achalpandey
- Karma
- 0
- Created
- ()
- Submissions
- 0
-
I think coding benchmark results don't represent our messy reality. As they 1) Use purpose-built test harnesses We use Claude Code or Codex 2) Test one-shot tasks We work in sessions Sessions are messy, we start with a…
- How are you measuring Claude Code or Codex performance? (docs.google.com)
- Show HN: Speak your mind and get a prioritized action plan instantly (apps.apple.com)