Eliezer S. Yudkowsky
Research Fellow
Singularity Institute for Artificial Intelligence
Email: sentience@pobox.com
Phone: (866) 983-5697
Redwood City, CA.
This is a temporary placeholder page. I've had a new personal
page on my schedule for some time, and hope to get to it soon.
Most of my old writing is horrifically
obsolete. Essentially you should assume that anything from 2001 or earlier was
written by a different person who also happens to be named "Eliezer
Yudkowsky". 2002-2003 is an iffy call.
First things first: Are you familiar with the concept of Vernor Vinge's
Singularity?
Since the
rise of Homo sapiens, human
beings have been the smartest minds around. Sometime in the next
few decades, we can expect technological advancements to break the
upper bound on intelligence that has held for tens of thousands of
years. The Singularity presents the human species with some
difficult issues, to which almost no one is paying attention because
they're too busy watching television. The Singularity Institute
for Artificial Intelligence, a 501(c)(3) public charity supported
primarily by individual donations, enables some people to tackle these
issues full-time. I am presently a full-time Research Fellow of
the Singularity Institute. Seeing humanity safely through the
Singularity is my vocation, the central quest around which my life is
organized.
Much of my writing appears on the website of the Singularity Institute for Artificial
Intelligence. If you haven't heard of the Singularity, then
you should forget about my personal website and go there first.
Nothing else here makes sense without that background.
My most recent material is two chapters I did for Nick Bostrom's
forthcoming edited volume Global
Catastrophic Risks. Anyone from academia, or anyone who
wants to see the references, should read
these first. These chapters were completed in early 2006,
and still represent my current views as of May 2006.
Cognitive biases potentially affecting judgment of global risks.
Introduces the field of heuristics
and biases (the experimental investigation of systematic human
errors and what they reveal about human cognition) from the perspective
of how known biases may throw off our reasoning about uncertain risks
to the human species.
Artificial Intelligence as a Positive and Negative Factor in Global Risk. How advanced artificial intelligence relates
to global risk as both a potential catastrophe and a potential
solution. Contains considerable background material in cognitive
sciences, and conveys much of my most recent views on intelligence, AI,
and Friendly AI.
I currently post daily on Overcoming Bias, a blog devoted to the art of human rationality.
I own, moderate, and occasionally post to the SL4
Mailing List.
A handful of things I've written that are not yet horrifically
obsolete as of May 2006:
Writings on human rationality:
Twelve Virtues of Rationality
(Short but sweet.)
The Simple Truth
(Why do people complicate this so much?)
An Intuitive Explanation of Bayesian
Reasoning
(Bayes for the bewildered.)
A Technical Explanation of Technical
Explanation
(More Bayes. Many of my other writings rely on this page.)
Cognitive
biases potentially affecting judgment of global risks
(If you aren't familiar with the field of heuristics and biases, you really, really want to read this.)
I am also presently blogging more rationality material at Overcoming Bias. Some of my favorite posts are Tsuyoku Naritai, Feeling Rational, Belief in Belief, Politics is the Mind-Killer, Universal Fire, and An Alien God.
Writings on Artificial Intelligence:
Artificial Intelligence as a Positive and Negative Factor in Global Risk. See above; contains helpful background in
cognitive science. This is the least obsolete thing I've written,
and you should probably read it before any of my earlier writings on AI.
Levels of
Organization in General Intelligence. Book chapter I wrote in
2002 for an edited volume, Artificial
General Intelligence, which is now supposed to come out in late
2006. I no longer consider
LOGI's theory useful for building de
novo AI. However, it still stands as a decent hypothesis
about the evolutionary psychology of human general intelligence.
Coherent
Extrapolated Volition. Takes a stab at saying what we might
wish to do with a Friendly AI if
we had the technical knowledge to build one.
Miscellaneous essays:
Yehuda Yudkowsky, 1985-2004.
The AI-Box Experiment
A Theory of Fun
All that stuff at Overcoming Bias
Fiction:
Non-Player Character
Prospiracy Theory
X17
Humor:
The 7 Signs of the Singularity
The Combined List of Artifacts
Friendly
AI Critical Failure Table
The Friendly Borg FAQ