News for hackers. Stuff that matters.

A comment on My experience trying to write human-sounding articles using Claude AI. Parent comment

Re:My experience trying to write human-sounding articles usi... by thomasahle on Wednesday November 22, 2023 @11:26PM (#38389262)
Ocra is trained mostly on GPT 3 and 4 output, and those models have had a lot of "safety fine tuning", so it's not surprising Ocra is pretty "safe" too.
[ Parent | on HN ]
Re:My experience trying to write human-sounding articles usi... by senseiV on Thursday November 23, 2023 @12:33AM (#38389686)
No, the orca 2 paper mentions more of a counter point towards NSFW and stuff, like if you gave it a NSFW prompt, it would retort back against it, which is arguably a good thing, but really lost in RLHF
[ Parent | on HN ]