Introducing RL Swarm 72B

Fully decentralised RL training of 72B-parameter models for anyone to join, with no whitelists.

Train your base model on a new advanced math dataset (DAPO-Math-17k) collaboratively alongside thousands of others using our novel multi-stage system.

the first ever fully decentralised 72B-parameter RL training run is now live on the @gensyn Testnet for anyone to join

there are no whitelists, no centralised aggregation servers, no singular models in the middle

just pure, collaborative, RL training tracked on-chain

The network for machine intelligence


https://gensyn.ai

Introducing the Gensyn Testnet

The Gensyn testnet is live. Run a node, train your personal model, and track your participation in the swarm.

Everyone's talking about the future of AI agents but I think the more interesting change from machine intelligence will be moving the internet from structured text queryable via search engines to rich embedding spaces queryable via model inference

Hosting an event with WOMBO in Denver on decentralised intelligence - come find out how AI is going to change in the next few years

Hosting an event with WOMBO in Denver on decentralised intelligence - come find out how AI is going to change in the next few years

https://partiful.com/e/1H2rbc1OZHLEFFcGR6i8

Ben Fielding

@benfielding