pydantic-monty investigation
Simon Willison revisited Monty and found that four sandbox resource-limit settings appear to work as advertised.
Simon Willison revisited pydantic-monty, a sandboxed subset of Python implemented in Rust. He asked Claude Code to inspect the most recent release, following his earlier exploration a few months ago. The key finding is that limits for execution duration, memory, allocations, and recursion depth all appear to behave as advertised.
Simon Willison has updated his investigation of pydantic-monty. Monty is a subset of Python implemented in Rust, with a design focus on letting Python code execute in a sandboxed environment. It has been a few months since he last studied Monty, and this time he asked Claude Code to review the recent versions and compiled the investigation results in a research project.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Simon Willison's Weblog →Summaries are AI-generated; the original article is authoritative.