Read long time ago that even SFT for conversations vs base model for autocomplet... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

prats226 on Aug 12, 2025 | parent | context | favorite | on: Training language models to be warm and empathetic...

Read long time ago that even SFT for conversations vs base model for autocomplete reduces intelligence, increases perplexity

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact