Eliezer Yudkowsky

Eliezer Yudkowsky is a prominent AI safety researcher and co-founder of the Machine Intelligence Research Institute (MIRI), where he has worked on technical approaches to ensuring advanced artificial intelligence systems remain aligned with human values. He is best known for his work on decision theory, particularly Functional Decision Theory, and for articulating concerns about existential risks from artificial general intelligence. Yudkowsky has been influential in the rationality community, founding LessWrong (originally Overcoming Bias) as a platform for discussing rationality, AI safety, and related topics.

Before focusing on AI safety, Yudkowsky worked on the Singularity Institute (now MIRI) and has written extensively on topics including Bayesian reasoning, cognitive biases, and the philosophical foundations of AI alignment. His work emphasizes the importance of solving alignment problems before superintelligent AI systems are developed. He has become a central figure in contemporary AI safety discourse, influencing both academic research and policy discussions around AI governance.

Eliezer Yudkowsky is an American AI safety researcher and rationality advocate who co-founded the Machine Intelligence Research Institute (MIRI) and created LessWrong, a major online community for discussing rationality and existential risk. He is known for developing Functional Decision Theory and for articulating technical and philosophical approaches to AI alignment. His work has been foundational in establishing AI safety as a serious research field.