Current AI safety defenses ('guardrails' and 'cages') have all been defeated by jailbreak attempts, and we have no proven method to build a containment mechanism that is guaranteed to hold a superintelligent AI.
factualpending
Speaker
Yoshua BengioEvidence Quote
“everything we've tried has been defeated. So people do these uh jailbreak prompts, for example, that break all the defenses that the companies that working on AI have been able to figure out.”
Created: 8/12/2026, 6:45:56 PM
My Notes
Loading notes...