Veytics Intelligence
2026-09-17 · Marketwatch

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

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.”

Read the full Veytics brief

We show the main point publicly. Create a free account to continue reading the full article, save it, discuss it, and connect it with market and OSINT context.