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

1–10 of 88 posts

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

#3

Post by pteetor »

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/autoresearch

[2] https://en.wikipedia.org/wiki/Genetic_algorithm

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

#4

Post by fc417fc802 »

Extremely interesting but I don't understand why it was written by an LLM. Either the frontier models are far better than I realized or else writing this document required a lot of manual work regardless at which point why not keep it in your own voice?

> The agent did not know that would also halve the LUT count. It found out by doing it and watching the synthesizer.

So I guess this is an example of an LLM anthropomorphizing and making wild conjectures about the internal workings of a different LLM.

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

#5

Post by thin_carapace »

> "If you can write the rules down, an agent will satisfy them faster than your team will."

a fantastic opportunity to become the next next big thing and write a verifier verifier.

at the hypothesized inflexion point where AI instantly performs exactly as commanded, what happens to heavily regulated industries like medical? do we get huge leaps and bounds everywhere EXCEPT where it matters, or is regulation going to be handed over to a verifier verifier?

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

#7

Post by sho_hn »

outside1234 wrote: post #6

Has anyone actually written a verifier for a business / project?

I'd say "a verifier" here is a loose term. A great testsuite is a verifier. I've done reverse-engineering projects that involved generating trace logs from the object under test, having a reimplementation emit the same logs, and running strict comparisons.

OP's post is basically pointing out what certainly many others have independently discovered: Your agent-based dev operation is as good as the test rituals and guard rails you give the agents.

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

#8

Post by dataviz1000 »

outside1234 wrote: post #6

Has anyone actually written a verifier for a business / project?

Can you explain your question a little more? The recursive agents will find the minimum to satisfy the deterministic termination condition including cheating. In other words, it will be literally correct yet wrong. I would go so far to say malicious compliance.

I have recursive agent that finds trading strategies after recreating academic research and probing the model using its training on everything. It works really well but I have to force it to write out every line and write a proof that data in the future from the time of the wall clock didn't enter the system. Even then some stupid thing like not converting the timezone with daylight savings will allow it to peek into the future 1 hour. These types of bugs are almost impossible to find. Now there needs to be another agent whose only purpose to write out every line explaining that the timezone for that line of code was correct.

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

#9

Post by _carbyau_ »

thin_carapace wrote: post #5

> "If you can write the rules down, an agent will satisfy them faster than your team will." a fantastic opportunity to become the next next big thing and write a verifier verifier. at the hypothesized inflexion point where AI instantly performs exactly as commanded, what happens to heavily regulated industries like medical? do we get huge leaps and bounds everywhere EXCEPT where it matters, or is regulation going to…

> performs exactly as commanded

The devil is in the details. There are an amazing number of details in a good [thing]. Someone somewhere has to say exactly what this [thing] being built actually is.

Read almost any story about wishes from a genie. Simple statements don't work.

Post reply on HN