Can a future artificial intelligence be made safe? And, assuming that AI safety is feasible,
[Note. This is a project proposal that was written in 1989. Published here for the
In a recent blog post titled Maverick Nannies and Danger Theses, Kaj Sotala gave a long and
How to Build an AGI — and How Not To So, you want to build an artificial general intelligence?
… or The Maverick Nanny with a Dopamine Drip Richard P. W. Loosemore Abstract My
Can we build a benevolent AI, and how do we get around the problem that
Reinforcement learning, the way it is now practiced in AI, is just old-fashioned Behaviorism on
Blogger WordPress Theme By Themesglance