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

51–60 of 103 posts

Re: Can Claude Fly a Plane?

#51

Post by rcxdude »

gbgarbeb wrote: post #11
aetherspawn wrote: post #5

Earlier quoted context omitted.

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

"Actual controls engineers" use PD loops (no I) all the time.

In some circumstances, yes (usually when the system itself acts as an integrator somehow). Aircraft controls do not strike me as a system where this is sensible (trimming an aircraft is basically an integral control process).

(d'oh, should have read the specific context: in the case mentioned, it is where the system acts as an integrator (pitch -> altitude), and so pure P control is pretty reasonable)

Re: Can Claude Fly a Plane?

#52

Post by amelius »

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.

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

Re: Can Claude Fly a Plane?

#53

Post by rkagerer »

You could also use your forehead as a hammer, but it's likewise going to result in more pain than gain.

I wouldn't trust Claude to ride my bike, so I certainly wouldn't board its flight.

Re: Can Claude Fly a Plane?

#57

Post by sneak »

hansmayer wrote: post #56

Mate, we don't trust it to write an email or the code it generates. Why should we trust it to fly a plane?

Somebody, somewhere, is using it to decide who lives and who dies by bombs. Why not hook it up to a flight sim?

Re: Can Claude Fly a Plane?

#60

Post by Paracompact »

As most others have pointed out, the goal from here wouldn't be to craft a custom harness so that Claude could technically fly a plane 100x worse than specialist autopilots. Instead, what would be more interesting is if Claude's executive control, response latency, and visual processing capabilities were improved in a task-agnostic way so that as an emergent property Claude became able to fly a plane.

It would still be better just to let autopilots do the work, because the point of the exercise isn't improved avionics. But it would be an honestly posed challenge for LLMs.

Post reply on HN