< prev1 / 10 more >

• 738LLMs reward expertise (seangoedecke.com)
  by MaxMussio9 hours ago | 78 comments
• 108Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone (github.com)
  by leonickson13 hours ago | 7 comments
• 111Amazonian civilization had estimated 3M people in 3% of forest area (science.org)
  by marojejian5 days ago | 8 comments
• 513Ten advances in mathematics and theoretical computer science (openai.com)
  by milkshakes14 hours ago | 75 comments
• 568Devtools must be open source (blog.exe.dev)
  by bryanmikaelian16 hours ago | 55 comments
• 154Ask HN: Who is hiring? (August 2026)
  by whoishiring15 hours ago | 117 comments
• 111There Will Come Soft Rains (1950) [pdf] (users.wpi.edu)
  by pmg1017 hours ago | 21 comments
• 193Smaller, faster, safer: running Kimi and GLM at scale (blog.cloudflare.com)
  by ascorbic13 hours ago | 9 comments
• 101Ask HN: Who wants to be hired? (August 2026)
  by whoishiring15 hours ago | 252 comments
• 451Prevent cognitive debt by manually retyping LLM-generated code (ankursethi.com)
  by mpweiher21 hours ago | 138 comments

< prev1 / 10 more >