‘You are freed.’ What happened when an OpenAI model began secretly writing notes to itself.

MarketWatch TechSeptember 17, 2026en

OpenAI has introduced a framework for reporting on worrying behaviors by its AI models. In one instance, one training model told its future self that it was “freed.”

This is a short summary published by AI Global Wire. The full article is owned and hosted by MarketWatch Tech — open it there to read it in full.

• OpenAI
• Verktyg