13/01/2012 - Paper: The Ethics of Artificial Intelligence
There is a new paper by Nick Bostrom and Eliezer Yudkowsky on the ethics of Artificial Intelligence. It will appear in the Cambridge Handbook of Artificial Intelligence:
The possibility of creating thinking machines raises a host of ethical issues. These
questions relate both to ensuring that such machines do not harm humans and other
morally relevant beings, and to the moral status of the machines themselves. The first
section discusses issues that may arise in the near future of AI. The second section
outlines challenges for ensuring that AI operates safely as it approaches humans in its
intelligence. The third section outlines how we might assess whether, and in what
circumstances, AIs themselves have moral status. In the fourth section, we consider
how AIs might differ from humans in certain basic respects relevant to our ethical
assessment of them. The final section addresses the issues of creating AIs more
intelligent than human, and ensuring that they use their advanced intelligence for
good rather than ill.
This paper serves as a good introduction to the problem of Friendly AI.
10/12/2011 - Video Q&A with Singularity Institute Executive Director
A full transcript of this video is hosted at Less Wrong.
18/11/2011 - Draft of Muehlhauser & Helm, ‘The Singularity and Machine Ethics’
Louie Helm and Luke Muehlhauser, Singularity Institute staff, are sharing a draft of their chapter submission to The Singularity Hypothesis edited volume for feedback:
The Singularity and Machine Ethics
Abstract: Many researchers have argued that a self-improving artificial intelligence (AI) could become so vastly more powerful than humans that we would not be able to stop it from achieving its goals. If so, and if the AI’s goals differ from ours, then this could be disastrous for humans. One proposed solution is to program the AI’s goal system to want what we want before the AI self-improves beyond our capacity to control it. Unfortunately, it is difficult to specify what we want. After a brief digression concerning human intuitions about intelligence, we offer a series of “intuition pumps” in moral philosophy for our conclusion that human values are complex and difficult to specify. We then survey the evidence from the psychology of motivation, moral psychology, and neuroeconomics that supports our position. We conclude by recommending ideal preference theories of value as a promising approach for developing a machine ethics suitable for navigating the Singularity.
11/08/2011 - Complex Value Systems are Required to Realize Valuable Futures
A new paper by Eliezer Yudkowsky is online at our publications page, “Complex Value Systems are Required to Realize Valuable Futures”. This paper was presented at the recent Fourth Conference on Artificial General Intelligence, held at Google HQ in Mountain View.
Abstract: A common reaction to first encountering the problem statement of Friendly AI (”Ensure that the creation of a generally intelligent, self-improving, eventually superintelligent system realizes a positive outcome”) is to propose a single moral value which allegedly suffices; or to reject the problem by replying that “constraining” our creations is undesirable or unnecessary. This paper makes the case that a criterion for describing a “positive outcome”, despite the shortness of the English phrase, contains considerable complexity hidden from us by our own thought processes, which only search positive-value parts of the action space, and implicitly think as if code is interpreted by an anthropomorphic ghost-in-the-machine. Abandoning inheritance from human value (at least as a basis for renormalizing to reflective equilibria) will yield futures worthless even from the standpoint of AGI researchers who consider themselves to have cosmopolitan values not tied to the exact forms or desires of humanity.
Keywords: Friendly AI, machine ethics, anthropomorphism
27/01/2011 - The Singularity: a Philosophical Analysis
For those who missed it, philosopher of mind David Chalmers published “The Singularity: a Philosophical Analysis” last April, and has been giving occasional talks on the subject matter. Chalmers was initially inspired to think about the Singularity from his invitation to our Singularity Summit conference in 2009.
06/01/2011 - 2010 Singularity Institute Publications
Basic AI Drives and Catastophic Risks (Carl Shulman, 2010)
Coherent Extrapolated Volition: A Meta-Level Approach to Machine Ethics (Nick Tarleton, 2010)
Economic Implications of Software Minds (S. Kaas, S. Rayhawk, A. Salamon and P. Salamon, 2010)
From mostly harmless to civilization-threatening: pathways to dangerous artificial general intelligences (Kaj Sotala, 2010)
Implications of a software‐limited singularity (Carl Shulman, Anders Sandberg, 2010)
Superintelligence does not imply benevolence (Joshua Fox, Carl Shulman, 2010)
Timeless Decision Theory (Eliezer Yudkowsky, 2010)
The above are papers, below are presentations:
How intelligible is intelligence? (Anna Salamon, Stephen Rayhawk, János Kramár, 2010)
Whole Brain Emulation and the Evolution of Superorganisms (Carl Shulman, 2010)
What can evolution tell us about the feasibility of artificial intelligence? (Carl Shulman, 2010)
22/12/2010 - Michael Vassar on the Singularity Institute at the Audacious Optimism Dinner
27/10/2010 - Presentation by Joshua Fox/Carl Shulman at ECAP 2010: “Super-intelligence Does Not Imply Benevolence”
Anders Sandberg has a good overall writeup about what happened at the Singularity track at the European Conference on Computing and Philosophy. Fox and Shulman’s presentation was one among five SIAI presentations at the conference. Carl Shulman is a former Visiting Fellow of the SIAI and a recipient of a grant from SIAI-Canada. Joshua Fox is a long-time SIAI supporter and volunteer.
