Eliezer Yudkowsky is an American artificial intelligence researcher concerned with the Singularity, and an advocate of Friendly Artificial Intelligence.

Yudkowsky is a Director, and co-founder of the Singularity Institute for Artificial Intelligence (SIAI). Yudkowsky is a fully-funded Research Fellow of the SIAI. Several of his written works have been published through the SIAI.

Friendly Artificial Intelligence

Yudkowsky's research work focuses on Artificial Intelligence designs which enable self-understanding, self-modification, and recursive self-improvement (also known as seed AI); and also on Artificial Intelligence architectures for stably benevolent motivational structures (also known as Friendly AI).

Written Works

Apart from his research work, Yudkowski is notable for his explanations of technical subjects in non-academic language, particularly on rationality, such as An Intuitive Explanation of Bayesian Reasoning. His writing style shows evidence of his early interest in writing science fiction.

Yudkowsky is the author of the SIAI publications "Levels of Organization in General Intelligence" and "Creating Friendly AI."

His most recent academic contribution is two chapters in Nick Bostrom's forthcoming edited volume Global Catastrophic Risks.

See also

• Seed AI - an AI theory advanced by Yudkowsky
• Singularitarianism - a moral philosophy advanced by Yudkowsky

External links

• Personal web site
• Biography page at KurzweilAI.net
• Biography page at SingInst.org

1979 births | Living people | Singularitarianism | Artificial intelligence researchers