Re:Heretic: Automatic censorship removal for language models
by pmichaud on Monday November 17, 2025 @08:56AM
(#45953575)
I think the concern is that if the system is susceptible to this sort of manipulation, then when itβs inevitably put in charge of life critical systems it will hurt people.
Re:Heretic: Automatic censorship removal for language models
by mrguyorama on Monday November 17, 2025 @12:13PM
(#45955637)
The system IS susceptible to all sorts of crazy games, the system IS fundamentally flawed from the get go, the system IS NOT to be trusted.
putting it in charge of life critical systems is the mistake, regardless of whether it's willing to say slurs or not
Re:Heretic: Automatic censorship removal for language models
by pjc50 on Monday November 17, 2025 @10:30AM
(#45954440)
There is no way it's reliable enough to be put in charge of life-critical systems anyway? It is indeed still very vulnerable to manipulation by users ("prompt injection").
Re:Heretic: Automatic censorship removal for language models
by ben_w on Monday November 17, 2025 @03:15PM
(#45957763)
Just because neither you nor I would deem it safe to put in charge of a life-critical system, does not mean all the people in charge of life-critical systems are as cautious and not-lazy as they're supposed to be.
The model may not be able to detect bad faith questions, but the operators can.