In general my approach to running arbitrary untrusted code is 20% sandboxing and 80% making sure that it’s an extremely low value attack target so it’s not worth trying to break in.
Programs are terminated after 1 second of runtime, they run in a container with no network access, and the machine they’re running on has no sensitive data on it and a very small CPU.
Recent articles
- How Rob Pike got spammed with an AI slop "act of kindness" - 26th December 2025
- A new way to extract detailed transcripts from Claude Code - 25th December 2025
- Cooking with Claude - 23rd December 2025