News for hackers. Stuff that matters.

A comment on Show HN: Fine-grained stylistic control of LLMs using model arithmetic.

Re:Show HN: Fine-grained stylistic control of LLMs using mod... by rosecross on Sunday December 10, 2023 @07:45AM (#38591158)
My first thought was this could be great for alignment, e.g., M_aligned = M - M_toxic.

Turns out, that’s exactly what they’ve explored in the paper.

Great stuff.

[ Parent | on HN ]

There are no comments on this comment yet.