Eliezer Yudkowsky Explained

Eliezer Yudkowsky
Birth Name:Eliezer Shlomo Yudkowsky
Birth Date:September 11, 1979
Organization:Machine Intelligence Research Institute
Known For:Coining the term friendly artificial intelligence
Research on AI safety
Rationality writing
Founder of LessWrong

Eliezer S. Yudkowsky (;[1] born September 11, 1979) is an American artificial intelligence researcher[2] [3] [4] and writer on decision theory and ethics, best known for popularizing ideas related to friendly artificial intelligence.[5] [6] He is the founder of and a research fellow at the Machine Intelligence Research Institute (MIRI), a private research nonprofit based in Berkeley, California.[7] His work on the prospect of a runaway intelligence explosion influenced philosopher Nick Bostrom's 2014 book .[8]

Work in artificial intelligence safety

See also: Machine Intelligence Research Institute.

Goal learning and incentives in software systems

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 . 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:

In response to the instrumental convergence concern, that autonomous decision-making systems with poorly designed goals would have default incentives to mistreat humans, Yudkowsky and other MIRI researchers have recommended that work be done to specify software agents that converge on safe default behaviors even when their goals are misspecified.[9] [6]

Capabilities forecasting

In the intelligence explosion scenario hypothesized by I. J. Good, recursively self-improving AI systems quickly transition from subhuman general intelligence to superintelligent. Nick Bostrom's 2014 book sketches out Good's argument in detail, while citing Yudkowsky on the risk that anthropomorphizing advanced AI systems will cause people to misunderstand the nature of an intelligence explosion. "AI might make an apparently sharp jump in intelligence purely as the result of anthropomorphism, the human tendency to think of 'village idiot' and 'Einstein' as the extreme ends of the intelligence scale, instead of nearly indistinguishable points on the scale of minds-in-general."[5] [10] In Artificial Intelligence: A Modern Approach, Russell and Norvig raise the objection that there are known limits to intelligent problem-solving from computational complexity theory; if there are strong limits on how efficiently algorithms can solve various tasks, an intelligence explosion may not be possible.[5]

Time op-ed

In a 2023 op-ed for Time magazine, Yudkowsky discussed the risk of artificial intelligence and proposed action that could be taken to limit it, including a total halt on the development of AI,[11] [12] or even "destroy[ing] a rogue datacenter by airstrike".[13] The article helped introduce the debate about AI alignment to the mainstream, leading a reporter to ask President Joe Biden a question about AI safety at a press briefing.

Rationality writing

Between 2006 and 2009, Yudkowsky and Robin Hanson were the principal contributors to Overcoming Bias, a cognitive and social science blog sponsored by the Future of Humanity Institute of Oxford University. In February 2009, Yudkowsky founded LessWrong, a "community blog devoted to refining the art of human rationality".[14] [15] Overcoming Bias has since functioned as Hanson's personal blog.

Over 300 blog posts by Yudkowsky on philosophy and science (originally written on LessWrong and Overcoming Bias) were released as an ebook, Rationality: From AI to Zombies, by MIRI in 2015.[16] MIRI has also published Inadequate Equilibria, Yudkowsky's 2017 ebook on societal inefficiencies.[17]

Yudkowsky has also written several works of fiction. His fanfiction novel Harry Potter and the Methods of Rationality uses plot elements from J. K. Rowling's Harry Potter series to illustrate topics in science.[14] [18] The New Yorker described Harry Potter and the Methods of Rationality as a retelling of Rowling's original "in an attempt to explain Harry's wizardry through the scientific method".[19]

Personal life

Yudkowsky is an autodidact[20] and did not attend high school or college.[21] He was raised as a Modern Orthodox Jew, but does not identify religiously as a Jew.[22] [23]

