Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

How are these reliably extracted (hint: they’re not)


It's very easy to extract the system prompt from Claude Code: you can patch it to intercept HTTP calls it makes.

I wrote about one tool for doing that here: https://simonwillison.net/2025/Jun/2/claude-trace/


See https://mariozechner.at/posts/2025-08-03-cchistory/

Why do you think these aren't legit?




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: