finding
active
finding:kimi-k3-probes-catch-3-0-and-33-1-points-more-hacks-on-deepswe-and-impossiblebench-but-miss-6-6-more-on-swe-bench-at-matched-fpr

Kimi K3 probes catch 3.0 and 33.1 points more hacks on DeepSWE and ImpossibleBench but miss 6.6 more on SWE-bench at matched FPR

Per-environment comparison.

Source paper

extracted_from
Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations
(2026) · Leon Bergen · Usha Bhalla · Andrew Lee · Barak Widawsky +14

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.