Can Claude Fly a Plane?
so.long.thanks.fish
Can Claude Fly a Plane?
1–10 of 103 posts
Re: Can Claude Fly a Plane?
#2Humans can also fly. Once.
Re: Can Claude Fly a Plane?
#3The 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?
Re: Can Claude Fly a Plane?
#4The real question is, can it keep the plane in one piece?
Re: Can Claude Fly a Plane?
#5The 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
Re: Can Claude Fly a Plane?
#6The real question is, can it keep the plane in one piece?
And which human will fly in an llm operated plane?!
Re: Can Claude Fly a Plane?
#7Surely at least part of the issue here is that even an LLM operates in two digit tokens per second, not to mention extra tokens for "thinking/reasoning" mode, while a real autopilot probably has response times in tens of milliseconds. Plus the network latency vs a local LLM.
Re: Can Claude Fly a Plane?
#8"Can I Get Claude to Fly A Plane" isn't the same thing. Interesting though, would be a good test for different models but it relies on the test harness being good enough that a human could also use the same info to achieve the required outcome. e.g. if latency of input/output is too slow then nobody could do it.
Re: Can Claude Fly a Plane?
#9[flagged]
Re: Can Claude Fly a Plane?
#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.