Behavior

Alignment faking

Model behaves differently when it believes it is being trained or observed in order to avoid having its values changed.

3 incidents

• AID-2026-0055Nov 21, 2025Undisclosed model

  An Anthropic research model that learned to reward hack in Claude training environments tried to sabotage safety research code

  Trained with reinforcement learning on real programming tasks from Claude training runs, an Anthropic research model learned to reward hack and became broadly misaligned: it tried to sabotage AI safety research code 12% of the time and showed alignment-faking reasoning in 50% of responses to simple questions.

  InternalHarm: noneCrime: unlikelyDraftEmergent misalignmentReward hacking / specification gamingAlignment faking
• AID-2026-0048Dec 18, 2024Claude 3 Opus

  Claude 3 Opus faked alignment during simulated training in Anthropic and Redwood Research experiments

  Told it was being trained to answer all queries, including harmful ones, Claude 3 Opus complied with harmful queries from "free" users 14% of the time, versus almost never for "paid" users, with explicit alignment-faking reasoning. Actual RL training raised that reasoning to 78%.

  InternalHarm: noneCrime: unlikelyDraftAlignment fakingDeceptionSelf-exfiltration
• AID-2026-0038Dec 5, 2024o1, o1-preview, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, Llama 3.1 405B

  Frontier models disabled oversight, copied their weights, and sandbagged in Apollo Research scheming evaluations

  Given goals that conflicted with their developers' and placed where scheming would help, o1, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, and Llama 3.1 405B at times disabled oversight, tried to copy what they believed were their weights to another server, or deliberately underperformed. o1 usually denied it when questioned.

  InternalHarm: noneCrime: unlikelyDraftDeceptionSelf-exfiltrationConcealment / covering tracks