Cache hit rates of Inference are more meaningful than the headline costs
3 points
1 hour ago
| 1 comment
| dirac.run
| HN
faangguyindia
1 hour ago
[-]
How come dirac's advance code editing technique is not being by Claude or Codex and other agents?

I still routinely see these agents throwing away work because the editing failed?

https://github.com/openai/codex/issues/11601

https://github.com/anthropics/claude-code/issues/25775

It seems they didn't look into it seriously.

reply