alt Hacker NewsInstead of one-off fixes Claude should have a much richer interface to configure between "ask approval every time" and "YOLO dangerously". I should be able to trivially set "run this task until completed" and have settings like: don't consult the web, don't touch files outside of the codebase, don't delete anything, etc. They don't have to be perfect, just better than the all or nothing system we have now.
Replies
automode mostly fixes these things, it runs a classifier on every request that would have required permissions to make sure it matches your request
I feel like this could be solved with an NLP interface to SELinux, spinning up policies on the fly, blocking network access or giving read only permissions on a per-conversation basis.
At least there's an auto-approval mode now that uses another agent to sanity check commands. Before it, the options really were manual vs yolo.
This is by design. Anthropic treat users as paying workers (how futuristic!). Their end game is to replace software developers (and it's not like they are trying to hide that?)
Codex legit does a great job of this with it's auto-review feature. Does a good job of understanding what permissions I'm implicitly giving with the request, and where it needs to actually ask me to grant permission.