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 thatsabadlook on Thursday October 15, 2026 @08:23AM (#50102630)
Did you read my post or are you just pumped to talk about local models?
[ Parent | on HN ]
Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by jacquesm on Thursday October 15, 2026 @08:28AM (#50102679)
It was you that brought up the local models. So yes, I did read your post.
[ Parent | on HN ]
Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by thatsabadlook on Thursday October 15, 2026 @08:31AM (#50102704)
The point of my comment was about how people should try really small models to see how bad they are to understand the technology better. Like 1 or 2b models.
[ Parent | on HN ]
Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by jacquesm on Thursday October 15, 2026 @08:44AM (#50102832)
1 or 2b models are toys.

Of course they are going to be harmless idiots. But there is a boundary where that is no longer the case and that boundary is well within what you can run locally.

[ Parent | on HN ]
Re:AI agents aren't 'going rogue.' Frontier labs are skippin... by thatsabadlook on Thursday October 15, 2026 @01:07PM (#50106773)
Super aware of that. Reread the original post.
[ Parent | on HN ]