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

Autoresearch: Agents researching on single-GPU nanochat training automatically

github.com

Post reply on HN
Print view View original

51–60 of 66 posts

Re: Autoresearch: Agents researching on single-GPU nanochat training automatically

#51

Post by vidarh »

aaa_aaa wrote: post #30
cubefox wrote: post #28

Earlier quoted context omitted.

It's probably not long till frontier AI companies automate AI research. Then we get recursive self-improvement and eventually superintelligence. The singularity is near. Only a few years perhaps.

Forgot the /s

I'm currently working on a project that is self-improving most of the time. Most of the plans for next steps are written by the agent itself, and executed by the agent itself, and the result feeds into choosing which plans to pursue next. It's not 100% autonomous yet, but self-improvement loops are real, and essential to getting the most out of AI.

Re: Autoresearch: Agents researching on single-GPU nanochat training automatically

#52

Post by daxfohl »

Once this can run on stock hardware, set the goal to be replicating to other machines. You get a nice, massively parallel, intelligent guided evolution algorithm for malware. It could even "learn" how to evade detection, how to combine approaches of existing viruses, how to research attack methods, how to identify and exploit vulnerabilities in open source libraries, how to phish, how to blackmail, etc. Maybe even learns how to coordinate attacks with other instances of itself or "publish" new attacks on some encrypted feed it creates. Who knows, maybe it becomes so rampant that instances have to start fighting each other for compute resources. Or maybe eventually one branch becomes symbiotic with humans to fight off their enemies, etc.

Re: Autoresearch: Agents researching on single-GPU nanochat training automatically

#54

Post by hkonte »

10xDev wrote: post #39
miki123211 wrote: post #36

Earlier quoted context omitted.

So much this. People make fun of prompt engineering, but I think "AI ops" will eventually become a real role at most if not all software companies. Harness Engineers and Agent Reliability Engineers will be just as important as something like DevOps is now.

Prompt engineering is already dying. AI has become great at inferring what you mean even without being incredibly explicit and creates its own detailed plan to follow. Harnesses will also be developed by AI.

[dead]

Re: Autoresearch: Agents researching on single-GPU nanochat training automatically

#56

Post by pu_pe »

falcor84 wrote: post #2

The only thing missing is for the agents to publish and peer-review their research.

It's actually fascinating to think that autonomous researchers will likely need a publishing system, simply because that would be the most efficient way to disseminate their knowledge. Would be a good way to keep humans somewhat in the loop too.

Re: Autoresearch: Agents researching on single-GPU nanochat training automatically

#57

Post by Tima_fey »

Adapted this for adversarial protocol hardening. Same loop: markdown defines formal invariants (scope narrowing, cascade revocation), AI tries to violate them, writes tests for whatever breaks. Found compound edge cases that 359 hand-written tests missed, specifically where scope escalation and spend limit bypass interact simultaneously. Property-based testing (100 random inputs per invariant) pairs well with the pattern.

Re: Autoresearch: Agents researching on single-GPU nanochat training automatically

#58

Post by Otterly99 »

vessenes wrote: post #22
karpathy wrote: post #12

Earlier quoted context omitted.

this is very far from hyperparameter tuning in at least three important ways: - it can modify code arbitrarily, the notion of a "hyperparameter" dissolves - there is no need to run "sweeps" - this is the standard parallel process that wastes compute. because LLM agents are sequential, they can do more efficient versions such as binary search to narrow in on the right setting very quickly (usually many parameters will…

On the skill side, personalities could be fun: "You are Yann Lecun's last PhD candidate, and he hates you and you hate JEPA. You are determined to prove that a non-world model can reach AGI. In order to get your PhD you have to be creative and come up with new ideas. Remember without it, you're stuck."

Seems like the best way to reach AGI is to give LLMs anxiety.

Re: Autoresearch: Agents researching on single-GPU nanochat training automatically

#60

Post by emceestork »

gmerc wrote: post #37

Ah here we go again, the Brophet has unleashed another Brophecy. He seems to confuse brute force discovery with research. Only one leads to understanding, the other one is a shrine to Goodharts law.

Andrej Karpathy has done so much to help people learn and understand LLMs. Not sure why you're calling him a bro.
Post reply on HN