Hacker News new | ask | show | jobs
Cache hit rates of Inference are more meaningful than the headline costs (dirac.run)
11 points by mellosouls 18 days ago
1 comments

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.

opencode has a plugin for similar work: https://github.com/Opencode-DCP/opencode-dynamic-context-pru...

It allows the model to remove context pollution.