News for hackers. Stuff that matters.
Re:Uncensored (Language) Models by pc86 on Monday May 15, 2023 @10:13AM (#35948457)
No comment on whether it's broadly a good thing or bad thing, but you can't get ChatGPT (on GPT-4 at least) to tell you even slightly scandalous jokes without a lot of custom prompting and subterfuge, and they seem to be spending active development and model training time to try to counter a lot of the circumvention we've seen to get around these guardrails. Not just for dirty jokes but for anything deemed bad.

So it seems pretty clear you can load values into an LLM.

Re:Uncensored (Language) Models by jhbadger on Monday May 15, 2023 @10:43AM (#35948981)
And on the censored local models too, like standard vicuna. If I am having my LLM play an adventure game or write a story and I ask "What does the princess look like?" I don't want a lecture on how judging people by their looks is bad (which I sometimes get) -- I can get, if not entirely agree with, stopping actual NSFW responses, but this condescending moralizing is absurd. That's why I'm glad people make uncensored Vicuna models and the like.