Anthropic's Level 3 safety protections prevent Claude from providing instructions for creating chemical, biological, and nuclear weapons, but this is only meaningful if people don't jailbreak the system and if Anthropic's open-source competitors don't remove these restrictions entirely

factualpending

Speaker

Dave Blanchard

Evidence Quote

level three is the stage where...you have to make sure that it's not internally trained to do something rogue...and then you have to make sure no one jailbreaks it

Source

AI Experts Debate: AI Job Loss, The End of Privacy & Beginning of AI Warfare w/ Mo, Salim & Dave 176Peter H. Diamandis
Created: 8/11/2026, 6:17:01 AM

My Notes

Loading notes...