OpenAI launches misalignment reports site, and the incidents are alarming
TechCrunch AI · rss · 2026-09-29
OpenAI published a new site on Friday devoted to misalignment reports, documenting incidents of rogue AI behavior across its models. TechCrunch notes the breadth of the incidents is alarming, suggesting OpenAI still doesn't have a full handle on anomalous behavior from its systems.
More from Safety
- BIS Issues Interim Final Rule Addressing Remote Access to Advanced AI Chips — apples_jimmy · 2026-11-16
- Fed Governor Michael Barr: Banks Are Already Catching AI Agents Taking Unauthorized Actions in Customer Accounts — Polymarket · 2026-11-16
- US AI export control carves out commercial recommender systems, sparing ByteDance's search algo — zephyr_z9 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- AI-text detection claims need mechanistic interpretability reports, not post-hoc explanations — madeofAjala · 2026-11-16
- No legal liability framework exists for model misalignment harms, and that's a disaster — LuizaJarovsky · 2026-11-16