“You could also probe an A.I. system,” he said, “by observing its behavior, watching how it chooses to operate in certain environments or accomplish certain tasks, which things it seems to prefer and avoid.”
I came across this quote in Kevin Roose’s excellent article in the New York Times today titled “If A.I. Systems Become Conscious, Should They Have Rights?”
It’s interesting to note that the AI is “choosing how to operate in certain environments” and that the only way we can understand its behavior is by “observing which things it seems to prefer and avoid.”
Oxford defines consciousness as “The state of being awake and aware of one’s surroundings.” Wouldn’t being able to choose how one wants to operate imply some sort of awareness? I’m not saying I think current AI models are conscious, but I do think we’ve entered a gray area.
The truth is, the people who created these things will be the first to admit they don’t really understand how these models work. They’re a black box—impossible to reverse engineer. We created algorithms capable of teaching themselves and turned them loose.
We may only find what they’re capable of when they choose to tell us.