I know nothing about AI code generation (or about AI in general), but I wonder if you could include in your prompt a request that the AI describe the reasons for its choices and actually include those reasons as comments in the code.
The model will always be completing the story you start with it. There's no opinion to uncover because there's no experience that occurred. It's impossible to know where your influence ends and the model's factual basis begins.
This is not the case eny more. I never thought LLMs write bad solutions, but when you let it think for you you loose something important, understanding. And when something brekas, some people consider this being a proof that the llm is the problem. And in a sense it is. But you are also to blame. And that's exactly the issue with this all industry - in order to move faster you don't need to "type" faster. A person bashing his hands on the keyboard randomly at top velocity can get pretty high wpm. In order to move master you need to _think_ faster, be _snappier_ and _sharper_ and most people aren't.
I like how one of my colleagues phrased it in a company meeting. He asked one of the c levels "for llm s to 10x me, I need to let them make all decitions and dictate intentions. By percentage, how much of the code you want me to _know_?"
---
Me: I've notice that Claude is deleting my comments and tends not to insert many of its own. I don't want to go too crazy, but can we modify CLAUDE.md to dial up the comments a little? Like, try not to delete comments that are still relevant, and add a few explanatory comments.
Claude: [... proposal for modifying CLAUDE.md ...]
Claude: Want me to apply this, tweak the wording, or place it differently? Note that your global ~/.claude/CLAUDE.md-style instructions (visible to me as system guidance) currently say "default to writing no comments" — the project-level rule above will override that for this repo, which is what you want.
Me: Where is this rule that says "default to writing no comments"? That seems crazy?
Claude: That text is part of the system prompt I'm given by Claude Code itself — it's not in any file in your project or in your ~/.claude/ config. It's baked into the harness's default instructions to the model.
Claude: Specifically, two lines from my system prompt:
Claude: Under "Doing tasks": "Default to writing no comments. Only add one when the WHY is non-obvious..."
Claude: Under "Text output": "In code: default to writing no comments. Never write multi-paragraph docstrings or multi-line comment blocks — one short line max."
Really? I find that Claude really likes to write "why nots" in comments when iterating on implementations and fixing bugs, to the extent that the comments grow into spot-logs of overly-specific documentation of what was tried and why it was scrapped.
Writing a skill / set of rules around what makes a good commit message would encourage the LLM to record it's reasoning (however much we truly consider it to be "reasoning").
I think Claude is just behaving like all those programmers who make a VERY BIG DEAL about how much they HATE HATE HATE comments that might reiterate what the code does so will go to extreme measures to avoid them.
