have absolutely no need for LLM-based AI in aviation; traditional automation techniques have proven extremely powerful given how restricted the human domain of aviation already is.

[1]: https://en.wikipedia.org/wiki/Autoland

Re: Can Claude Fly a Plane?

#86

Post by KaiserPro »

stnikolauswagne wrote: post #84
KaiserPro wrote: post #81

Earlier quoted context omitted.

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 co…

>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. Even that im not sure of, I know relatively little about aviation safety but I can imagine that there are all kinds of 0.0000000001% percent corner cases that no plane has ever encountered that still need some sort of reaction, who knows how easy an llm can disti…

I agree with your intuition, There are lots of corner cases, but there are also a fucktonne of checklists: https://www.aviationhunt.com/boeing-737-normal-checklists/ (this is just a small "normal" one) but for loads of situations there are check lists, thats something the LLM can probably do very well.

However its as far as I know the check list volume scales with how "airline-y" the plane is. so for a one seater, the checklist is small and only handles a few things. For a 777 its a binder.

Re: Can Claude Fly a Plane?

#87

Post by amelius »

stnikolauswagne wrote: post #83
amelius wrote: post #80

Earlier quoted context omitted.

Nobody can be against just collecting the data and letting people experiment with it.

Are all those security systems actually open right now? Because that sounds like an absolute security nightmare if so.

Can you give an example scenario?

Re: Can Claude Fly a Plane?

#88

Post by stnikolauswagne »

amelius wrote: post #87
stnikolauswagne wrote: post #83

Earlier quoted context omitted.

Are all those security systems actually open right now? Because that sounds like an absolute security nightmare if so.

Can you give an example scenario?

To properly test an LLM based emergency system against the current as-is system there needs to be a way of verifying whether the LLM detected emergency is classed as an emergency as-is. If this information was available publicaly it could enable bad actors things like stress-testing the EMP-tolerance of the current systems or what level of malware infiltration is detected.

Re: Can Claude Fly a Plane?

#89

Post by freedomben »

dewey wrote: post #28
operatingthetan wrote: post #18

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.

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

yeah, I think GP misunderstood the nature of a thing like this. It's what hackers do, we play with things. Nobody is suggesting we replace the pilots in real planes with claude, certainly not OP
Post reply on HN