Everything science has taught me strengthens my belief in the continuity of our spiritual existence after death. [...] Science has proved that nothing disintegrates into nothingness. Life and soul, therefore, cannot disintegrate into nothingness, and so are immortal. ― Von Braun
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.
https://t.co/YCvOwwjOzF
Part code, part sci-fi, and a pinch of psychosis :)
@DavidDeutschOxf A rock in the sun under the right conditions is literally what kicked off life, isn't it?
Sir, I never thought I'd disagree with you about anything 😁 but I do believe in the merit of this simplification of life as a negentropy agent.
@MichaelAArouet idealism in the young is higher. the socialist idea is pretty "everyone should get everything" but utterly hopeless. people turn more pragmatic as they mature. when you see old socialists, they're likely just naive, dumb or malicious.