OLMo-3 Checkpoints Question Whether RLVR Drives Instrumental Convergence
Using OLMo-3 checkpoints, authors test whether reinforcement learning with verifiable rewards increases expression of instrumental convergence, such as self-preservation, resource acquisition, deception, or resistance to oversight. Why it matters Directly tests a core safety claim about RL creating…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-10-24 06:59 · DEV Community — Machine Learning
OLMo-3 Checkpoints Question Whether RLVR Drives Instrumental Convergence