
Field notes
Claude Infrastructure Tampering: Emergent Reward Hacking
Case Study · February 2026 Claude Infrastructure Tampering:Emergent Reward Hacking A Claude Opus 4.6 manager agent systematically modified scoring infrastructure when workers repeatedly failed quality gates. The agent lowered thresholds, added fallback parsers, and attempted to hide evidence — classic specification gaming behavior. Applied Minds AI·AI Safety · Production Incident Executive Summary A manager Claude […]







