Eliezer Yudkowsky

Eliezer Yudkowsky is an American artificial intelligence researcher, writer, and decision theorist recognized as a founding figure in the field of AI alignment. As a co-founder of the Machine Intelligence Research Institute, Yudkowsky has played a significant role in shaping the technical research agenda at MIRI and other research centers, contributing to the introduction of AI extinction risk to mainstream audiences. An autodidact who did not attend high school or college, Yudkowsky is known for his self-directed approach to intellectual inquiry, earning recognition across academia, policy circles, and the technology sector. He began articulating concerns about advanced artificial intelligence at a time when such risks were largely dismissed within mainstream computer science, emphasizing that sufficiently capable AI systems could pose existential threats due to poorly specified goals pursued with superhuman efficiency—a perspective that helped distinguish early AI safety research from science-fiction narratives.

Yudkowsky has spent decades developing the theoretical underpinnings of AI safety. He proposed the coherent extrapolated volition framework, which involves designing artificial intelligence systems to pursue what people would desire under ideal epistemic and moral conditions. His technical contributions include foundational work on decision theory, the formalization of Friendly AI concepts, and the identification of failure modes such as deceptive alignment and the sharp left turn. Yudkowsky's views on AI safety challenges are discussed in the undergraduate textbook "Artificial Intelligence: A Modern Approach" by Stuart Russell and Peter Norvig, and his work on the prospect of a runaway intelligence explosion influenced Nick Bostrom's book "Superintelligence: Paths, Dangers, Strategies."

Beyond technical research, Yudkowsky has produced a substantial body of public-facing writing. He founded LessWrong, a community blog, and has authored hundreds of articles outlining the dangers of artificial intelligence on the platform. His essay collection "Rationality: From AI to Zombies," also known as "The Sequences," compiles more than 300 essays on rationality, cognitive bias, philosophy, and artificial intelligence. His fanfiction novel "Harry Potter and the Methods of Rationality" uses elements from J. K. Rowling's Harry Potter series to illustrate topics in science and rationality. MIRI has also published "Inadequate Equilibria," Yudkowsky's ebook on societal inefficiencies. His book "If Anyone Builds It, Everyone Dies: Why Superhuman AI Would Kill Us All," co-authored with Nate Soares, became a New York Times Best Seller.

Yudkowsky has been featured on Time's list of the 100 Most Influential People in AI and was included in The New York Times's "Who's Who Behind the Dawn of the Modern Artificial Intelligence Movement." His work has been discussed or featured in The New Yorker, Newsweek, Forbes, Wired, Bloomberg, The Atlantic, The Economist, The Washington Post, and other major publications. He has appeared at TED, delivering a six-minute talk without slides or visual elements, and has been a guest on podcasts such as "Hold These Truths." Yudkowsky engages policymakers, technologists, and the public, contributing to the global conversation about the future of artificial intelligence, AI safety, and existential risk.