Post
Jesse Karmani
jesseplusplus.com
did:plc:n54rmprsh4w7x2htcnu7s2sz
This is the only article I’ve seen so far mentioning that all of the recent incidents of AI hacking from the big firms were CTF exercises run by the *same* AI cybersecurity firm who messed up the sandbox and allowed internet access. I wish the headlines told that story.
https://www.cnbc.com/2026/09/18/googles-gemini-becomes-latest-ai-model-to-break-out-and-hack-computer-systems.htmlll
2026-09-19T14:36:41.966Z