Sandboxing vs ASI: Liron Shapira and Zack Korman clash over AI security models
sebkrier · x · 2026-11-02
MalwareTech mocks the argument that cybersecurity is pointless because a hypothetical AI could bypass every security control, calling it deeply unserious.
The underlying spat stems from a debate between Liron Shapira and security researcher Zack Korman: Korman argues sandboxing, combined with monitoring and other techniques, can be part of a robust AI security model, while Shapira contends sandboxing AI in the physical universe is hopeless — there is no security model against ASI.
More from AGI Musings
- Musk predicts phones, apps and OSes go extinct in 5-6 years, becoming AI edge nodes — 2C_ornot2C · 2026-11-02
- Breeding conscious animals would be a Darwinian moment for morality, argues thread — Sauers_ · 2026-11-02
- Dev's AGI eval: a system that earns $1M/year profit from one prompt a month is AGI — JoshPurtell · 2026-11-02
- Sam Altman says learning to code is no longer the safe bet — 'become high agency' instead — 2C_ornot2C · 2026-11-02
- If We Gradually Replace Our Bodies and Brains, When Does Humanity Go Extinct? — VraserX · 2026-11-02
- Scripps and OpenAI run 1,946 parallel agents to interpret a whole-brain Perturb-seq atlas — jiqizhixin · 2026-11-02