[not_kurt_godel]

> When I came back a few minutes later I saw my machine open a browser window in my regular Firefox and then navigate to the dialog in question. I had not told Claude Code to use any browser automation, and I was pretty sure it wasn’t possible for it to trigger mouse movements or keyboard shortcuts within a window, so how was it doing that?

I continue to feel validated in my refusal to use terminal-based LLMs on my local machine. Even if they don't do anything malicious, there are just too many things they can screw up that can cause me to lose a non-trivial amount of work and/or my machine and therefore ability to work.

[onlyrealcuzzo]

I'm shocked they don't come with a way to run them in a sandbox.

Shouldn't this be relatively easy for a $1T company to set up?

Isn't this trivial compared to the entire harness?

[fr3dx]

There is a builtin sandbox and various third-party options https://code.claude.com/docs/en/sandbox-environments

[eqmvii]

That's more or less what Claude Cowork is.

Every serious engineer I've seen try to use it ran away screaming, because of limitations in the sandbox.

I've also seen people set their coding agents up entirely within containers -- that may be the better way going forward, but it's an extra stop and a lot of extra plumbing to maintain.

[not_kurt_godel]

Doing so would be an effective admission that LLM guardrails are inherently probabilistic, unpredictable, and insecure. Plus the only truly robust sandbox approach would be clunky setup of a local VM.

[simonw]

That clunky VM setup is a what Claude Cowork does, which is Claude Code with extra safety features for non-programmers.

There was a big thread about that here the other day: https://news.ycombinator.com/item?id=48479452