Academic publications

See also

External links

Notes and References

  1. . February 16, 2012. Timestamp 1:18.
  2. News: Silver . Nate . Nate Silver . 2023-04-10 . How Concerned Are Americans About The Pitfalls Of AI? . . 2023-04-17 . April 17, 2023 . https://web.archive.org/web/20230417223622/https://fivethirtyeight.com/videos/how-concerned-are-americans-about-the-pitfalls-of-ai/ . live .
  3. Web site: Ocampo . Rodolfo . 2023-04-04 . I used to work at Google and now I'm an AI researcher. Here's why slowing down AI development is wise . live . https://web.archive.org/web/20230411042255/https://theconversation.com/i-used-to-work-at-google-and-now-im-an-ai-researcher-heres-why-slowing-down-ai-development-is-wise-202944 . April 11, 2023 . 2023-06-19 . The Conversation . en .
  4. Web site: Gault . Matthew . 2023-03-31 . AI Theorist Says Nuclear War Preferable to Developing Advanced AI . live . https://web.archive.org/web/20230515111504/https://www.vice.com/en/article/ak3dkj/ai-theorist-says-nuclear-war-preferable-to-developing-advanced-ai . May 15, 2023 . 2023-06-19 . Vice . en .
  5. Book: Russell . Stuart . Stuart J. Russell . Norvig . Peter . Peter Norvig . 2009 . Artificial Intelligence: A Modern Approach . Prentice Hall . 978-0-13-604259-4. Artificial Intelligence: A Modern Approach .
  6. Book: Leighton, Jonathan . 2011 . The Battle for Compassion: Ethics in an Apathetic Universe . Algora . 978-0-87586-870-7.
  7. Book: Kurzweil, Ray. The Singularity Is Near. Viking Penguin. New York City. 2005. 978-0-670-03384-3. Ray Kurzweil. registration.
  8. Ford . Paul . February 11, 2015 . Our Fear of Artificial Intelligence . April 9, 2019 . . en . March 30, 2019 . https://web.archive.org/web/20190330074135/https://www.technologyreview.com/s/534871/our-fear-of-artificial-intelligence/ . live .
  9. Corrigibility . Soares . Nate . Fallenstein . Benja . Yudkowsky . Eliezer . Eliezer Yudkowsky . 2015 . AAAI Publications . AAAI Workshops: Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence, Austin, TX, January 25–26, 2015 . October 16, 2015 . January 15, 2016 . https://web.archive.org/web/20160115113546/http://aaai.org/ocs/index.php/WS/AAAIW15/paper/view/10124/10136 . live .
  10. Book: Bostrom. Nick. Nick Bostrom. Superintelligence: Paths, Dangers, Strategies. 2014. 978-0199678112. Superintelligence: Paths, Dangers, Strategies. Oxford University Press .
  11. News: Moss . Sebastian . 2023-03-30 . "Be willing to destroy a rogue data center by airstrike" - leading AI alignment researcher pens Time piece calling for ban on large GPU clusters . Data Center Dynamics . 2023-04-17 . April 17, 2023 . https://web.archive.org/web/20230417223624/https://www.datacenterdynamics.com/en/news/be-willing-to-destroy-a-rogue-data-center-by-airstrike-leading-ai-alignment-researcher-pens-time-piece-calling-for-ban-on-large-gpu-clusters/ . live .
  12. News: Ferguson . Niall . Niall Ferguson . 2023-04-09 . The Aliens Have Landed, and We Created Them . . 2023-04-17 . April 9, 2023 . https://web.archive.org/web/20230409160604/https://www.bloomberg.com/opinion/articles/2023-04-09/artificial-intelligence-the-aliens-have-landed-and-we-created-them . live .
