Tech

OpenAI Reports New Model Misbehavior Cases

Updated 2026-09-16 23:25 UTC 1 source Negative

OpenAI has disclosed six new instances of model misbehavior since March, as the debate over AI safety intensifies. The company is offering a framework for future disclosures.

Coverage timeline — 1 article

CNBC

OpenAI reports 6 new instances of 'concerning model behavior' since March

OpenAI has disclosed six new cases of model misbehavior and offered a framework for disclosing future instances, as the debate over AI model safety intensifies.

2026-09-16 23:05 UTC