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.

Original post →

More from Safety

Safety channel →