Under the hood it's effectively running:

    docker run --rm -w $PWD:/workspace \
      python:3.11-slim \
      pip install -q patchpal && \
      <command>

This isn't any sort of fancy or interesting sandboxing, this is shelling out to "docker run", and not even using docker as well as it could.

Quoting from the linked page:

> The tradeoff is ~5-10 seconds of container startup overhead

Sure, maybe it's 5-10 seconds if you use containers wrong. Unpacking a root filesystem and spinning up a clean mount namespace on linux is a few ms, and taking more than a second means something is going wrong, like "pip install"ing at runtime instead of buildtime for some reason.

I can spin up a full linux vm and run some code in quicker than 5 seconds.

Works great when you have a clear verification signal (tests passing), but what drives convergence when that signal isn’t well-defined?

Launch an AI agent to operate on production servers/sql safely using tmux

https://news.ycombinator.com/item?id=47411242