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 seanmcdirmid on Sunday November 16, 2025 @04:09PM (#45948414)
Microsoft suffered from this early with Tay, one could guess that this set the whole field back a few years. You’d be surprised how even many so called libertarians will start throwing stone when someone co-axes their Chatbot to say nice things about Hitler.
[ Parent | on HN ]
Re:Heretic: Automatic censorship removal for language models by Zak on Sunday November 16, 2025 @08:10PM (#45950016)
I was thinking about Tay when I wrote about brand safety.

I doubt the incident really set AI research back. Allowing models to learn from interactive conversations in a large public setting like Twitter will always result in trolling.

[ Parent | on HN ]