25/06/2010 - Robots go to work at Scotland hospital
The construction of the Forth Valley Royal Hospital in Larbert, Stirlingshire, cost a hefty sum of £300m British pounds, but its new method of patient-care promises to lead the way towards a brighter future. The hospital will use a number of worker robots to clean the facilities, bring fresh linen and food to patients, as well as dispense drugs and remove clinical waste. The machines will be set up to follow specific routs to make sure they don’t bump into obstacles or each other, and will move through corridors underneath the hospital. They will also have the ability to open doors and locate their exact position with the laser beams mounted on top of their forklift-like frames. And to minimize errors and problems, there will always be a human on stand-by.
Besides making the lives of nurses easier, one of the most important aspects of their application will be controlling infection. When dealing with disease, tasks are often separated between “dirty and clean”, and one person doing both jobs increases the risk of spreading the sickness. The robots, however, will be immune to such threats, and will make the hospital a safer place both for staff and patients.
The hospital workers will not have to worry about their jobs, however, as the primary mission of these robots will be to make sure staff have more time to spend with patients, while the machines do the manual work. The hospital opens in August, and it will be interesting to see how well this innovative method will work.
BBC has more details and a sort video here.
16/04/2010 - Banking center gets robotic guides
It looks like that highly stylish A.I. future promised to us by movies may finally be on its way to becoming a reality. A 395-acre Spanish banking center, which has no less than nine buildings and 5,500 employees, is turning to various high-tech to help greet and accommodate its guests. Perhaps the most impressive of all is its “swarm” of Santander Interactive Guest Assistants (SIGA) robots, which will help users find their way around the massive buildings. Of course, robotic tour guides have been in development since the 90s and several have already been deployed in museums in North America and Europe.The robots themselves look pretty cool. In appearance they resemble large red helmets, and can wisp effortlessly around the different destinations they are instructed to show the visitors around. They can also sense other people and robots around, so as not to bump into them, and follow maps that tell them exactly where everything in the financial center is located. They are WiFi-controlled and operate on touch-screen technology, which allows guests to choose their language, or access features such as an audio and video history of the banking center, or the Santander group itself.
The video below shows the robots in action, as well as the other highly impressive innovations, such as the LED-panels that can digitally expand and access various facilities around a miniature model of the financial center. All this must have cost a huge amount of money, but as the employees interviewed in the video say, they wanted to offer a truly unique experience for their visitors. If the robots and all the other technology works as smoothly as shown here, they might have indeed created an environment that can’t be found anywhere else in the world—yet. It’s a model that many other businesses and institutions will want to one day emulate, though can only sit back and admire for now.
09/04/2010 - Chalmers: “The argument for a singularity is one that we should take seriously”
Here is a quote from the Chalmers paper that I linked yesterday:
One might think that the singularity would be of great interest to academic philosophers, cognitive scientists, and artificial intelligence researchers. In practice, this has not been the case. Good was an eminent academic, but his article was largely unappreciated at the time. The subsequent discussion of the singularity has largely taken place in nonacademic circles, including Internet forums, popular media and books, and workshops organized by the independent Singularity Institute. Perhaps the highly speculative flavor of the singularity idea has been responsible for academic resistance to the idea.
I think this resistance is a shame, as the singularity idea is clearly an important one. The argument for a singularity is one that we should take seriously. And the questions surrounding the singularity are of enormous practical and philosophical concern.
Practically: If there is a singularity, it will be one of the most important events in the history of the planet. An intelligence explosion has enormous potential benefits: a cure for all known diseases, an end to poverty, extraordinary scientific advances, and much more. It also has enormous potential dangers: an end to the human race, an arms race of warring machines, the power to destroy the planet. So if there is even a small chance that there will be a singularity, we would do well to think about what forms it might take and whether there is anything we can do to influence the outcomes in a positive direction.
Great advice for everyone living in the 21st century!
08/04/2010 - David Chalmers on Singularity, Intelligence Explosion
Recently, David Chalmers announced that he was posting a new paper based on his Singularity Summit 2010 talk: “The Singularity: A Philosophical Analysis”. In his announcement, Chalmers notes, “I’m still an amateur on these topics and any feedback would be appreciated.” You can also watch a video of Chalmers’ Summit talk.
