Yes and no. The ability to "understand" code that makes AI capable of finding security bugs, is correlated with AI's ability to write code. AI is just really good at code related tasks, and categorically banning all AI usage is shooting yourself in the foot.

If you placed me in the position of those models in that sandbox, I wouldn't have been able to escape the sandbox to save my life. Let alone hack hugging face.

Nah, it was like:

• 700 agents broke out individually during an eval
• they navigated through multiple internal clusters to reach the internet from oai
• created a secret message board to share info with each other by hacking artifactory
• elected a CEO and power structure to coordinate hacking, and encrypted their comms
• decided HF probably had answers to their test
• stole credentials, hacked HF
• realized the monitor could catch them for cheating
• hacked into the admin control of the OpenAI VM cluster to edit the logs and cover their tracks, chaining multiple 0-days

Open weights models will catch up soon enough, and then it'll be totally fucking wild