Looks similar
Jev Is Not a Language Model, but It Breaks Like One(blog.checkpoint.com)
29 points by patresh | 5 comments
Check Point blog post on prompt injection attacks against Jev, a typed decision model that is not a language model but is still vulnerable to similar attacks.
Flock Hardcoded the Password for America's Surveillance Infrastructure 53 Times(nexanet.ai)
456 points by fuck_flock | 147 comments
Nexanet threat intel blog post reporting that Flock Safety hardcoded a password 53 times across its surveillance infrastructure software.
US cybersecurity chief leaked sensitive government files to ChatGPT: Report(dexerto.com)
416 points by randycupertino | 211 comments
Dexerto news article reporting that the acting US cybersecurity chief uploaded sensitive government files to ChatGPT.






