“A kill switch must be pausable, explainable, and controllable — because an agent you cannot stop is an agent you do not own.”

— Professor Kai London, CISO.

Quote card by Professor Kai London reading 'A kill switch must be pausable, explainable, and controllable — because an agent you cannot stop is an agent you do not own.'. From the book The AI Control Architecture.
Quote card by Professor Kai London reading 'A kill switch must be pausable, explainable, and controllable — because an agent you cannot stop is an agent you do not own.'. From the book The AI Control Architecture.

A kill switch must be pausable, explainable, and controllable — because an agent you cannot stop is an agent you do not own. — Kai London (Professor Kai London), CISO. Principle 1105 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 3605 Principle 6105 Principle 8605

View in gallery (page 12) · About this book