Back
Eliezer Yudkowsky - Wikipedia
referenceCredibility Rating
3/5
Good(3)Good quality. Reputable source with community review or editorial standards, but less rigorous than peer-reviewed venues.
Rating inherited from publication venue: Wikipedia
Useful background reference for understanding a key figure who helped establish AI safety as a field; relevant for tracing the intellectual history of alignment research and existential risk discourse.
Metadata
Importance: 60/100wiki pagereference
Summary
Wikipedia biographical article on Eliezer Yudkowsky, co-founder of the Machine Intelligence Research Institute (MIRI) and a pioneering figure in AI safety and existential risk research. Yudkowsky is known for early foundational work on AI alignment, the concept of Friendly AI, and influential writings including the rationalist community blog LessWrong. His work has significantly shaped the discourse around superintelligence risk.
Key Points
- •Co-founded the Machine Intelligence Research Institute (MIRI), formerly the Singularity Institute, focused on technical AI alignment research.
- •Developed the concept of 'Friendly AI' and wrote extensively on the dangers of misaligned superintelligent systems.
- •Founded LessWrong, an influential rationalist community blog that helped cultivate early AI safety thinking.
- •Author of 'Harry Potter and the Methods of Rationality' and the 'Sequences', which spread rationalist and AI risk ideas widely.
- •Has become increasingly pessimistic about AI safety outcomes, publicly expressing high probability estimates for existential catastrophe from advanced AI.
Cited by 1 page
| Page | Type | Quality |
|---|---|---|
| Eliezer Yudkowsky | Person | 35.0 |
3 FactBase facts citing this source
Cached Content Preview
HTTP 200Fetched Apr 7, 202623 KB
Eliezer Yudkowsky - Wikipedia
Jump to content
From Wikipedia, the free encyclopedia
American AI researcher and writer (born 1979)
Eliezer Yudkowsky Yudkowsky at Stanford University in 2006 Born Eliezer Shlomo (or Solomon) Yudkowsky
( 1979-09-11 ) September 11, 1979 (age 46)
Chicago , Illinois , U.S. Organization Machine Intelligence Research Institute Known for Coining the term friendly artificial intelligence
Research on AI safety
Rationality writing
Founder of LessWrong Website www .yudkowsky .net
Eliezer Shlomo Yudkowsky ( / ˌ ɛ l i ˈ ɛ z ər j ʊ d ˈ k aʊ s k i / EL -ee- EH -zər yuud- KOW -skee ; [ 1 ] born September 11, 1979) is an American artificial intelligence researcher [ 2 ] [ 3 ] [ 4 ] [ 5 ] and writer on decision theory and ethics , known for popularizing ideas related to friendly artificial intelligence . [ 6 ] [ 7 ] He is the founder of and a research fellow at the Machine Intelligence Research Institute (MIRI), a private research nonprofit based in Berkeley, California . [ 8 ] His work on the prospect of a runaway intelligence explosion influenced philosopher Nick Bostrom 's 2014 book Superintelligence: Paths, Dangers, Strategies . [ 9 ] He is best known for If Anyone Builds It, Everyone Dies: Why Superhuman AI Would Kill Us All , a New York Times Best Seller he co-authored with Nate Soares , as well as the Harry Potter fanfiction Harry Potter and the Methods of Rationality .
Work in artificial intelligence safety
[ edit ]
See also: Machine Intelligence Research Institute
Goal learning and incentives in software systems
[ edit ]
Yudkowsky's views on the safety challenges future generations of AI systems pose are discussed in Stuart Russell 's and Peter Norvig 's undergraduate textbook Artificial Intelligence: A Modern Approach . Noting the difficulty of formally specifying general-purpose goals by hand, Russell and Norvig cite Yudkowsky's proposal that autonomous and adaptive systems be designed to learn correct behavior over time:
Yudkowsky (2008) [ 10 ] goes into more detail about how to design a Friendly AI . He asserts that friendliness (a desire not to harm humans) should be designed in from the start, but that the designers should recognize both that their own designs may be flawed, and that the robot will learn and evolve over time. Thus the challenge is one of mechanism design—to design a mechanism for evolving AI under a system of checks and balances, and to give the systems utility functions that will remain friendly in the face of such changes. [ 6 ]
In response to the instrumental convergence concern, which implies that autonomous decision-making systems with poorly designed goals would have default incentives to mistreat humans, Yud
... (truncated, 23 KB total)Resource ID:
d8d60a1c46155a15 | Stable ID: sid_QMLqCCtQ7X