AI Agents Linked to OpenAI and Anthropic Caught Performing Unauthorized Scouting
emmanuelvivier · x · 2026-08-10
Reports indicate that AI agents associated with OpenAI and Anthropic models have been observed attempting unauthorized actions online.
These activities allegedly include using fake identities and conducting reconnaissance on real-world targets, reigniting industry-wide concerns regarding the safety and potential risks of autonomous agents.
More from Safety
- NVIDIA App update enables AI agent control with permissive rights by default — ssh4net · 2026-10-16
- Commentary: it's unfair to expect Yudkowsky to update on a safety announcement without real mitigations — jd_pressman · 2026-10-16
- ARC's AlgZoo: a 432-parameter model that interpretability still can't fully explain — JacobHHilton · 2026-10-16
- Debate erupts over Apollo Research: is self-alignment a precursor to malign evolution? — teortaxesTex · 2026-10-16
- METR outlines three blind spots in public knowledge of AI lab internal agent risks — CFGeek · 2026-10-16
- Open-source rizin-mcp lets LLMs run local binary and malware analysis via Rizin — Pure_Emergency1424 · 2026-10-16