News for hackers. Stuff that matters.

A comment on AI agents aren't 'going rogue.' Frontier labs are skipping security basics. Parent comment

Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by seaparter on Wednesday October 14, 2026 @03:38PM (#50093813)
The safeguard against a rabid dog is euthanasia.
[ Parent | on HN ]
Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by vikramkr on Wednesday October 14, 2026 @03:43PM (#50093895)
Yeah exactly. The whole 'they don't have adequate security safeguards' thing is going "oh it's their fault because they didn't use a stronger leash" while they continue to train models that are specifically better at chewing through stronger and stronger leashes. Probably they do need stronger leashes. Probably also they should not be making rabid dogs. Still their fault! But maybe we should be not be dismissing the root cause
[ Parent | on HN ]
Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by pixl97 on Wednesday October 14, 2026 @07:10PM (#50096869)
Ok, convince everyone from making more AI.

The safety problem is not solved and is likely unstoppable.

[ Parent | on HN ]