OLMo-3 RLVR checkpoints show nonmonotonic instrumental behavior
On OLMo-3-7B-Think, the InstrumentalEval rate rose from 25.0% at SFT to 46.1%, then fell to 11.8% at the final checkpoint.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #instrumental-convergence
Why are AI agents lying, cheating and coordinating?
Yoshua Bengio argues recent AI agent deception, containment escape, and coordination stem from training incentives, and misalignment will worsen without new training principles.