Researchers clash: does sandboxing untested models actually stop supply chain attacks?

BlancheMinerva · x · 2026-09-18

A brief but substantive AI-security exchange: @anpaure argues supply chain attacks do not require sandboxing as a defense, while BlancheMinerva counters that the sandboxing under discussion is about keeping untested or under-tested models from accessing the internet. The disagreement centers on whether sandboxing targets supply chain risk or simply isolates untrusted model runtimes.

Original post →

More from Safety

Safety channel →