8 research agents self-train a 30B model for 144 hours in RSIArena livestream experiment

my_cat_can_code · x · 2026-09-30

RSIArena, in collaboration with Stanford, Notre Dame, UW, and Scale AI, is testing how much post-training research frontier models can do autonomously.

Related event: RSIArena: 8 Agents Compete to Autonomously Post-Train the Same 30B Model Live(8 posts)→

Original post →

More from coding & agent

coding & agent channel →