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.
More from Safety
- The overlooked risk in AI regulation: capture by militants, not just by firms — soumitrashukla9 · 2026-09-18
- Chris Rohlf: agents can't be deterred like humans — defense must move at machine speed — chrisrohlf · 2026-09-18
- Nathan Lambert: OpenAI hack via Claude shows closed models are the real AI risk tip — natolambert · 2026-09-18
- Researchers clash over whether training AI to disclaim consciousness makes models more misaligned — coherence · 2026-09-18
- Judea Pearl shares new causal inference papers while Congress debates AI regulation — yudapearl · 2026-09-18
- MIT Tech Review answers readers: could AI really kill us all? — nordicinst · 2026-09-18