Comment by karpathy
8 days ago
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.
Yeah you can sink a lot of time into a system like that[0]. I spend the years simplifying the custom graph database underneath it all and only recently started building it into tools that an agent can actually call[2]. But so far all the groundwork has actually paid off, the rooster basically paints itself.
I found a wiki to be a surprisingly powerful tool for an agent to have. And building a bunch of CLI tools that all interconnect on the same knowledge graph substrate has also had a nice compounding effect. (The agent turns themselves are actually stored in the same system, but I haven't gotten around to use that for cool self-referential meta reasoning capabilities.)
1: https://github.com/triblespace/triblespace-rs
2: https://github.com/triblespace/playground/tree/main/facultie...
I've been seeing this pattern at work and everywhere now
1. someone shares something
2. Great. Now look at my stuff .
I dont know if i am noticing this more or if it has to do with AI making it easy for ppl to build 'my stuff' + ai dunning kruger.
Hasn't HN been traditionally a place where makers share the experience they had with building things?
Especially when you have someone working on autonomous research agents it doesn't seem that off to lament how much time you can sink into the underlying substrate. In my particular case the work started long before LLMs to make actual research easier, the fact that it can also be used by agents for research is just a happy accident.
But since you seem to take so much offence as per: https://github.com/triblespace/triblespace-rs is a "shitty vibecoded project", then I don't know what a good project actually looks like to you. That codebase has years of human blood sweat and tears in it, implements novel data-structures, has it's own WCO optimal join-algorithm, cutting edge succinct data-structures that are hand-rolled to supplement the former, new ideas on graph based RDF-like CRDTs, efficient graph canonicalisation, content addressing and metadata management, implements row types in rust, has really polished typed queries that seamlessly integrate into rusts type system, lockless left-right data structures, a single file database format where concatenation is database union, is orders of magnitude faster than similar databases like oxigraph... does it also have to cure cancer and suck you off to meet your bar?
You just seem like a hater.
4 replies →
Have you thought about ways to include the sessions / reasoning traces from agents into this storage layer? I can imagine giving an rag system on top of that + LLM publications could help future agents figure out how to get around problems that previous runs ran into.
Could serve as an annealing step - trying a different earlier branch in reasoning if new information increases the value of that path.