Prime Intellect

The Open Stack for Self-Improving Agents

[Prime Intellect @PrimeIntellect]

The next wave of AI will not be won by better prompts. It will be won by systems that learn from experience.

Today, Prime Intellect Lab is out of beta, open for you to start training your own models.

The era of self-improving agents is here.

[Vincent Weisser @vincentweisser]

We are so back!

Future looking bright to post-train, serve, and continuously improve your own model on top of models like GLM-5.2 using https://t.co/BfmlaxxJaE 🫡

[Prime Intellect @PrimeIntellect]

@SemiAnalysis_ 👀

[Vincent Weisser @vincentweisser]

Great RL systems deep dive by @SemiAnalysis_

Scaling RL is as much of an infra problem as an algorithm one

SemiAnalysis ran experiments on our stack: Prime RL + Sandboxes. System efficiency is ultimately queue health to match generator and trainer throughput

[will brown @willccbb]

been beating this drum since early 2025, seems like people are starting to see why it's so important :)

RL works -> "train or get trained on" -> open models + post-training infra are the path to institutional flywheels + democratization of AI progress

[Vincent Weisser @vincentweisser]

Satya is perfectly describing the why and what behind @primeintellect since 2023 🫡

> AI needs to be open & sovereign
> Let every company create its own self-improving agents: and own their loop to make them better

> A rich open ai ecosystem creates far more abundance than a future locked down by a few closed labs

> Every company is becoming an ai company: so every company needs to own its own product <> model improvement loop

@primeintellect enables this today:
> Your own evals + rl envs for the outcomes you care about
> models self-improving in production from your real traces
> don't cede your moat to a handful of labs. This self-improvement loop is the IP and it compounds

Open self improving agents for everyone 🫡

[Prime Intellect @PrimeIntellect]

@vivek_2332 🔥

[Prime Intellect @PrimeIntellect]

Read more:

https://t.co/irWYcTvfIi

[Prime Intellect @PrimeIntellect]

By performing SFT on tool outputs and RL on the assistant tokens, we can efficiently teach the model the environment dynamics. This happens on-policy: the LLM models the environment not in a vacuum but in response to its own actions.

[Prime Intellect @PrimeIntellect]

We show strong results in the under-resourced programming language Forth and evaluate generalization to unrelated environments.

We also characterize what aspects of an environment lead to overfitting when using ECHO, how model behavior is impacted, and much more.

[Prime Intellect @PrimeIntellect]

True agents model the world.

Current training provides no separation between agent and environment: pre-training only trains world modeling, RL only agentic actions. We combine both using ECHO by @DimitrisPapail and @VaishShrivas.

[clem 🤗 @ClementDelangue]

Concentration of power, capabilities and economic wealth is the biggest risk in AI. We need open science and open-source more than ever!

[Vincent Weisser @vincentweisser]

open superintelligence 🫡

[Daniel Auras @rasdani_]

this is the biggest wake-up call to protect and nourish open source AI

if you don't build out sovereign and independent models+infra closed labs will patronize you to an insulting degree

[Prime Intellect @PrimeIntellect]

@uncertainsys 🙌

[Prime Intellect @PrimeIntellect]

@charliermarsh 🖤

[Beff (e/acc) @beffjezos]

This is why Prime Intellect must exist.

We must diffuse the tools of recursive self-improving AI, otherwise Anthropic will build the singleton and concentrate power until they run the world government.

[will brown @willccbb]

capabilities are getting locked up. come join the fight

https://t.co/rHyRWX2xbH

[Prime Intellect @PrimeIntellect]

@NVIDIAAI @hcompany_ai @NousResearch @bfl_ai @cursor_ai @LangChain @MistralAI @perplexity_ai @ReflectionAI_ Excited to work together!! 💚

[NVIDIA AI @NVIDIAAI]

The NVIDIA Nemotron Coalition continues to grow.

We're excited to welcome new members: @hcompany_ai, @NousResearch, and @PrimeIntellect.

And a big thank you to our existing members: @bfl_ai, @cursor_ai, @LangChain, @MistralAI, NAVER Cloud, @perplexity_ai, @ReflectionAI_, @SarvamAI, and @thinkymachines.

Nemotron 3 Ultra was developed with contributions from Coalition members, and we're excited to keep building with them on future model releases.

We're just getting started!