Resilience and Adaptation to Advanced AI

By Jamie Bernardi

Jamie Bernardi argues that we can't rely solely on model safeguards to ensure AI safety. Instead, he proposes "AI resilience": building society's capacity to detect misuse, defend against harmful AI applications, and reduce the damage caused when dangerous AI capabilities spread beyond a government or company's control.

Source:
https://airesilience.substack.com/p/resilience-and-adaptation-to-advanced?utm_source=bluedot-impact

A podcast by BlueDot Impact.

Learn more on the AI Safety Fundamentals website.

Chapters

• 2:06 The Need for Societal AI Resilience
• 5:49 Adaptation’s Historical Successes
• 7:33 What is Adaptation to Advanced AI?
• 8:50 Formalising Adaptation
• 10:21 Example: Adapting to Spear Phishing Risk
• 11:41 What is AI Resilience?