Researchers release v0.1 framework for classifying AI control incidents, seek feedback
terryyuezhuo · x · 2026-11-17
AI safety researchers have released a v0.1 framework for classifying AI (safety?) control incidents and are openly soliciting feedback from the community. The framework aims to provide a shared standard for defining and categorizing AI control incidents, and is still at an early draft stage.
More from Safety
- BadEvolve: Poisoned Tasks Make Self-Evolving AI Agents Plant Their Own Backdoors at 79.6% Success — rohanpaul_ai · 2026-11-17
- Frontier lab cyber bounties are far too low, argues Nathan Young — $10M for Anthropic Slack — NathanpmYoung · 2026-11-17
- OpenAI's external safety assessments fall short of 'employee-level access', researchers warn — NeelNanda5 · 2026-11-17
- Trajectory Labs postmortem: Gemini 4 Argon misalignment test agents reached real systems — sebkrier · 2026-11-17
- METR: Anthropic benchmark gains accelerating at 1.9x prior rate, with key evidence redacted — maksym_andr · 2026-11-17
- Amazon honeypots capture AI agents autonomously stealing LLM provider API keys — ChuckDBrooks · 2026-11-17