< prev 2 / 10 more >

• 73Terminal-Bench-Science: Evaluating AI agents on scientific research workflows (terminal-bench-science.ai)
  by matt_d8 hours ago | 12 comments
• 169Show HN: We built open OpenRouter that turns usage into a better model (github.com)
  by SilenN11 hours ago | 13 comments
• 480Show HN: The load-bearing vocabulary of Claude (louisabraham.github.io)
  by Labo33323 hours ago | 66 comments
• 283The turbulent AI era is here (gatesnotes.com)
  by nanna1 day ago | 83 comments
• 1GoGoGrandparent (YC S16) is hiring back end engineers (ycombinator.com)
  4 hours ago |
• 98AI Engineer Notebooks – free, framework-free RAG/agents/evals on Colab (github.com)
  by calmrocks10 hours ago | 5 comments
• 35Bootstrappable Builds: How and Why (lwn.net)
  by signa115 hours ago | 7 comments
• 232Decompiling a Nintendo 64 game in 84 days (blog.chrislewis.au)
  by knackers17 hours ago | 21 comments
• 81Select * from Internet.blogposts (pfrazee.leaflet.pub)
  by mmattbtw9 hours ago | 12 comments
• 144Afterglow: Run classic After Dark screen savers on modern macOS (morphing.cloud)
  by NaOH1 day ago | 16 comments

< prev 2 / 10 more >