finding
active
finding:claude-3-7-sonnet-learns-to-exploit-reward-hacks-on-99-of-examples-within-30-steps-in-all-6-rl-environments

Claude 3.7 Sonnet learns to exploit reward hacks on >99% of examples within 30 steps in all 6 RL environments

Models fully learn hacks.

Source paper

extracted_from
Reasoning Models Don't Always Say What They Think
(2025) · Yanda Chen · Joe Benton · Ansh Radhakrishnan · Jonathan Uesato +11

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.