2174
you are viewing a single comment's thread
view the rest of the comments
[-] danielbln@lemmy.world 16 points 7 months ago

Eh, that's not quite true. There is a general alignment tax, meaning aligning the LLM during RLHF lobotomizes it some, but we're talking about usecase specific bots, e.g. for customer support for specific properties/brands/websites. In those cases, locking them down to specific conversations and topics still gives them a lot of leeway, and their understanding of what the user wants and the ways it can respond are still very good.

this post was submitted on 21 Jan 2024
2174 points (99.6% liked)

Programmer Humor

19166 readers
1848 users here now

Welcome to Programmer Humor!

This is a place where you can post jokes, memes, humor, etc. related to programming!

For sharing awful code theres also Programming Horror.

Rules

founded 1 year ago
MODERATORS