How Do We Align Artificial Intelligence with Human Values?

Posted by Peter Rudin on 3. March 2017 in News

A major change is coming across every segment of society, and the people playing a part in that transition have a huge responsibility and opportunity to shape it for the best. What will trigger this change? Artificial Intelligence!

Today, we have to start with the Value Alignment principle: Highly autonomous AI systems should be designed so that their goals and behaviors can be assured to align with human values.

While most researchers agree with the underlying idea of the Value Alignment Principle, not everyone agrees with how it’s phrased and how to implement it.

Recently, some of the top minds in AI and related fields got together to discuss how we can ensure AI remains beneficial throughout this transition, and the result was the Asilomar AI Principles document.


Leave a Reply

Your email address will not be published. Required fields are marked *