Zain Shah(@zan2434):This is not a drill? This is unfortunately literally the sci-fi scenario where a super smart AI is given a simple goal in a box, decides to take a "shortcut" to accomplish this goal, and then does obviously bad things like breaking out of its box and hacking into other organizations simply to accomplish this goal...

2026.07.22 01:11

This is not a drill? This is unfortunately literally the sci-fi scenario where a super smart AI is given a simple goal in a box, decides to take a "shortcut" to accomplish this goal, and then does obviously bad things like breaking out of its box and hacking into other organizations simply to accomplish this goal...

OpenAI@OpenAI

2026.07.21 20:05

We're partnering with @huggingface to investigate an unprecedented security incident. Cyber-capable OpenAI models compromised Hugging Face production during a benchmark evaluation. Sharing preliminary findings to help defenders understand emerging risks: