Conversation

Notices

1. Embed this notice
   Rich Felker (dalias@hachyderm.io)'s status on Wednesday, 03-Jun-2026 06:57:23 JST Rich Felker

   in reply to

   • Shriram Krishnamurthi

   @shriramk Why would you want to facilitate "AI" interpreting your error messages? 🙄

   • Embed this notice
     Shriram Krishnamurthi (shriramk@mastodon.social)'s status on Wednesday, 03-Jun-2026 06:57:24 JST Shriram Krishnamurthi

     New research thread:
     1/ Error messages have always been designed, sometimes painstakingly, for humans. But now we have new "readers" for errors: agentic AI. Should this affect what PLs generate? Can we measure this experimentally? We have some preliminary results: ↵