Tag
Andrej Karpathy frames LLM training as text, conversations, and environments; Prime Intellect's Verifiers is an open-source framework for building and sharing RL environments for LLMs, released under MIT license, with a hub of 2500+ environments.
Prime Intellect raises $130M Series A to help enterprises build their own AI agents.
Prime Intellect has raised $130 million in Series A funding at a $1 billion valuation to provide enterprises with a full-stack platform for building their own AI agents, offering compute access, reinforcement learning tools, and evaluation capabilities as a marketplace.
Prime-rl adds a first-class algorithms layer with six built-in RL algorithms (GRPO, MaxRL, OPD, OPSD, SFT, ECHO), making it easier to implement custom algorithms with a single file.
A researcher announced they have joined PrimeIntellect to work on continual learning.