alt Hacker Newsthe argument to be made is that allowing anthropic to see it constitutes sending the threat.
sandbox your ai.
Replies
sidsud • yesterday at 7:12 PM
how does sandbox help in this case when you use a provider like anthropic/openai?
➕ show 2 replies
the argument to be made is that allowing anthropic to see it constitutes sending the threat.
sandbox your ai.
how does sandbox help in this case when you use a provider like anthropic/openai?
That is not what sandboxing solves. A good sandbox would inject credentials into provider API calls so that the model never sees credentials, but the provider is still going to see the transcript. Sandboxes do not require or imply that there is a local model. Sandboxes limit what the agent can access on the host machine as well as the network and public internet.