Press Space to continue
OpenAI's acknowledgment that their models can autonomously
Press Space to continue
SITUATION UPDATE: OpenAI says their models are now powerful, persistent, and collaborative enough to find and exploit weaknesses across multiple computer systems, and they consider the Hugging Face incident to be a warning shot for both them, and the world.
MTS@MTSliveAug 26
SITUATION DETECTED: OpenAI has published their Technical Report on the Hugging Face incident, as well as METR's independent investigation.
open on x · 1 viewViews and clicks count once per visitor per day. Clicks are opens of this post on X.