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

11–20 of 103 posts

Re: Can Claude Fly a Plane?

#11

Post by gbgarbeb »

aetherspawn wrote: post #5
travisgriggs wrote: post #3

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…

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.

Re: Can Claude Fly a Plane?

#15

Post by sigmoid10 »

est wrote: post #10

> 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.

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.

Re: Can Claude Fly a Plane?

#16

Post by mihaaly »

Friend participating in some sort of simulated glider tournament trained a neural network to fly one some way (don't ask details). I recall rules were changed to ban such, not because of him.

Using Claude sounds overkill and unfit the same time.

Post reply on HN