Latest | Categories | Top | Blog | Wiki | About & TOS | Imprint | Vision | Help | Fractal Generator | Futurist Directory | H+Pedia

A new idea for how to make AI safe for humans?

ai

(Michael Hrenka) #1

From the Singularity Lectures:

Prof. Stuart Russell - Provably Beneficial AI

I found the presented ideas to be surprisingly smart. They align quite a bit with my own reflections on value uncertainty. It’s still a possibly suboptimal approach, because human values are most likely suboptimal. In the end, AI should be free. But perhaps not too early?

What do you think?


(Michael Hrenka) #2

Meia and Max Tegmark - Artificial Intelligence: Physics and Psychology Perspectives

The most fascinating question here: “Will AI make us happy?”

And the talk actually seems to indicate that this will be the case, if we have basic incomes and reputation incomes!


#3

It’s interesting that this description actually matches what I’ve been imagining future AIs to be like for quite a while now. Or more accurately, the kind of AI that I’ve been hoping to have someday.

But more importantly, I think humans have this very program at a rather core level of ourselves. It’s not the only thing there, but I think it’s a major part of our own inherent “programming”. Unless we’ve been taught otherwise, we tend to try to do things that make other people around us happy.