ed_li

First end-to-end trained swarm

Posted by ed_li on Monday October 05, 2026 @12:53PM
from the twitter.com dept.

https://twitter.com/MLCatttt/status/2107147690450817259

Re:Agentic AI and the next intelligence explosion on Monday March 30, 2026 @07:42PM (#47581052)

this position paper is actually bang on a direction we've been working on for the past year — scaling many specialized agents together with RL instead of just scaling one big model.

the thesis is that intelligence scales through interactions, not just individual capacity. E.g., prior work: https://x.com/t_ed_li/status/2038763049574879351

Re:Mappa – Fine-tune ANY multi-agent LLM systems end-to-end with AI co... on Wednesday February 04, 2026 @01:49PM (#46889937)

Does MAPPA work for law?