x

AI ALIGNMENT FORUM
AF

Law-Following AI

This Sequence of posts will argue that working to ensure that AI systems follow laws is a worthwhile way to improve the long-term future of AI. Additional relevant posts are also linked at the end of the Sequence.

The posts in this Sequence are by me in my personal capacity, and are not representative of OpenAI or any other organization.

Cover art by OpenAI's DALL•E.

11Law-Following AI 1: Sequence Introduction and Structure

Cullen

4y

5

4Law-Following AI 2: Intent Alignment + Superintelligence → Lawless AI (By Default)

Cullen

4y

2

2Law-Following AI 3: Lawless AI Agents Undermine Stabilizing Agreements

Cullen

4y

2

4Law-Following AI 4: Don't Rely on Vicarious Liability

Cullen

3y

2