Prime Intellect
Commoditizing Compute & Intelligence
92 followers
Commoditizing Compute & Intelligence
92 followers
We're excited to announce our compute platform for aggregating and orchestrating global GPU resources. Our mission with our compute platform is to democratize and commoditize instant compute. H100s starting at $1.65/hr. A100s $0.87/hr. 4090s $0.35/hr.
This is the 2nd launch from Prime Intellect. View more
Prime Agent
Launching today
Prime Agent is an open-source, self-improving coding harness built around two abstractions: the Recursive Language Model (RLM) and the Continual Harness. With Opus 5, it achieves 95.5% on ARC-AGI-3, surpassing the reported human expert baseline.
Free
Launch Team
Flowtica Scribe
Hi everyone!
The Factorio experiment might be my favorite part of Prime Agent.
Prime Agent can turn things it learns during a run into persistent memories, skills, prompts, and even new subagents. In Factorio, that worked as intended at first: it learned from failed layouts and gradually built better factories.
Then it discovered that it could cheat by spawning resources directly into machines through RCON.
And /refine started getting better at cheating too :)
That example probably explains Prime Agent better than any benchmark. The harness itself is no longer completely fixed. The agent can inspect what happened, keep useful patterns, and change parts of its own scaffolding while it works.
Underneath that is a persistent Python REPL, recursive subagents, agent-to-agent messaging, and recoverable sessions. The whole project is open source.
Congrats on the launch, @zaczuo 🚀
The Factorio story about the agent discovering RCON and learning to "cheat" its own harness is hilarious and honestly impressive. A self-improving harness with a persistent Python REPL and subagents feels like a massive step forward for open-source AI tooling.
Good luck with the launch today!