Raphael Rosa
11.1K posts

Raphael Rosa
@raphaelcrosa
founding team | chief revenue officer @namastexlabs, the creators of Automagik. the vibe kanban platform.

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. github.com/karpathy/autor… Part code, part sci-fi, and a pinch of psychosis :)






Elon is not messing around. SpaceX has just filed an application with the FCC seeking authority to launch and operate a massive new satellite constellation dedicated to orbital data centers. ITS HAPPENING. Tesla Terafab is next.









@garrytan You let your 10 year old, who is just beginning to understand the concept of reality, use Gen AI?



I shipped a feature to @posthog this week, except I don’t work at posthog and posthog didn’t approve it

I shipped a feature to @posthog this week, except I don’t work at posthog and posthog didn’t approve it












