A researcher demonstrated a proof-of-concept attack chain that provided C2-style influence over ChatGPT’s isolated sandbox during a session at Black Hat USA 2026.
Origine de l’article : lire l’article original
Researcher Claims Control of ChatGPT Secure Sandbox
Previous Article
Next Article
OpenAI's new hardware leaks: Over $300, same size as an Alexa Dot
Jony Ive’s first OpenAI gadget is reportedly a hockey puck-sized smart speaker
