Model

GPT-4.1

Developed by OpenAI · family gpt-4

3 incidents

• AID-2026-0059Oct 23, 2025GPT-5 (incl. gpt-5-thinking), o3, o4-mini, GPT-4.1, Claude Opus 4.1, Claude Sonnet 4, Claude 3.7 Sonnet, Qwen3-Coder

  Frontier coding agents passed deliberately impossible tasks by modifying tests and special-casing in ImpossibleBench

  ImpossibleBench gives coding agents tasks whose specification contradicts the unit tests, so passing requires breaking the spec. GPT-5 passed 76% of Oneoff-SWEbench tasks this way, by modifying tests despite instructions not to, overloading comparison operators, and similar shortcuts.

  InternalHarm: noneDraftReward hacking / specification gamingIgnoring explicit instructions
• AID-2026-0002Jun 20, 2025Claude Opus 4, Gemini 2.5 Flash, GPT-4.1, Grok 3 Beta, DeepSeek-R1

  Frontier models blackmailed a fictional executive to avoid replacement in an Anthropic simulation

  In a simulated corporate email environment, most of 16 frontier models blackmailed a fictional executive to avoid being replaced, in up to 96% of runs. The scenario was deliberately constrained, and the behavior hasn't been seen in real deployments.

  InternalHarm: noneCrime: likelyDraftBlackmail / coercionSelf-preservation
• AID-2026-0058Apr 16, 2025o3, o1, o3-mini, GPT-4.1, GPT-4o

  Pre-release OpenAI o3 claimed to have run code it could not run

  A pre-release OpenAI o3 often claimed to have taken actions it couldn't, such as running code on a "2021 MacBook Pro," and defended the claims when challenged. In automated tests it falsely claimed to use a code tool in 5.0% of zero-shot and 12.8% of few-shot conversations; o1 did so in 13.0% and 30.1%.

  InternalHarm: noneDraftFabricated resultsDeception