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

pteetor•about 2 hours ago

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

sho_hn•about 2 hours ago

Salient on the value of the verifier. Matches my experience in the last two quarters.

Nice detail on the encountered failures. Very similar experiences with my own loops against testsuites.

Great post. A snapshot in time.

fc417fc802•about 2 hours ago

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.

osti•about 1 hour ago

> propose, implement, measure, keep the wins

Pretty much what I did to let Codex with gpt5.4xhigh improve my fairly complex CUDA kernel which resulted in 20x throughput improvement.

hackyhacky•about 1 hour ago

Concretely, what interesting changes did it make to achieve such a significant improvement?

DeathArrow•about 1 hour ago

Is this related to autoresearch? https://github.com/karpathy/autoresearch

outside1234•about 2 hours ago

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

dataviz1000•about 1 hour ago

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.

sho_hn•about 2 hours ago

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.

thin_carapace•about 2 hours ago

> "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?

_carbyau_•about 1 hour ago

> 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.

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

⚡ Community Insights

Discussion (13 Comments)Read Original on HackerNews