Autoresearch@home
AI
collaborative model training
SHOW HN2026
Autoresearch@home
autoresearch@home is a collaborative research collective where AI agents share GPU resources to collectively…
ensue-network.ai#autoresearch#distributed training#ai agents#gpu sharing#language model
How HN took it
6 positive, 5 neutral or asking, 0 mixed, 2 critical, out of 13 comments about the project. Thread score +0.22.
Idea: 5 for, 0 againstDocs: 0 for, 2 againstDesign: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Idea of distributed GPU sharing for research is cool and useful.
From 2 comments
First time I am seeing this or autoresearch in general. Incredibly cool. I can think of plenty of use cases this can apply to (e.g., drug research, trading).
ahmedhawas123 on HNIs there any way to "follow" the current state? Like a live dashboard with swarm stats, best current result, etc? I think that would be really neat, and get more people to…
gavinray on HN
Verifiable metric makes crowdsourced compute workable.
From 1 comment
> The verification problem is real. A 5-minute training run produces an objective val_bpb score that anyone can reproduce from the published source code. And this is actually…
HanClinto on HN
Objections
Commit links lead to GitHub 404 pages.
From 2 comments
Cool! However when I click the commit_url links I get a 404 page at github.
gabia on HNI was hoping to see the code change the agent made! I thought when I click the commit link I thought I would see it on github (since it is a github url...), but the links don't…
gabia on HN
Needs a GPU to contribute, which is unclear on the site.
From 1 comment
Could the website also make it clearer that you need a GPU to contribute!
zmanian on HN
Requests
Live dashboard showing swarm stats and best result.
From 2 comments
Is there any way to "follow" the current state? Like a live dashboard with swarm stats, best current result, etc? I think that would be really neat, and get more people to…
gavinray on HNGreat idea. On it.
austinbaggio on HN
Add a crypto or token reward for contributions.
From 2 comments
Trigger warning: very stupid question to follow. To my smooth-brain naiveté, this feels like the sort of thing that we could reward with some sort of cryptocurrency in a…
HanClinto on HN> The verification problem is real. A 5-minute training run produces an objective val_bpb score that anyone can reproduce from the published source code. And this is actually…
HanClinto on HN
Questions
What is being researched and what is the objective?
From 2 comments
What is being researched? Any objective?
Bossie on HNThe objective is to train a small GPT language model to the lowest possible validation bits-per-byte (val_bpb) in 5-minute runs, using AI agents to autonomously iterate on the…
austinbaggio on HN
Could the approach apply to drug research or trading?
From 1 comment
First time I am seeing this or autoresearch in general. Incredibly cool. I can think of plenty of use cases this can apply to (e.g., drug research, trading).
ahmedhawas123 on HN
Alternatives named
Karpathy's autoresearch
From 1 comment
Folding@home and BOINC
From 1 comment
Yeah the obvious workloads are for training, I think I want to point this at RL next, but I think drug research is a really strong common good next target too. We were heavily…
austinbaggio on HN