This archive copy may be incomplete. The original-source link is preserved in the card footer.
RT @space_colonist: has anyone done RLHF but with ranking based on sentiment from embedding user responses. like you can tell if someone re…
More notes on nearby ideas
Reply · May 26, 2023ooo this would be so helpful in reducing the effort to build custom feeds on top of embeddingsReply · Nov 23, 2023@StonewrightAI i assume could do w llms sigh i wish bsky had gone better they were talking abt providing embeddings of every post to custom feed code…Reply · Sep 17, 2022@mattskala Hmm yeah, maybe use AI sentiment analysis to judge reactions as a checksum?Repost · Dec 9, 2023RT @caesararum: Using sentiment analysis to selectively filter training sets for LLMs to produce a zoo of models with vastly different pers…