factual

Red teaming gives no guarantees for generative AI

The phrase 'red teaming,' borrowed from Cold War adversarial exercises and cybersecurity, is not well defined for generative AI and offers no guarantees: there is no proof that ChatGPT cannot be jailbroken past its guardrails (e.g., to explain how to rob a bank), so relying on red teaming for safety is unjustified.

factualpending

Speaker

Tina Eliassi-Rad

Evidence Quote

“It's not like, 'Oh, here's Ethereum the proof, QED go home.' You cannot jailbreak this.”

Source

301 | Tina Eliassi-Rad on Al, Networks, and Epistemic Instability— Sean Carroll's Mindscape
Created: 6/13/2026, 12:26:13 AM

Your notes

Loading notes...