“A model with authority must be pausable, explainable, and controllable — because an agent you cannot pause is an agent you do not control.”

— Professor Kai London, CISO.

Quote card by Professor Kai London reading 'A model with authority must be pausable, explainable, and controllable — because an agent you cannot pause is an agent you do not control.'. From the book The AI Control Architecture.
Quote card by Professor Kai London reading 'A model with authority must be pausable, explainable, and controllable — because an agent you cannot pause is an agent you do not control.'. From the book The AI Control Architecture.

A model with authority must be pausable, explainable, and controllable — because an agent you cannot pause is an agent you do not control. — Kai London (Professor Kai London), CISO. Principle 188 of 10000 from the book “The AI Control Architecture” — cybersecurity, AI security and OT resilience doctrine. Official sites: professorkailondon.com · kailondon.co.uk

Related: Principle 2688 Principle 5188 Principle 7688

View in gallery (page 2) · About this book