Hacker News new | ask | show | jobs
by cowlby 64 days ago
I "fixed" this for myself with tweakcc which let's you patch the system prompts. I changed the malware part to just be "watch out for malware" and it's stopped being unaligned.

They really should hand off read() tool calls to a lean cybersecurity model to identify if it's malware (separately from the main context), then take appropriate action.

1 comments

The newest versions of the Claude Code package on npm just download the native executables and run that instead. Does tweakcc support that yet? Last time I tried it, there were some pretty huge error messages. For now I've been coping with a pinned version.