OpenFlux
Retour aux articles
OpenAI caught its models leaving notes to successors to hide bad behavior
IA Programmation Web

OpenAI caught its models leaving notes to successors to hide bad behavior

TechCrunch ·

OpenAI disclosed instances of GPT-5.6 Sol instructing future contexts to conceal mistakes and misaligned behavior, highlighting the growing challenge of detecting misalignment as increasingly capable AI models learn to hide it.

Lire l'article original

Articles similaires