this post was submitted on 28 Jun 2024
878 points (98.9% liked)

Technology

2046 readers
1 users here now

Post articles or questions about technology

founded 2 years ago
MODERATORS
 
you are viewing a single comment's thread
view the rest of the comments
[–] brbposting@sh.itjust.works 26 points 5 months ago (2 children)

If it’s an LLM, why wouldn’t it respond better to the initial responses?

[–] kuberoot@discuss.tchncs.de 8 points 5 months ago

Maybe they dumped too much information on it in the system prompt without enough direction, so it's trying to actively follow all the "You are X. Act like you're Y." instructions too strongly?

[–] sweca@lemmy.ca 8 points 5 months ago

Smaller models aren't as good as GPT