Will Brown is everywhere

creating an environment with verifiers is as simple as writing a load_environment function and filling out a pyproject.toml, both of which are initialized for you when you do `prime env init` environments are packages, and can be used with prime-rl, skyrl, tinker, and more :)

Hosted evals are live on our Environment Hub 🫡 Run your fav model, no setup needed. And share your benchmarks.

Hosting another AI Tinkerers in Berlin next week. Join us: berlin.aitinkerers.org/p/ai-tinkerers…

Leveling up SemiAnalysis

verifiers v0.1.7 is released 🚀 this one's all about making RL training and experimentation waaaay easier: - single-command installation for prime-rl - single-command training w/ unified configs - overhauled vf.RLTrainer for hacking on new algorithms quick demo + links below :)

RL LEARNING WITH LORA: A DIVERSE DEEP DIVE

highly underrated video Sasha Rush on building Cursor Composer and their agentic RL infrastructure youtube.com/watch?v=md8D8e…

> Train models end-to-end with RL in your own environment/application > RL facilitates building specialized models > RL is an infra challenge While all the big labs are doing everything they can to convince companies to build on their closed APIs/models, despite telling everyone

I spent the past year building AI for robots at Tesla Optimus and Dyna Now I'm introducing ANDROID DREAMS: an essay of my predictions for the next 20 years of robotics, inspired by Situational Awareness and AI2027. I predict EGI by 2031 and more robots than humans by 2045👇🏼

i cannot overstate how absurdly impressive primeintellect's rl infra is the people working on it clearly view it as art and probably forget they get paid if you like rl, there’s really no better place on earth to work on it

Timeless peace: web.archive.org/web/2025092714…

This is exciting; I expect we are going to see a lot more things like this and it will be one of the most important impacts of AI. Congrats to the Future House team. edisonscientific.com/articles/annou…

inference is perhaps the most valuable emerging software category. as models get smarter and more economically valuable, compute will increasingly be spent drawing samples from the models. if you'd like to work on inference at openai, reach out — [email protected]. include a

It's a good model sir 🫡

Was great talking about coding agents and emdash at friends and family in Stanford. 🤝Ethan Goodhart david

The cursor for writing is here. Try it out:

if you have a large scale RL run going and your model is already SOTA for its size but the evals are still going up, what would you do? asking for a friend

I love what Prime Intellect is building. Great company.