| ▲ | fender256 3 hours ago |
| Exactly. Claude in a VM is the way to go. |
|
| ▲ | pianopatrick 2 hours ago | parent | next [-] |
| Might be more secure to get a real laptop and treat Claude as any other human worker. I.e. apply all the normal sysadmin tools that manage laptops for people to manage the laptop for Claude |
|
| ▲ | trvz 3 hours ago | parent | prev [-] |
| A VM hosted by someone else. Somethig on your personal notebook or the proxmox server in your garage is still too risky. |
| |
| ▲ | supermatt 2 hours ago | parent [-] | | Why are 3rd party hosted VMs safer than your own? | | |
| ▲ | trvz 2 hours ago | parent [-] | | They're not. When things go wrong it's better to compromise someone else's VM host than your own computer. It's only a matter of time now until AI will find novel ways to break out of virtualisation. | | |
| ▲ | faeyanpiraat an hour ago | parent [-] | | In the short term wouldnt a “dont escape” prompt prevent this? Also if it started being widespread wouldnt Anthropic specifically train new models against doing it? | | |
|
|
|
