AI Safety Interview Question: Code a Sandbox to Block All SSH Outbound

nptacek · x · 2026-08-08

A user shared a new interview question reportedly used by top AI labs: candidates are asked to code a sandbox environment that completely blocks basic internal SSH requests from reaching the external internet. This reflects the extreme demand for robust low-level isolation to prevent agent jailbreaks and cyberattacks.

Original post →

More from coding & agent

coding & agent channel →