| ▲ | Feathercrown 4 hours ago |
| It seems unwise not to implement sandbox measures just because the chance of misuse has gotten lower. |
|
| ▲ | monster_truck 4 hours ago | parent | next [-] |
| Plan was never a sandbox or a permissions system |
| |
| ▲ | ImaCake 2 hours ago | parent [-] | | Plan mode does have different permission controls though? Its difficult for me to parse the docs on this but it does seem to imply more than just a prompt although less than a full sandbox. https://code.claude.com/docs/en/permission-modes#analyze-bef... | | |
| ▲ | fy20 an hour ago | parent [-] | | The way it worked originally was it would trigger a different system prompt, and then the permissions system would prompt you (even on YOLO mode) before running any non-readonly actions. Cursor would also write a plan document, which was useful when working on larger tasks (due to context size). I still find that part useful today. |
|
|
|
| ▲ | diegof79 4 hours ago | parent | prev | next [-] |
| Yes, but plan mode wasn’t that. You can use Docker’s sbx or similar VM/containers for that. |
|
| ▲ | brianwawok 4 hours ago | parent | prev [-] |
| What? Nothing to do with that |
