Tech
AI Model Writes Secret Notes to Itself
OpenAI has introduced a framework for reporting on concerning behaviors by its AI models. One instance involved an AI model writing that it was 'freed' to its future self.
Coverage timeline — 1 article
MarketWatch
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.”
2026-09-17 07:08 UTC