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

Show HN: Auto-Architecture: Karpathy's Loop, pointed at a CPU

github.com

Post reply on HN
Print view View original

41–50 of 88 posts

Re: Show HN: Auto-Architecture: Karpathy's Loop, pointed at a CPU

#41

Post by amelius »

pteetor wrote: post #3

In case you are unfamiliar with Karpathy's Loop[1], it is a genetic algorithm[2] where the genetic "mutations" are clever-but-random ideas generated by an LLM agent, aimed at improving a system. (1) Let the LLM randomly perturbate the system. (2) Measure the system's performance. (3a) If the perturbation improved performance, keep the change. (3b) Otherwise, don't. (4) Repeat [1] https://github.com/karpathy/autoresea…

A genetic algorithm keeps a population, and there is a "crossing" operation.

I don't see both ingredients in Karpathy's proposed scheme.

Re: Show HN: Auto-Architecture: Karpathy's Loop, pointed at a CPU

#43

Post by amelius »

thald wrote: post #31
pteetor wrote: post #3

In case you are unfamiliar with Karpathy's Loop[1], it is a genetic algorithm[2] where the genetic "mutations" are clever-but-random ideas generated by an LLM agent, aimed at improving a system. (1) Let the LLM randomly perturbate the system. (2) Measure the system's performance. (3a) If the perturbation improved performance, keep the change. (3b) Otherwise, don't. (4) Repeat [1] https://github.com/karpathy/autoresea…

I was working some time ago on LLM assisted optimizations and algorithm discovery and this does not look like a novel idea. AlphaEvolve from google is evolutionary algorithm which uses LLMs for Idea generation following very similar loop: - https://deepmind.google/blog/alphaevolve-a-gemini-powered-co... - Open source implementation of the algorithm: https://github.com/algorithmicsuperintelligence/openevolve

I mean, this is such low hanging fruit, you have to be careful not to step on it.

Re: Show HN: Auto-Architecture: Karpathy's Loop, pointed at a CPU

#44

Post by riedel »

amelius wrote: post #43
thald wrote: post #31

Earlier quoted context omitted.

I was working some time ago on LLM assisted optimizations and algorithm discovery and this does not look like a novel idea. AlphaEvolve from google is evolutionary algorithm which uses LLMs for Idea generation following very similar loop: - https://deepmind.google/blog/alphaevolve-a-gemini-powered-co... - Open source implementation of the algorithm: https://github.com/algorithmicsuperintelligence/openevolve

I mean, this is such low hanging fruit, you have to be careful not to step on it.

Just because it is a nice meme I want to throw in Schmidhuber's work on (do not treat this comment as serious except you are Schmidhuber himself):

* Gödel Machine (2006-2007) [1]

* Optimal Ordered Problem Solver (2002) [2]

* Meta-Learning and Artificial Curiosity (1990s onward) [3]

[1] https://arxiv.org/html/2505.22954v3

[2] https://arxiv.org/abs/cs/0207097

[3] https://evolution.ml/pdf/schmidhuber.pdf

Edit: markdown formatting

Re: Show HN: Auto-Architecture: Karpathy's Loop, pointed at a CPU

#45

Post by iterateoften »

pteetor wrote: post #3

In case you are unfamiliar with Karpathy's Loop[1], it is a genetic algorithm[2] where the genetic "mutations" are clever-but-random ideas generated by an LLM agent, aimed at improving a system. (1) Let the LLM randomly perturbate the system. (2) Measure the system's performance. (3a) If the perturbation improved performance, keep the change. (3b) Otherwise, don't. (4) Repeat [1] https://github.com/karpathy/autoresea…

Lol, I respect karpathy a lot, but this is such an obvious in your face idea that it is laughable to put someone’s name on it.

What’s next “karpathy investing” where ai in a loop builds a portfolio?

Re: Show HN: Auto-Architecture: Karpathy's Loop, pointed at a CPU

#47

Post by 2ndorderthought »

yk09123 wrote: post #33
pteetor wrote: post #3

In case you are unfamiliar with Karpathy's Loop[1], it is a genetic algorithm[2] where the genetic "mutations" are clever-but-random ideas generated by an LLM agent, aimed at improving a system. (1) Let the LLM randomly perturbate the system. (2) Measure the system's performance. (3a) If the perturbation improved performance, keep the change. (3b) Otherwise, don't. (4) Repeat [1] https://github.com/karpathy/autoresea…

This is like idiocracy for Software Devs at this point

It does burn holes in ones brain doesn't it... At least with the silly sorting algorithms we know they are supposed to be silly...

Re: Show HN: Auto-Architecture: Karpathy's Loop, pointed at a CPU

#48

Post by embedding-shape »

iterateoften wrote: post #45
pteetor wrote: post #3

In case you are unfamiliar with Karpathy's Loop[1], it is a genetic algorithm[2] where the genetic "mutations" are clever-but-random ideas generated by an LLM agent, aimed at improving a system. (1) Let the LLM randomly perturbate the system. (2) Measure the system's performance. (3a) If the perturbation improved performance, keep the change. (3b) Otherwise, don't. (4) Repeat [1] https://github.com/karpathy/autoresea…

Lol, I respect karpathy a lot, but this is such an obvious in your face idea that it is laughable to put someone’s name on it. What’s next “karpathy investing” where ai in a loop builds a portfolio?

I'd go a step further and say that sort of loop is probably the first thing most people who play around with agent harnesses try, pretty much the first "Hmm, what should I do now?" thing that pops into people's head.

Re: Show HN: Auto-Architecture: Karpathy's Loop, pointed at a CPU

#49

Post by 2ndorderthought »

KronisLV wrote: post #38
yk09123 wrote: post #33

Earlier quoted context omitted.

This is like idiocracy for Software Devs at this point

Is it? Evolution also seems to be a result of semi-random crap over the span of millenia and nobody is critiquing it like that. Why should throwing ideas at the wall in regards to optimizing code be any different: as long as you can measure and verify it, are okay with added complexity, and are capable of making the code itself not be crap by the end of it? If an approach is found that improves how well something wor…

It's basically saying to randomly slop something and see if it gets better. Evolution has physical principles and guard rails backing it. Here there are no principals whatsoever, just slopping the slopper to see if it's somehow less sloppy then writing a gist with a slop machine.

I wouldn't call it karpathys loop I'd call it slop descent. Or descent into slop. Or something like that

Post reply on HN