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.”

Leer el informe completo de Veytics

Mostramos la idea principal publicamente. Crea una cuenta gratis para seguir leyendo el articulo completo, guardarlo, comentarlo y conectarlo con contexto de mercados y OSINT.