How to tell if your AI is conscious

Have you ever talked to someone who is “into consciousness?” How did that conversation go? Did they make a vague gesture in the air with both hands? Did they reference the Tao Te Ching or Jean-Paul Sartre? Did they say that, actually, there’s nothing scientists can be sure about, and that reality is only as real as we make it out to be?

The fuzziness of consciousness, its imprecision, has made its study anathema in the natural sciences. At least until recently, the project was largely left to philosophers, who often were only marginally better than others at clarifying their object of study. Hod Lipson, a roboticist at Columbia University, said that some people in his field referred to consciousness as “the C-word.” Grace Lindsay, a neuroscientist at New York University, said, “There was this idea that you can’t study consciousness until you have tenure.”

Nonetheless, a few weeks ago, a group of philosophers, neuroscientists and computer scientists, Dr. Lindsay among them, proposed a rubric with which to determine whether an AI system like ChatGPT could be considered conscious. The report, which surveys what Dr. Lindsay calls the “brand-new” science of consciousness, pulls together elements from a half-dozen nascent empirical theories and proposes a list of measurable qualities that might suggest the presence of some presence in a machine.

For instance, recurrent processing theory focuses on the differences between conscious perception (for example, actively studying an apple in front of you) and unconscious perception (such as your sense of an apple flying toward your face). Neuroscientists have argued that we unconsciously perceive things when electrical signals are passed from the nerves in our eyes to the primary visual cortex and then to deeper parts of the brain, like a baton being handed off from one cluster of nerves to another. These perceptions seem to become conscious when the baton is passed back, from the deeper parts of the brain to the primary visual cortex, creating a loop of activity.

Another theory describes specialized sections of the brain that are used for particular tasks — the part of your brain that can balance your top-heavy body on a pogo stick is different from the part of your brain that can take in an expansive landscape. We’re able to put all this information together (you can bounce on a pogo stick while appreciating a nice view), but only to a certain extent (doing so is difficult). So neuroscientists have postulated the existence of a “global workspace” that allows for control and coordination over what we pay attention to, what we remember, even what we perceive. Our consciousness may arise from this integrated, shifting workspace.

But it could also arise from the ability to be aware of your own awareness, to create virtual models of the world, to predict future experiences and to locate your body in space. The report argues that any one of these features could, potentially, be an essential part of what it means to be conscious. And, if we’re able to discern these traits in a machine, then we might be able to consider the machine conscious.

One of the difficulties of this approach is that the most advanced A.I. systems are deep neural networks that “learn” how to do things on their own, in ways that aren’t always interpretable by humans. We can glean some kinds of information from their internal structure, but only in limited ways, at least for the moment. This is the black box problem of AI So even if we had a full and exact rubric of consciousness, it would be difficult to apply it to the machines we use every day.

And the authors of the recent report are quick to note that theirs is not a definitive list of what makes one conscious. They rely on an account of “computational functionalism,” according to which consciousness is reduced to pieces of information passed back and forth within a system, like in a pinball machine. In principle, according to this view, a pinball machine could be conscious, if it were made much more complex. (That might mean it’s not a pinball machine anymore; let’s cross that bridge if we come to it.) But others have proposed theories that take our biological or physical features, social or cultural contexts, as essential pieces of consciousness. It’s hard to see how these things could be coded into a machine. — The New York Times