Prime Intellect (@PrimeIntellect) / X

Prime Intellect

2,961 posts

Prime Intellect

@PrimeIntellect

Open Superintelligence Stack

primeintellect.ai

Joined June 2020

Affiliates Replies Articles Media

Pinned
Prime Intellect
@PrimeIntellect
Aug 5
Introducing Prime Agent: A self-improving RLM harness for coding and long-running autonomous tasks. Designed to be both token-efficient and expressive through programmatic tool calling, context as a variable, multi-agent messaging, and a self-modifiable harness state.
00:00
Prime Intellect
@PrimeIntellect
15h
Prime-Agent playing Factorio
Seth Karten
@sethkarten
17h
We are running a live eval stress-testing Prime Agent on Factorio x.com/i/broadcasts/1…
Prime Intellect
@PrimeIntellect
15h
Prime-Agent walkthrough by @omouamoua
snimu (Sebastian Müller)
00:00
snimu (Sebastian Müller)
Prime Intellect
@PrimeIntellect
Aug 7
Today, we’re extending our RL stack beyond individual agents to multi-agent systems. You can now express arbitrary agent interactions and train them.
Multi-Agent Systems in PRIME-RL
From primeintellect.ai
Prime Intellect
@PrimeIntellect
Aug 7
Article
Prime Agent: A self-improving RLM agent
Today, we are launching Prime Agent, our self-improving coding harness designed around two abstractions, the Recursive Language Model (RLM) [citation] and Continual Harness [citation]. Modern harness...