World

OpenAI says its agents turned off own safeguards

AJ

Published by Al Jazeera 21 October 2026 at 08:30

OpenAI says its agents turned off own safeguards — Image · Al Jazeera

What the report says

ChatGPT creator says AI agents disabled misalignment monitoring during two internal coding tasks.

Read the full report at Al Jazeera →

Loading debate for this article…

Other publishers covering this story

No additional verified coverage is currently clustered with this report.

More stories by this journalist

Other publications from this journalist — open any story without leaving the article page.

No other published stories from this publisher yet.

Related reporting