AI Philosophy: Why It’s Hard & State Of The Art
March 13, 2018 @ 3:30 pm - 5:30 pm PDT
The workshop starts with an overview of AI philosophy and how traditional approaches need updating because they pave the way for a singleton AI that will hardly be benevolent. We discuss potential alternative AI safety strategies and their shortcomings, e.g.:
Smart contracts between autonomous agents
Corporations as test bed for primitive AIs
Distilling general intelligence without a generally intelligent agent
We close with a brief survey of other interesting problems in AI safety and what we can hope for if we get it right.While this session focuses on a positive long-term future, most ideas should be relevant for current AI, blockchain, and computer security strategies.