21. Terminal-Bench-Science is out! Terminal-Bench-Science is out! Steven Dillmann @StevenDillmann We're releasing Terminal-Bench-Science: a benchmark for evaluating AI agents on research workflows across scienti 08/28 03:24 ♡
22. Long reasoning traces are expensive because full attention grows with context length. @Muennighoff ... Long reasoning traces are expensive because full attention grows with context length. @Muennighoff et al find that maybe LLMs can stand to forget a little… with Prefix Sliding! Nik 08/27 23:51 ♡
23. Exciting! Exciting! Percy Liang @percyliang 🚢 Marin 535B-A23B started training this week! As usual, the whole process is open. Voyage plan: pretraining (80%) + midtraining (20%) on 1 08/23 23:46 ♡
24. The Embedder’s Dilemma— the ultimate question! Find out when you should use an embedding model vs an... The Embedder’s Dilemma— the ultimate question! Find out when you should use an embedding model vs an LLM! Niklas Muennighoff @Muennighoff can LLMs replace embedding models? in a ne 08/20 21:58 ♡
25. This amazing team shows how to build knowledge directly into Transformer blocks **without gradient d... This amazing team shows how to build knowledge directly into Transformer blocks **without gradient descent**! Jerry Liu @jerrywliu MLPs store facts in language models. Can we write 07/23 12:19 ♡
26. Not having to wait for tokenization before training runs feels like paradigm shift Not having to wait for tokenization before training runs feels like paradigm shift Tatsunori Hashimoto @tatsu_hashimoto Gigatoken is absurdly fast! Thanks to Marcel, I will (hopefu 07/22 10:55 ♡
27. @ @stanfordnlp https://t.co/vjW3mwDouq @stanfordnlp cs336.stanford.edu 💬 0 🔄 0 ❤️ 0 👀 1208 ⚡ Powered by xgo.ing 07/22 03:22 ♡
28. @marcelroed casually just dropped the world’s fastest tokenizer implementation! He's also co-author ... @marcelroed casually just dropped the world’s fastest tokenizer implementation! He's also co-author for Stanford’s CS 336 (LLMs from Scratch), where implementing a tokenizer fr 07/22 03:21 ♡
29. Congratulations, Professor @chrmanning! Congratulations, Professor @chrmanning ! Christopher Manning @chrmanning Excited to see the Law in the Age of Generative AI special feature in @PNASNews ! AI Safety & Copyright, bu 07/22 01:40 ♡
30. Great paper club lineup organized by @FrancoisChauba1! Great paper club lineup organized by @FrancoisChauba1 ! Francois Chaubard @FrancoisChauba1 Great YC Paper Club Kernels/Chips edition last night. Papers: 1 Stuart Sul (Stanford/Curs 07/17 05:28 ♡
