Another theory describes specialised 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 AI 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.
And even to researchers who are largely on board with computational functionalism, no existing theory seems sufficient for consciousness.
“For any of the conclusions of the report to be meaningful, the theories have to be correct,” Lindsay said. “Which they’re not.” This might just be the best we can do for now, she added.
After all, does it seem like any one of these features, or all of them combined, comprise what William James described as the “warmth” of conscious experience? Or, in Thomas Nagel’s words, “what it is like” to be you? There is a gap between the ways we can measure subjective experience with science and subjective experience itself. This is what David Chalmers has labelled the “hard problem” of consciousness. Even if an AI system has recurrent processing, a global workspace, and a sense of its physical location — what if it still lacks the thing that makes it feel like something?
When I brought up this emptiness to Robert Long, a philosopher at the Center for AI Safety who led work on the report, he said, “That feeling is kind of a thing that happens whenever you try to scientifically explain, or reduce to physical processes, some high-level concept.”
The stakes are high, he added; advances in AI and machine learning are coming faster than our ability to explain what’s going on. In 2022, Blake Lemoine, an engineer at Google, argued that the company’s LaMDA chatbot was conscious (although most experts disagreed); the further integration of generative AI into our lives means the topic may become more contentious. Long argues that we have to start making some claims about what might be conscious and bemoans the “vague and sensationalist” way we’ve gone about it, often conflating subjective experience with general intelligence or rationality. “This is an issue we face right now, and over the next few years,” he said.
As Megan Peters, a neuroscientist at the University of California, Irvine, and an author of the report, put it, “Whether there’s somebody in there or not makes a big difference on how we treat it.”
We do this kind of research already with animals, requiring careful study to make the most basic claim that other species have experiences similar to our own, or even understandable to us. This can resemble a fun house activity, like shooting empirical arrows from moving platforms toward shape-shifting targets, with bows that occasionally turn out to be spaghetti. But sometimes we get a hit. As Peter Godfrey-Smith wrote in his book Metazoa, cephalopods probably have a robust but categorically different kind of subjective experience from humans. Octopuses have something like 40 million neurons in each arm. What’s that like?
We rely on a series of observations, inferences and experiments — both organized and not — to solve this problem of other minds. We talk, touch, play, hypothesize, prod, control, X-ray and dissect, but, ultimately, we still don’t know what makes us conscious. We just know that we are.
This article originally appeared in The New York Times.
Written by: Oliver Whang
©2023 THE NEW YORK TIMES