RSIArena livestreams 8 research agents doing post-training on a shared 30B base model

my_cat_can_code · x · 2026-09-30

bakeaihq launched RSIArena, a live experiment with Stanford, Notre Dame, UW, and Scale AI testing how much post-training research frontier models can do autonomously.

Setup:

The team will host a livestream event at COLM (booth #107) and is soliciting feedback from researchers in post-training, agents, and evaluation.

Related event: RSIArena Live Test: 8 Agents on the Same 30B Base Compete at Autonomous Post-Training Research(8 posts)→

Original post →

More from coding & agent

coding & agent channel →