This archive copy may be incomplete. The original-source link is preserved in the card footer.
RT @caesararum: Using sentiment analysis to selectively filter training sets for LLMs to produce a zoo of models with vastly different pers…
More notes on nearby ideas
Reply · Nov 1, 2023@RealVXV oh like LLM trained with all my tweets to act like meReply · Sep 4, 2025@lillybilly299 i label it and it usually performs way worse but i find it interesting & the llms want me to share it so it eventually gets back to…Reply · May 26, 2023ooo this would be so helpful in reducing the effort to build custom feeds on top of embeddingsQuote tweet · Mar 18, 2023same, I'm not surprised that LLMs are human-like but that humans are so LLM-like https://x.com/Scobleizer/status/1637163731510779904