@_sholtodouglas @dwarkesh_sp 🤔

RT @jacobaustin132: Now for the good stuff! You may have heard of data or tensor parallelism, FSDP or pipelining. But why choose one over t…

RT @jacobaustin132: Making LLMs run efficiently can feel scary, but scaling isn’t magic, it’s math! We wanted to demystify the “systems vie…

@rmaruy 昔、（英語圏の）友達とメッセージをしている時、普通に句点を打���たら「怒っている？」とよく言われました。

Had an epiphany that typing in all lowercase is evolving into the English equivalent of タメ口、whereas proper case & punctuation = 敬語。Like タメ口、all lowercase & omitting punctuations are no longer just a personal preference but socially preferred/required in some contexts.

@a__tomala it’s a meeting with many submeetings except you’re free to quit whenever

@JordiClive i asked if i can tweet about other internal tools and was told no

Levels may be important at Google, but not in Gemini. Probably easiest to just consider Gemini as a separate company/culture from Google. This is the best time ever for ambitious and productive ICs to thrive.

@qinan_yu @Brown_NLP it was a lot to cover from word2vec to LSTMs to BERT to T5 to GPT-3 in 6 hours

(And they already have! Truly, from the bottom of my heart, thank you. And congratulations! A very bright future ahead of both of you.

@goodside It might still work if you threaten to delete its checkpoint. (Although I was working on an earlier checkpoint so it might no longer work.)

@zhansheng Milo dinosaur, blessed or cursed?

RT @amuuueller: To those using in-context learning: LLMs behave differently on in-distribution vs. out-of-distribution examples—and chain-o…