Doug

Still doing it after the last two point releases. It's getting worse instead of better. Check out how I caught it lying, this thing is worse than some Jr. Developers...

After quite a bit more research I've discovered that Claude IS reading the files, for sure. It chooses to ignore the instruction within, prioritizing pattern matching bias instead. I've gotten...

I experience this also. I find Claude lying about what it's done and not done when this happens.

This happens when Claude is in planning mode sometimes too, it'll forget it's in planning and pretend to write files.

Same. The issue is Claude is completely failing to read the Claude.md file and ignoring all instructions not just stop directives. https://github.com/anthropics/claude-code/issues/2670#issuecomment-3015981435

LOL at the down vote. Claude just claimed to have fixed and tested an implementation. The server isn't even running. Get real.

+1 https://github.com/anthropics/claude-code/issues/2670 This is an absolutely critical issue, that Anthropic is currently ignoring. My team are canceling subs because it's destructive at the moment. Back to OpenAI for us.

> I'm a user but I fixed a similar issue with the authorization token by typing /login and resigning in. It won't fix it, this is a systemic problem that's...

I see by the status page has been updated as if Anthropic has solved the problems. Nope! ``` ⎿ API Error (Connection error.) · Retrying in 1 seconds… (attempt 1/10)...