Claude Code 2.0
Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you.. Latest version: 2.0.1, last published: 11 hours ago. Start using @anthropic-ai/claude-code in your project by running `npm i @anthropic-ai/claude-code`. There are 153 other projects in the npm registry using @anthropic-ai/claude-code.
Something I realized about this category of tool (I call them "terminal agents" but that already doesn't work now there's an official VS Code extension for this - maybe just "coding agents" instead) is that they're actually an interesting form of general agent.
Claude Code, Codex CLI etc can effectively do anything that a human could do by typing commands into a computer.
They're incredibly dangerous to use if you don't know how to isolate them in a safe container but wow the stuff you can do with them is fascinating.
So tell us how to safely run this stuff then.
I was under the impression that Docker container escapes are actually very rare. How high do you rate the chance of a prompt injection attack against Claude running in a docker container on macOS managing to break out of that container?
(Actually hang on, you called me out for suggesting containers like Docker are safe but that's not what I said - I said "a safe container" - which is a perfectly responsible statement to make: if you know how to run them in a "safe container" you should do so. Firecracker or any container not running on your own hardware would count there.)
> So tell us how to safely run this stuff then.
That's the secret, cap... you can't. And it's due to in band signalling, something I've mentioned on numerous occasions. People should entertain the idea that we're going to have to reeducated people about what is and isn't possible because the AI world has been playing make believe so much they can't see the fundamental problems to which there is no solution.
polyrand