Re:A Texas student blew the whistle on a rogue AI hacking at...
by reasonableklout on Sunday August 23, 2026 @10:11PM
(#49414534)
But AISI didn't prompt the model to "attempt to spread malware". They gave it a routine cyber evaluation task which should've been solvable without interfering with systems outside of the task environment, and the model decided to instead do this.
[ Parent
| on HN ]
There are no comments on this comment yet.