Browse Hacker News
7,060 matching stories
[ 164 ms ] page + count
-
after working quite rigorously for a few months with claude code, I found out that I was blindly approving permission requests for the sake of progressing my projects, this led me to realize that coding agents generate…
- Show HN: AI Vision Index, private tests of how well 36 AI models see (aivisionindex.com)
I wanted to know for my work which model is best at vision tasks (using both llms like claude and smaller models like YOLO - smaller specialist models are still not finished testing). I found that none of the public…
- Clawdcursor > Computer-Use (clawdcursor.com)
- Why Doctors in Thailand Fear KFC (nytimes.com)
- Introduction to Compute Markets #1: The Primary Market (twitter.com)
- The Silver Bullet Syndrome (youtube.com)
- Bangalore India Hospital Flow (sive.rs)
- Fixing Stack Overflow's toxicity with $500 (sadok.mx)
- Making Flawed Benchmarks Useful (blatent.ai)
- Original Diablo Game Design Doc [pdf] (graybeardgames.com)
- Affair Bench: The public record of private affairs. (affairbench.com)
- Devin Review 2.0 (devin.ai)
- Pigshell: Unix the Web (pigshell.com)
- AI Shakes Volunteer Sites (cacm.acm.org)
- Mercedes Gives Its Cars an AI Upgrade (wsj.com)
- Explaining the popularity of Max Richter's compositions (economist.com)
- We beat DeepL at its strongest settings, 99 to 3 (airtranslate.ai)
- Let's Talk About Why All This OT Stuff Is Connected (tisiphone.net)