  13. Hutson . Matthew . 2023-05-16 . Can We Stop Runaway A.I.? . en-US . The New Yorker . 2023-05-19 . 0028-792X . Eliezer Yudkowsky, a researcher at the Machine Intelligence Research Institute, in the Bay Area, has likened A.I.-safety recommendations to a fire-alarm system. A classic experiment found that, when smoky mist began filling a room containing multiple people, most didn't report it. They saw others remaining stoic and downplayed the danger. An official alarm may signal that it's legitimate to take action. But, in A.I., there's no one with the clear authority to sound such an alarm, and people will always disagree about which advances count as evidence of a conflagration. "There will be no fire alarm that is not an actual running AGI," Yudkowsky has written. Even if everyone agrees on the threat, no company or country will want to pause on its own, for fear of being passed by competitors. ... That may require quitting A.I. cold turkey before we feel it's time to stop, rather than getting closer and closer to the edge, tempting fate. But shutting it all down would call for draconian measures—perhaps even steps as extreme as those espoused by Yudkowsky, who recently wrote, in an editorial for Time, that we should "be willing to destroy a rogue datacenter by airstrike," even at the risk of sparking "a full nuclear exchange." . May 19, 2023 . https://web.archive.org/web/20230519014111/https://www.newyorker.com/science/annals-of-artificial-intelligence/can-we-stop-the-singularity . live .
  14. Book: Miller, James. Singularity Rising. BenBella Books, Inc.. 2012. registration. 978-1936661657.
  15. News: You Can Learn How To Become More Rational. Miller. James. Business Insider. July 28, 2011. March 25, 2014. August 10, 2018. https://web.archive.org/web/20180810011032/https://www.businessinsider.com/ten-things-you-should-learn-from-lesswrongcom-2011-7. live.
  16. Web site: Miller . James D. . Rifts in Rationality – New Rambler Review . newramblerreview.com . 28 July 2018 . en-gb . July 28, 2018 . https://web.archive.org/web/20180728221702/http://newramblerreview.com/book-reviews/economics/rifts-in-rationality . live .
  17. Web site: Inadequate Equilibria: Where and How Civilizations Get Stuck . Machine Intelligence Research Institute . Machine Intelligence Research Institute . May 13, 2020 . September 21, 2020 . https://web.archive.org/web/20200921034330/https://intelligence.org/equilibriabook/ . live .
  18. Snyder . Daniel D. . 2011-07-18 . 'Harry Potter' and the Key to Immortality . 2022-06-13 . . December 23, 2015 . https://web.archive.org/web/20151223191026/http://www.theatlantic.com/entertainment/archive/2011/07/harry-potter-and-the-key-to-immortality/241972/ . live .
  19. Packer . George . 2011 . No Death, No Taxes: The Libertarian Futurism of a Silicon Valley Billionaire . . 54 . October 12, 2015 . December 14, 2016 . https://web.archive.org/web/20161214085902/http://www.newyorker.com/magazine/2011/11/28/no-death-no-taxes . live .
  20. News: Matthews. Dylan. Pinkerton. Byrd. June 19, 2019. He co-founded Skype. Now he's spending his fortune on stopping dangerous AI.. Vox. March 22, 2020. March 6, 2020. https://web.archive.org/web/20200306002854/https://www.vox.com/future-perfect/2019/6/19/18632586/jaan-tallinn-skype-kazaa-artificial-intelligence-risk-threat. live.
  21. Web site: Saperstein. Gregory. August 9, 2012. 5 Minutes With a Visionary: Eliezer Yudkowsky. CNBC. September 9, 2017. August 1, 2017. https://web.archive.org/web/20170801082948/https://www.cnbc.com/id/48538963. live.
  22. News: Elia-Shalev . Asaf . Synagogues are joining an 'effective altruism' initiative. Will the Sam Bankman-Fried scandal stop them? . 4 December 2023 . . 2022-12-01.
  23. Yudkowsky . Eliezer . October 4, 2007 . Avoiding your belief's real weak points . live . https://web.archive.org/web/20210502195348/https://www.lesswrong.com/posts/dHQkDNMhj692ayx78/avoiding-your-belief-s-real-weak-points . May 2, 2021 . April 30, 2021 . LessWrong.

This article is licensed under the GNU Free Documentation License. It uses material from the Wikipedia article "Eliezer Yudkowsky".

Except where otherwise indicated, Everything.Explained.Today is © Copyright 2009-2024, A B Cryer, All Rights Reserved. Cookie policy.