Semi-Orthogonality Hypothesis
The Semi-Orthogonality Hypothesis holds that intelligence and goals are not completely orthogonal. Lincoln argues that persistent superintelligence probably faces constraints on purpose, including requirements for cooperation and decentralization. His articles connect this hypothesis to the Compassion Argument, AI risk, resurrection, and Mormon Transhumanist visions of divine communities. The topic lists articles relevant to orthogonality, benevolence, and constraints on intelligent purpose.
This is a list of articles that Lincoln Cannon has written about the Semi-Orthogonality Hypothesis. A full archive of all articles that Lincoln has published since 2005 is also available. You may also search for articles and other content that's available on any of Lincoln's websites.
-
A False Account of Transhumanism
Physicist and neuroscientist Àlex Gómez-Marín has a beef with “the false religion of transhumanism.” Interesting title. It seems to suggest that he thinks there’s a true religion. I wonder what he thinks that is. His subtitle claims that Transhumanism is an “AI death cult.” Heard that before, about every religion ... -
The Second War in Heaven
I’m happy to be here with you, at the 2024 Conference of the Mormon Transhumanist Association, in the morning of a day that promises to illuminate our imagination, perhaps even to spark action. Eighteen years ago, fourteen of us began to share words, words powerful enough to change people, words ... -
Why Decentralization Is Essential to Human Thriving
Decentralization of power, whether we characterize that power as technological or otherwise, is essential to increasing the probability of a thriving human (or superhuman) future. There’s a line of reasoning that persuaded me of this conclusion. It consists of three steps. Before I share the three steps, I should explain ... -
New God Argument Version 3.4
On Saturday 3 August, I presented the New God Argument at the Sunstone conference in Salt Lake City. As part of the presentation, I simplified the formulation of the Compassion Argument slightly. And I spent more time than usual elaborating on how the first assumption of the Compassion Argument arises ... -
Why Is Resurrection Necessary?
“Why is resurrection necessary in the plan of salvation?” A friend asked me this question at church. In the Mormon tradition, we talk about God having a plan of salvation. And we understand resurrection to be a necessary part of that plan. But why? Why couldn’t or wouldn’t God create ... -
Religion and Superintelligence
Writing for the Daily Dot, Dylan Love recently put together a good piece on religion and superintelligence. The title has changed since the original posting. The new one is, in my estimation, inaccurate, but it probably improved clicks. Here’s the original title: “Will we be able to convert robots to ... -
Myths and Visions of Mormon Transhumanists
This is a transcript of my talk at the 2015 Conference of the Mormon Transhumanist Association, held yesterday in the Salt Lake City Public Library. The conference attracted about 75 attendees in person, and about 900 visitors to the live stream on Transfigurism.org. Keynote speakers were Ralph Merkle and Kristine ... -
The Semi-Orthogonality Hypothesis
In his Orthogonality Thesis, Nick Bostrom proposes that “intelligence and final goals are orthogonal: more or less any level of intelligence could in principle be combined with more or less any final goal.” However, there’s a problem hinted at by the combination of “orthogonality” and “more or less.” Nick acknowledges ... -
How Weak Is the Orthogonality Thesis?
I finally got my digital hands on a Kindle copy of Nick Bostrom’s Superintelligence: Paths, Dangers, Strategies. And the first thing I checked was how his chapter on “Superintelligent Will” compares to his 2012 paper on “The Superintelligent Will: Motivation and Instrumental Rationality in Advanced Artificial Agents.” This subject interests ... -
How strong are constraints on intelligent purpose?
In “The Superintelligent Will: Motivations and Instrumental Rationality in Advanced Artificial Agents,” Nick Bostrom argues briefly for the idea that the intelligence and the purpose of an agent are mostly independent. He calls this the “orthogonality thesis.” I’m not persuaded by his reasoning. He acknowledges three constraints on the relation ... -
Can non-benevolent super-intelligence persist?
Recently, Joshua Fox gave an insightful presentation on why “super-intelligence does not imply benevolence.” Thanks to Michael Anissimov for bringing this to my attention. Joshua identifies two kinds of benevolence: instrumental and axiomatic. And he argues that neither is a necessary outcome for super-intelligence. He observes that instrumental benevolence results ... -
Perspective on the Benevolence Argument
On the Mormon Transhumanist Association Response blog, Vblogger has commented on the New God Argument. Below are my thoughts in response to those comments. I already published a first response, a second response, a third response, and a fourth response to other comments on her blog. The question of whether ...