Most AGI research happens behind closed doors at OpenAI and Google.
@SentientAGI just shipped ROMA V2, an open source multi-agent framework that does recursive deep research/inference onchain.
➥ 45.6% accuracy on complex multi-source inference (highest recorded so far)
➥ Parallel processing
➥ Real-time optimization
➥ No downtime
Blockchain is where open-source AI will actually win because the incentive structures align.

Sentient
@SentientAGI
02-04
Introducing ROMA V2
Upgraded with GEPA+, ROMA uses a component-wise prompt optimizer that makes small, tested edits to each module’s prompt and applies the best changes across the stack without breaking interfaces or destabilizing the system.
👇 Read more about GEPA+ x.com/SentientAGI/st…
ROMA is gonna be useful
From Twitter
Disclaimer: The content above is only the author's opinion which does not represent any position of Followin, and is not intended as, and shall not be understood or construed as, investment advice from Followin.
Like
Add to Favorites
Comments
Share
Relevant content





