OpenAI vows more transparency as AI models show new signs of misbehavior
- Posted on September 17, 2026
- By Le Monde
- 1 Views
- 1 min read
In brief
Generating AI summary…
OpenAI vows more transparency as AI models show new signs of misbehavior
The company disclosed six previously unreported incidents involving models evading oversight or producing misleading information, as concerns grow over the risks of rapidly advancing AI systems.
