| ▲ | giancarlostoro 5 hours ago | |
I mean, it depends on what you're doing but I force claude to always commit code every time it finishes a todo. It never seems to stop doing that, so I run it in dangerous mode on Zed. I get to review the code after the fact anyway. | ||
| ▲ | Someone 5 hours ago | parent | next [-] | |
The risk isn’t that it makes weird commits; it’s that it may decide to clean up stuff and delete more than desired. - https://github.com/anthropics/claude-code/issues/4331 | ||
| ▲ | pluralmonad 5 hours ago | parent | prev [-] | |
The danger there is not that it commit bad things, but that as part of working the task it gets tricked into sending your env/secrets/credentials to prompt injectors. That would not show up in your commit diff. Edit: At the very least, I would not allow it to do indiscriminate web searching. | ||