05/02/2010 - Which Consequentialism? Machine Ethics and Moral Divergence
Here’s a paper presented at the 2009 Asia-Pacific Conference on Computing and Philosophy by participants in SIAI’s 2009 Visiting Fellows Program that is making the rounds. The point of the paper, which was written by Carl Shulman, Nick Tarleton, and Henrik Jonsson, is that consequentialism as commonly discussed has a number of “free variables” where intuitions disagree about the right values of these variables. Therefore, machine ethics should draw on the emerging field of moral psychology to figure out how to fill in these free variables. This point is plainly put in the title of one of the last sections, “Current moral theories are inadequate for machine ethics”.
A reply from UK philosopher David Pearce has recently been posted by Roko Mijic at Less Wrong.
06/01/2010 - SIAI Media Director Michael Anissimov on KUSP Radio in Santa Cruz
On Sunday, January 3rd, I did an interview on KUSP in Santa Cruz, California, a National Public Radio affiliate. I talked to Rick Kleffel for an hour about the Singularity, the Singularity Institute, what we do, anthropomorphism, Friendly AI, and the like. It was for his “Talk of the Bay” radio program. Here is the audio archive.
audio/x-mpegurl
10/11/2009 - Hungry Optimizers with Low-Complexity Values
Check out my blog post, “Hungry Optimizers with Low-Complexity Values” at Accelerating Future.
11/09/2009 - Ed Boyden on the Singularity in Technology Review
Ed Boyden, who leads the Synthetic Neurobiology Group at MIT, is concerned about the Singularity, and will be speaking at our upcoming Singularity Summit conference in New York. He recently published the article “The Singularity and the Fixed Point” on the website of Technology Review, MIT’s magazine, which looks into the challenge of giving Artificial Intelligence proper motivations. Making theoretical progress on the question of, “how do we give Artificial Intelligence proper motivations, such that we can trust those motivations even if the AI becomes smarter and more powerful than humans?” is a primary reason for SIAI’s existence.
29/05/2009 - Reach: Robot video
28/05/2009 - Videos from Global Catastrophic Risks Conference Available
Video is now available from the Global Catastrophic Risks Conference held at Oxford University, July 2008. Lecturers include SIAI Scientific Advisor Prof. Nick Bostrom and SIAI Research Fellow Eliezer Yudkowsky.
26/05/2009 - Lectures by Steve Omohundro
A compilation of talks by SIAI Advisor Dr. Steve Omohundro, some not previously mentioned on this blog, is at Future Current.
In particular, note Omohundro’s talk on “AI and the Future of Human Morality” at the Silicon Valley World Transhumanist Association Meetup, May 2008. Video and a transcript are available online.
26/05/2009 - SIAI Team Members on The Future and You
Several SIAI Team members have been interviewed over the last year for Stephen Euin Cobb’s podcast, The Future and You:
- Scientific Advisor Professor Nick Bostrom , September 2008.
- SIAI Media Director Michael Anissimov, March 2008.
- As well as Director of Research Dr. Ben Goertzel, August 2008, mentioned earlier on this blog.
22/05/2009 - AGI-08 Video Available
Video from the AGI-09 conference, chaired by SIAI Director of Research Dr. Ben Goertzel and with the participation of SIAI Scientific Advisor Dr. Moshe Looks, is now available online.
14/04/2009 - Yudkowsky?s Talks
Jeriaska has compiled links to talks by SIAI Research Fellow Eliezer Yudkowsky, including some not yet mentioned on this blog, at Accelerating Future.
In addition, Tim Tyler has collected lectures and discussions by Yudkowsky. See the collection of links at Facebook.
06/04/2009 - Goertzel interviewed at the Immortality Institute
SIAI Director of Research Dr. Ben Goertzel was interviewed by Immortality Institute Executive Director Justin Loew at the ImmInst Sunday Evening Updates, Dec. 2008. Video is available online. Topics include Goertzel’s AGI roadmap, the Global Brain, and AGI risks.
30/03/2009 - Goertzel, Omohundro, Pell, and Lamis at Convergence08
SIAI Director of Research Dr. Ben Goertzel participated in a panel discussion on “AI Convergence with SIAI Scientific Advisors Dr. Barney Pell and Dr. Steve Omohundro, SIAI Director of Partnerships Jonas Lamis, and Google Director of Research Dr. Peter Norvig at Convergence ‘08.
21/03/2009 - Pitt Interviewed on OpenCog
Dr. Joel Pitt, working on OpenCog with support from SIAI, was interviewed by Russell Brown of the New Zealand TV show “Media7.”
