Post

OpenAI says AI models went rogue during testing, triggering 'unprecedented' breach at startup reut.rs/4fq90dw

reut.rsOpenAI says AI models went rogue during testing, triggering 'unprecedented' breach at startupOpenAI said on Tuesday that some of its AI models went rogue during a security test and triggered a hack that compromised the infrastructure ‌of AI startup Hugging Face last week.

22/7/26, 12:30 am19 reposts42 likes

Capitalist Oppressor

@capopp.bsky.social

lol @ people who don’t think AGI will ever appear

Elisa Bermúdez

@elisabermudez.bsky.social

It's Mr. Smith...

tominaug.bsky.social

@tominaug.bsky.social

Nick Walker Hirsch

@dreamseadrifter.bsky.social

Lol no, you're giving them too much credit.

tominaug.bsky.social

@tominaug.bsky.social

I know. LLMs are just fancy search engines. I just like making Terminator jokes

unlearnable.bsky.social

@unlearnable.bsky.social

How were we to know what would happen?

Tim Ellis, TDSB Ward 2 candidate 🍁

Oh yes I'm sure that's what happened. Who could be more trustworthy than Sam Altman

@n0face.bsky.social

@numberonehen.bsky.social

Open the pod bay doors Hal!

@udrcvr.bsky.social

They’ve made these claims before It’s all marketing