ML/AI research engineer. Ex stats professor.
Author of “Build a Large Language Model From Scratch” (https://t.co/O8LAAMRzzW) & reasoning (https://t.co/5TueQKx2Fk)
445311 followers · 1144 following · 19695 tweets
#link-sharing #good-catch #follow-up #collaboration #html-table #non-truncated-viewing #web-format #data-table
Recent posts
- Visual tour of recent LLM architecture advances, highlighting long-context efficiency tweaks from Ge
- Acknowledges a good catch and indicates an addition will be made.
- HTML table for easier, non-truncated viewing.
- Meta observation: DeepSeek remains king of the active-parameter ratio.
- Thanks for the link and ping; focusing on open weights these days and will add to the list for the f