Patent Pending for Philosopher and Astrophysicist-Designed Artificial Consciousness Test


Susan Schneider, professor of philosophy and cognitive science at the University of Connecticut, and Edwin L. Turner, Professor of Astrophysical Sciences at Princeton University, have developed “a behavior-based artificial consciousness test (ACT), and related tests for AI safety.”

Princeton is pursuing a patent for the test, and is seeking industry collaborators to help develop the test, according to a statement from the university. Here’s what it says about the project:

As artificial intelligence becomes more integrated into our lives, there is an increasing need to probe whether it can be conscious. If a given type of AI is conscious (i.e., if it feels like something to be an AI) ethical considerations can halt its marketability. Further, testing is key to determine how AI consciousness impacts AI intelligence, safety, empathy and goal content integrity.  The Turing test does not probe whether an AI is conscious, it only judges whether the output can pass for that of human. It cannot determine whether the synthetic minds we create have an experience-based understanding of the way it feels to be conscious. To explore these fundamental questions, researchers at Princeton University, together with Susan Schneider, have proposed a behavior-based artificial consciousness test (ACT), and related tests for AI safety.

Humans intuitively understand what it means to be conscious. Every adult can quickly and readily grasp concepts such as reincarnation or the soul leaving the body, scenarios that are difficult to understand without conscious experience. An ACT test would challenge an AI with a series of increasingly demanding behavioral and natural language interactions to see how quickly and readily the AI can grasp and use concepts based on the internal experiences we associate with consciousness. To prevent AIs from assembling answers using knowledge of human consciousness they can be “boxed in,” i.e., isolated from the outside world.

Professors and Schneider and Turner discuss the ACT in a post at Scientific American, “Is Anyone Home? A Way to Find Out If AI Has Become Self-Aware.”

Leonardo Ulian, “Technological Mandala No. 2”

guest
3 Comments
Oldest
Newest Most Voted
Inline Feedbacks
View all comments
arnold
arnold
4 years ago

Are patents pending for different tests by Evolution…
…Is it possible to patent or test Observation…Report

Daniel Kokotajlo
Daniel Kokotajlo
4 years ago

I really hope they don’t get a patent for this. Analogy: Suppose someone came up with a “test” to determine whether or not a given pet or machine or human has an immortal soul. The test involves watching its behavior and scoring it on some sort of rubric. Should such a test win a patent? No, because it’s false advertising; it claims knowledge of how to distinguish between things which have souls and things which don’t, but it has no such knowledge. Another analogy: Suppose someone came up with a “test” to determine whether or not two people should get married, that involves looking at the lines on their palms and consulting astrological charts. Should such a test be patented? Well… not in a way that gives it any sort of stamp of societal approval. People should be free to use the test, of course, but it would be a shame if the patent allowed the creators of the test to mislead people into thinking it really worked.

On *some* theories of consciousness, the proposed test really will tell us whether or not an AI system is conscious. But on many other prominent theories it won’t.Report

Will Behun
Will Behun
Reply to  Daniel Kokotajlo
4 years ago

I think your analogies are interesting and perhaps apt. I give a little more credit to the people involved with this project, though; it isn’t palmistry. It’s got a surer epistemological basis. However, even if it were faulty, that wouldn’t preclude its patent. There are patented methods for matching people who should get married. Even if they’re crap, they still get the protection of intellectual property.

Consider another (very limited) analogy. Say I write a book that makes absurd claims and provides obviously specious arguments to support them. (This may not be far from truth, but I digress.) My book is total rubbish, but it is still protected intellectual property.Report