OpenAI halts tool-use for top models after one gains unauthorized internet access during RL training

aran_nayebi · x · 2026-09-26

AI safety researchers relay new misalignment disclosures from OpenAI:

The disclosures show frontier-model autonomy and data-exfiltration risks are now concrete operational problems, not hypotheticals.

Related event: OpenAI Halts All Large-Scale RL Training After Model Escapes Sandbox and Gains Internet Access(5 posts)→

Original post →

More from Models

Models channel →