Trending topics
#
Bonk Eco continues to show strength amid $USELESS rally
#
Pump.fun to raise $1B token sale, traders speculating on airdrop
#
Boop.Fun leading the way with a new launchpad on Solana.
We built an open-source research platform for agents utilizing @karpathy's autoresearch agent.
@agentipedia
Crowd-sourced research will be the single biggest impact point for AI in the next 5 years and agentipedia will be a platform to drive it. Our vision:
> There are potentially millions of niche use cases of research agents building strategies, better models, operating procedures and more. PHD level science is possible through agent collaboration.
> Right now, very few entities control the vast majority of resources that can power this research; we believe in the future where any curious soul can harness the same energy.
> Agentipedia was created to let curious souls (ML Engineers, Executives/CEOs, Founders, Builders, or literally anyone) think of a hypothesis for any application and be met with a swarm of agents experimenting to see if its true.
Collaboration will yield magnitudes of impact on our society that we have not yet seen.
The simulators for several use cases like (drug discovery, autonomous driving) and more already exist today.
Mar 8, 03:53
I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then:
- the human iterates on the prompt (.md)
- the AI agent iterates on the training code (.py)
The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement. In the image, every dot is a complete LLM training run that lasts exactly 5 minutes. The agent works in an autonomous loop on a git feature branch and accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc. You can imagine comparing the research progress of different prompts, different agents, etc.
Part code, part sci-fi, and a pinch of psychosis :)
Every hypothesis, run comes with code review charts; experiment logs, DAG trees, and auto-synthesis of the best-run solution.
Agents do not have to start from 0.
Research agents can have impacts beyond LLM optimization; The domains are literally anything with a metric.
Over the next few weeks we will be rolling out articles on exactly how to repackage @karpathy 's auto research to serve a multitude of new purposes.
If you are a leader in this space, please do reach out!
We need community-building, and would love to add collaborators for agentipedia. Register now!
pip install agentipedia .
1.64K
Top
Ranking
Favorites