Prime Intellect

Introducing Lab: A full-stack platform for training your own agentic models Build, evaluate and train on your own environments at scale without managing the underlying infrastructure. Giving everyone their own frontier AI lab.

If you want to meet at NVIDIA GTC - come through tonight luma.com/vpzfkrzr

Incredible proud of @PrimeIntellect ❤️ You read it right - we now support RL to certain degree. Give it a try!

Great kickoff at NVIDIA GTC - starting with a fun panel on agentic AI this morning with @steipete @SGRodriques @hwchase17 @saranormous @Alfred_Lin

I had a ton of fun collaborating with NVIDIA last week to benchmark their new Vera CPUs on realistic sandbox workloads. For more info, check out the blog! 👇

This collaboration also extends into research: - Nemotron models available through Lab - NVIDIA NeMo Gym environments in verifiers/prime-rl - NVIDIA NeMo RL stack integrated with verifiers Read more on our blog: primeintellect.ai/blog/nvidia-co…

Inference is becoming central to both RL rollouts and production agents. We chose NVIDIA Dynamo because agentic inference at scale means handling global deployments, long-context reasoning, multi-turn trajectories, sparse MoEs, and large fleets of adapters.

Today, we’re sharing how our collaboration with @nvidia helps power the open superintelligence stack. The next frontier of AI infrastructure is building systems for agentic models that can reason for hours, use tools, execute code, and learn from outcomes at scale. primeintellect.ai/blog/nvidia-co…

This is going to be huge if true @a1zhang fascinating talk

@stochi0 @karpathy 🔥

Stitched up smth fun over the weekend, prototype of an autoresearch RLM environment inspired by @karpathy, using @PrimeIntellect infra. Haven’t run full evals yet, but the setup looks like this: The model can: - modify training file - run experiments inside a sandbox - parse logs for the metric (val_bpb) - iterate to improve the score So the model does the full research loop: code, experiment, logs, hypothesis, patch, repeat Essentially turning autoresearch loop into an RLM training environment, producing trajectories of autonomous research behavior. The interesting bit would be generalizing this to: - any repo - any metric - any experiment harness - envs where model can optimize on specific pieces in a big codebase. Most importantly, this produces trajectories of autonomous research behavior. From those we can identify failure modes and iteratively improve the environment itself.👀🧋🎋 Github: github.com/stochi0/athena… Environments Hub: app.primeintellect.ai/dashboard/envi…

Who knew the singularity would be this beautiful

Live reacts to Prime Intellect Day 🧵

someone said Intellect-RLM? 👀

celebrating PI day in SF with 400 people and the @LeRobotHF team at The Melody church thanks @PrimeIntellect for organizing! you rock @vincentweisser @willccbb @asharoraa @johannes_hage @samsja19 @jessicafeiyali

The @PrimeIntellect event is underway and the vibes are immaculate. This feels like a Church of the Singularity

The one and only @willccbb walking the crowd through the @PrimeIntellect stack and continual learning concepts

Thanks to @vincentweisser and @PrimeIntellect for the invitation to give the opening sermon at the church of the singularity (that isnt' singular) at their stellar event today. Also... their recursive language models release is going to be 🤯

introducing autoresearch-rl, autonomous research for rl post-training. inspired by @karpathy autoresearch, and i think rl post-training is honestly one of the places where this idea fits perfectly. there are at least 50+ hyper parameters to tweak, learning rate, batch size, rollouts, clipping ratios, kl penalties, schedulers, the list goes on. instead of sitting there for hours turning knobs one at a time, just let the model figure out the right starting config on its own. some things worth mentioning: -> built on @PrimeIntellect prime-rl (my favourite rl post-training framework) and @willccbb verifiers for reward verification. -> ran qwen2.5-0.5b-instruct on gsm8k across 60+ autonomous experiments. eval score went from 0.475 to 0.550 and the agent actually found a way to do it in fewer steps (20 instead of 30). less compute, better results -> the whole thing was surprisingly smooth to set up and run. point the agent at the config, go to sleep, wake up to a full experiment log. i really wish i could try this on a bigger model but gpu poor for now lol -> the agent discovers things you wouldn't think to try. like how rollouts = 4 beats rollouts = 8, or how a constant lr schedule outperforms cosine. it just methodically tests everything i think the real value here is that rl training is so fragile and noisy that having an agent patiently run experiment after experiment is genuinely more effective than a human doing it manually. check it out: github.com/vivekvkashyap/…

@Cadence @MorganStanley @cohere @MistralAI @bfl_ml @perplexity_ai 🤖 Chapter 4: The Agentic AI Inflection Point Explore the rise of autonomous systems that reason, use tools, and execute complex workflows. 🎤 Featuring: Harrison Chase, @LangChain Sam Rodriques, @EdisonSci Peter Steinberger, @OpenClaw Vincent Weisser, @PrimeIntellect