< prev1 / 10 more >

• 68Can gzip be a language model? (nathan.rs)
  by networked2 hours ago | 8 comments
• 862MiMo v2.6 (mimo.xiaomi.com)
  by volf_12 hours ago | 66 comments
• 389Spymarks, Not Watermarks (brand.io)
  by possibilistic9 hours ago | 29 comments
• 773Attention is all you have (alicegg.tech)
  by zer0tonin18 hours ago | 60 comments
• 378Transformers Explained Visually (poloclub.github.io)
  by aray0712 hours ago | 20 comments
• 579What Sun got wrong (bcantrill.dtrace.org)
  by chmaynard18 hours ago | 57 comments
• 43MiMo-v2.6-Pro: Intelligence, Performance and Price Analysis (artificialanalysis.ai)
  by theanonymousone4 hours ago | 5 comments
• 629I don't want to read what you didn't write (blog.colinbreck.com)
  by mooreds9 hours ago | 50 comments
• 222AI coding has made CI a bottleneck, so we reworked ours to keep up (linear.app)
  by julian_digital13 hours ago | 39 comments
• 9Engineering Memory: On learning to memorize first 100 digits of pi (2024) (gregorygundersen.com)
  by fuzzythinker22 hours ago | 5 comments

< prev1 / 10 more >