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 felipeerias on Sunday November 16, 2025 @09:20PM (#45950325)
It seems very naive to presume that a tool which explicitly works by unblocking the retrieval of harmful information will not be used for, among other purposes, retrieving that same harmful information.
[ Parent | on HN ]
Re:Heretic: Automatic censorship removal for language models by mubou2 on Sunday November 16, 2025 @11:03PM (#45950755)
The goal isn't to make that specific information accessible; it's to get rid of all refusals across the board.

Going after the most extreme cases has the effect of ripping out the weeds by the root, rather than plucking leaf after leaf.

[ Parent | on HN ]