|
| ▲ | ealready_value 2 days ago | parent | next [-] |
| Ever since they made auto-mode default I swear claude has tuned to use python commands instead of the Edit Tool to frustrate the ~security conscience~ luddites into using auto-mode. |
| |
| ▲ | whstl a day ago | parent [-] | | Yeah, It’s in the system prompt, Claude will tell you if you ask why it’s using Python. My theory is that Anthropic is just a vibe-coding company. Their goal is to capture the attention of white-collar non-coders, since programmers will jump ship fast to another model. |
|
|
| ▲ | bombcar 2 days ago | parent | prev | next [-] |
| That's what I meant - you give it an instruction that seems to work (always ask before deploy) and so you trust it, and then you notice it can easily convince itself to deploy without authorization ("the user asked me to fix this, and they must know it's a deploy ..."). It plays itself. |
|
| ▲ | aesthesia 2 days ago | parent | prev | next [-] |
| Is this about normal system prompt instructions or instructions for the auto mode classifier? I'd be a bit more surprised about the classifier forgetting instructions. |
| |
| ▲ | whstl a day ago | parent [-] | | Classifier? Prompts? This is commands blocked in settings.json I block destructive filesystem operations and destructive git usage via “deny” directives. I also have instructions injected in CLAUDE.md and re-injected on every single prompt. Claude just tried to use command concatenation to break those rules. I have also seen it writing a script with rm inside and running it. | | |
| ▲ | aesthesia 19 hours ago | parent [-] | | The commenter you replied to mentioned that you can customize the auto mode classifier by providing a prompt, implying that this would be a more robust way of constraining Claude's behavior. It wasn't clear from your response whether you were using this functionality. You might try it out as a way to more reliably prevent these kinds of workarounds. |
|
|
|
| ▲ | silversmith 2 days ago | parent | prev [-] |
| What seems to work for me is automation - read file hook that re-injects instructions in the prompt every 15 minutes. Switch on the filename and get language-specific instructions too. |
| |
| ▲ | whstl 2 days ago | parent [-] | | I have something that injects my relatively small prompt every message, and it still disobeys me after 10 messages or so. The violation above was precisely in this situation :/ |
|
