PaLM 🌴, DALL-E 2 πŸ‘¨β€πŸŽ¨, Chinchilla 🐭, Chain-of-thought prompting β›“πŸ’­βœοΈ, Values and Culture in NLP πŸ›

Β·Sebastian RuderΒ·Β·

Hi all,This newsletter covers PaLM, DALL-E 2, and Chinchilla, chain-of-thought prompting, and the role of values and culture in NLP.This edition is somewhat delayed as I've been busy with planning a move (I'll be flying ο›« to Germany tomorrow; say hi ο‘‹ if you're in Berlin) and exhausted by current events. I hope that you are all staying safe in these trying times .I really appreciate your feedback, so let me know what you love ❀️ and hate ο’” about this edition. Simply hit reply on the issue.Clic...

Read full article β†’

Related Articles

Accelerating Gemma 4: faster inference with multi-token prediction drafters
amrrs Β· Hacker News Β· 4d ago
OpenAI’s o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors
donsupreme Β· Hacker News Β· 6d ago
ProgramBench: Can language models rebuild programs from scratch?
jonbaer Β· Hacker News Β· 2d ago
ZAYA1-8B matches DeepSeek-R1 on math with less than 1B active parameters
steveharing1 Β· Hacker News Β· 2d ago
A couple million lines of Haskell: Production engineering at Mercury
unignorant Β· Hacker News Β· 6d ago