< prev1 / 10 more >

• 218Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k (systima.ai)
  by systima2 hours ago | 30 comments
• 39Can We Understand How Large Language Models Reason? (cacm.acm.org)
  by adunk2 hours ago | 9 comments
• 362Old and new apps, via modern coding agents (terrytao.wordpress.com)
  by subset9 hours ago | 29 comments
• 141I love LLMs, I hate hype (geohot.github.io)
  by therepanic1 hour ago | 24 comments
• 15The One-Step Trap (In AI Research) (incompleteideas.net)
  by jxmorris121 hour ago | 4 comments
• 46Against Usefulness (motivenotes.ai)
  by supo2 hours ago | 4 comments
• 61Automation Without Understanding (arxiv.org)
  by root-parent3 hours ago | 11 comments
• 42Why write code in 2026 (softwaredoug.com)
  by softwaredoug2 days ago | 37 comments
• 63LARP – Revenue infrastructure for serious founders (larp.website)
  by BerislavLopac3 hours ago | 8 comments
• 25Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper (ploy.ai)
  by brryant3 hours ago | 4 comments

< prev1 / 10 more >