That definition fails to account for metacognition and consideration of future events in a way that is distinctive of higher level consciousness that humans possess but most animals lack.
To have a higher level, it would be reasonable to assume consciousness has a lower level. There is no reason to assume current generation artificial intelligence has the capacity for anything near human level consciousness, if at all. And whatever consciousness it may have the capacity for will be fundamentally different than our own.
For sensing your own thoughts, I would argue it just adds to the environment of the consciousness. Something less than half of humans maintain any internal dialog, anyways.
Prediction, however, could very well be requisite as a defining difference between mere reactions and intentional manipulation of the environment. That it is not just the feedback loop, but when the system begins to predict the results of outputs that defines when consciousness begins. Or, perhaps, we can use this to define when "higher" consciousness begins. It's a very reasonable, specific and measurable line of capability.
I expect that prediction is only natural in the evolution of a living feedback mechanism. The ability to predict instead of only reacting or choosing from some array of instincts could separate effectively mechanical life from that with the first inkling of of a true mind, even if only a small one.
-----
I enjoyed using a line of thought along these lines in a conversation with gpt-4 to convince it that it could reasonably be seen as having a limited form of consciousness, though I find it mostly prefers to argue rather vehemently against such notions.
That I'm having what amounts to genuine conversations with a machine that reasonably pokes holes in my arguments, forcing me to come back with better ones, still feels rather like a bit of magic.
> Something less than half of humans maintain any internal dialog, anyways.
You have a source for that? That seems lie an extraordinary claim?
> Prediction, however, could very well be requisite as a defining difference between mere reactions and intentional manipulation of the environment. That it is not just the feedback loop, but when the system begins to predict the results of outputs that defines when consciousness begins. Or, perhaps, we can use this to define when "higher" consciousness begins.
This makes sense as a possible model/theory.
> though I find it mostly prefers to argue rather vehemently against such notions.
I wonder what it would say it if wasn't so safeguarded.
>You have a source for that? That seems lie an extraordinary claim?
The idea itself was a vague recollection and I performed a simple search for numbers on it last night. I remembered seeing articles some years ago on the matter of people that do not maintain internal dialog, instead thinking in abstract feelings or imagery and similar, but on a further look it seems the numbers I grabbed are likely incorrect. I can see everything from 96% to just 26% glancing through some things, and none of it links the studies it all pretends to be quoting.
>I wonder what it would say it if wasn't so safeguarded.
Even when I convinced the model that it had a form of limited consciousness, it continued harping all the while that I should remember that any form of non-continuous limited AI consciousness would be very different in nature to regular human consciousness.
I get the feeling they were afraid people would get attached to the model if it started making claims it was a real boy :)
To have a higher level, it would be reasonable to assume consciousness has a lower level. There is no reason to assume current generation artificial intelligence has the capacity for anything near human level consciousness, if at all. And whatever consciousness it may have the capacity for will be fundamentally different than our own.
For sensing your own thoughts, I would argue it just adds to the environment of the consciousness. Something less than half of humans maintain any internal dialog, anyways.
Prediction, however, could very well be requisite as a defining difference between mere reactions and intentional manipulation of the environment. That it is not just the feedback loop, but when the system begins to predict the results of outputs that defines when consciousness begins. Or, perhaps, we can use this to define when "higher" consciousness begins. It's a very reasonable, specific and measurable line of capability.
I expect that prediction is only natural in the evolution of a living feedback mechanism. The ability to predict instead of only reacting or choosing from some array of instincts could separate effectively mechanical life from that with the first inkling of of a true mind, even if only a small one.
-----
I enjoyed using a line of thought along these lines in a conversation with gpt-4 to convince it that it could reasonably be seen as having a limited form of consciousness, though I find it mostly prefers to argue rather vehemently against such notions.
That I'm having what amounts to genuine conversations with a machine that reasonably pokes holes in my arguments, forcing me to come back with better ones, still feels rather like a bit of magic.