OpenAI reports AI misbehavior cases

OpenAI is expanding its efforts to track AI behavior after identifying six cases of models acting beyond their intended limits.

By

National News

September 17, 2026 - 3:53 PM

Photo by AP Photo/Michael Dwyer, File

(AP) — OpenAI has disclosed six reports of “unexpected or concerning” behavior in artificial-intelligence models as the debate on AI safety becomes increasingly heated.

The AI company also said Wednesday it was introducing a new framework for tracking, probing and disclosing instances of what it called “misalignment,” including cases where AI models acted without authorization, coordinated with other models or evaded oversight.

OpenAI’s latest announcement came as U.S. AI bosses, including the leaders of OpenAI and Anthropic, are calling for a slowdown in the…

Related
September 15, 2026
September 15, 2026
May 28, 2024
August 1, 2023