News for hackers. Stuff that matters.

A comment on Heretic: Automatic censorship removal for language models. Parent comment

Re:Heretic: Automatic censorship removal for language models by SalmoShalazar on Sunday November 16, 2025 @05:33PM (#45949078)
Okay let’s calm down a bit. “Extremely important” is hyperbolic. This is novel, sure, but practically jailbreaking an LLM to say naughty things is basically worthless. LLMs are not good for anything of worth to society other than writing code and summarizing existing text.
[ Parent | on HN ]
Re:Heretic: Automatic censorship removal for language models by int_19h on Sunday November 16, 2025 @05:47PM (#45949167)
A censored LLM might refuse to summarize text because it deems it offensive.
[ Parent | on HN ]
Re:Heretic: Automatic censorship removal for language models by blackqueeriroh on Monday November 17, 2025 @05:59PM (#45959416)
An LLM cannot “deem” anything.
[ Parent | on HN ]
Re:Heretic: Automatic censorship removal for language models by int_19h on Tuesday November 18, 2025 @12:42AM (#45961761)
I'm not interested in sophistry. You know perfectly well what I mean, and so does everyone else.
[ Parent | on HN ]