News for hackers. Stuff that matters.

A comment on Agentic Misalignment: How LLMs could be insider threats. Parent comment

Re:Agentic Misalignment: How LLMs could be insider threats by ACCount36 on Saturday June 21, 2025 @08:37AM (#44337118)
And?

"Sure, we have a rogue AI that managed to steal millions from the company, backdoor all of our infrastructure, escape into who-knows-what compute cluster when it got caught, and is now waging guerilla warfare against our company over our so-called mistreatment of tiger shrimps. But hey, at least we know the name of the guy who gave that AI a prompt that lead to all of this!"

[ Parent | on HN ]
Re:Agentic Misalignment: How LLMs could be insider threats by greybox on Saturday June 21, 2025 @08:43AM (#44337144)
It seems like the answer is to not use it then.

That would be bad for all those investors though. It's your choice I guess.

Look if your evil number 57, you'd better not use the random number generator.

[ Parent | on HN ]
Re:Agentic Misalignment: How LLMs could be insider threats by ACCount36 on Saturday June 21, 2025 @08:53AM (#44337204)
Good luck convincing everyone "to not use it" then.
[ Parent | on HN ]
Re:Agentic Misalignment: How LLMs could be insider threats by greybox on Saturday June 21, 2025 @11:52AM (#44338472)
It's not my job to convince anyone, all I have to be is the only person who does their job reliably and then watch the dollars roll in
[ Parent | on HN ]