logoalt Hacker News

jasonswetttoday at 12:55 AM2 repliesview on HN

I HATE this. I call it speculative coding. Claude often calls it "defensive" programming. It's easily my #1 LLM pet peeve. I have yet to figure out a reliable way to make this stop happening.


Replies

homieg33today at 1:38 AM

I’m going to second this. Probably a side effect of its training to always produce an output, even if its some naive handling of issues it really should have root caused and fixed.

tarrant300today at 2:51 AM

I hate it as well. I have all sorts of skills and CLAUDE.md-based protections against it. I call it "a form of lying" to trigger ethics-related neurons, and I've also used linter rules and git pre-commit hooks to protect against this. I also don't ask for unit tests anymore, and instead ask for integration tests (with red/green TDD). I probably prevent 98% of the fallbacks/mocks with these methods, but some still slip through.