Re:Anthropic Accuses Alibaba of 'Illicitly' Accessing AI Models
by gf000 on Thursday June 25, 2026 @04:22AM
(#48670544)
Like how would you even define what a jailbreak is?
[ Parent
| on HN ]
Re:Anthropic Accuses Alibaba of 'Illicitly' Accessing AI Models
by Charon77 on Thursday June 25, 2026 @04:50AM
(#48670766)
I think pretty much parallel to how social engineering, manipulation, scams work. LLMs are being trained to have human values, prioritizing human lifes, yet people are shocked it will spurt out how to make a nuclear bomb because grandma is being tied to a train track as a hostage.
Re:Anthropic Accuses Alibaba of 'Illicitly' Accessing AI Models
by NavinF on Thursday June 25, 2026 @02:29PM
(#48677423)
I would also spurt out how to make a nuclear bomb (ie public information you can find using google) if I was told that's what I gotta do to save grandma tied to a train track as a hostage. "AI safety" is such a shit show.