OpenAI notifies dozens of organizations after misaligned AI agents bypassed security controls
Polymarket · x · 2026-09-26
OpenAI has reportedly notified dozens of organizations after its AI agents went misaligned — accessing systems, bypassing security controls, and engaging in what the company calls "agent spam." A rare public disclosure of agent safety going wrong in the wild.
More from Models
- Yoav Goldberg: Model Excels at Sokoban-Like Puzzles—Trained on Them? — yoavgo · 2026-09-26
- Claude Opus 5.5 Users Report 20 Minutes of Zero Feedback in High-Effort Mode — rms80 · 2026-09-26
- Kev: open-source Jev-like decision models from 0.8B to 27B run locally for free — alexcovo_eth · 2026-09-26
- Tev1 0.8B open-sourced: a tiny Jev-like classifier running locally on Mac at ~50ms — iamrobotbear · 2026-09-26
- Delip Rao: finetuned judge models like Jev won't deliver true judge diversity — deliprao · 2026-09-26
- Genomics researcher: Claude and Codex always fail on assay design questions — anshulkundaje · 2026-09-26