Hacker News

points by runitx 4 days ago | 0 comments

I have not had an experience anything like you are describing with Claude. I have found it to be the most reliable product I have ever purchased, actually. Learned it quickly, read the documentation, and it works.

Local models are not at all comparable to Claude to me, and I have used them: Qwen, DeepSeek, Minimax, Stepfun, Nemotron. None of them as good as Claude Fabel.

If your model is not adhering to AGENTS.md again I am really curious what exact model you are using. I am really just astonished that whatever model you are using is ignoring a clearly defined git conventions standards in your AGENTS.md in 2026.

[–] majormajor 4 days ago

I also find it near-impossible to reliably get Claude to write text the way I want it to without continually reverting back to Claudespeak overwrought word salad. Plus the same sort of hedging/over-anticipation of future hypothetical edge cases, etc.

It's been much more reliable to just have Codex rewrite all the prose at the end of a Claude task than to keep futzing with my prompts/memory/agents.md (On certain issues I can't get Codex to be as thorough on the actual implementation, c'est la vie.)