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.
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 :)
What I find special about the TNGS is the Darwin series of automata created at the Neurosciences Institute by Dr. Edelman and his colleagues in the 1990's and 2000's. These machines perform in the real world, not in a restricted simulated world, and display convincing physical behavior indicative of higher psychological functions necessary for consciousness, such as perceptual categorization, memory, and learning. They are based on realistic models of the parts of the biological brain that the theory claims subserve these functions. The extended TNGS allows for the emergence of consciousness based only on further evolutionary development of the brain areas responsible for these functions, in a parsimonious way. No other research I've encountered is anywhere near as convincing.
I post because on almost every video and article about the brain and consciousness that I encounter, the attitude seems to be that we still know next to nothing about how the brain and consciousness work; that there's lots of data but no unifying theory. I believe the extended TNGS is that theory. My motivation is to keep that theory in front of the public. And obviously, I consider it the route to a truly conscious machine, primary and higher-order.
My advice to people who want to create a conscious machine is to seriously ground themselves in the extended TNGS and the Darwin automata first, and proceed from there, by applying to Jeff Krichmar's lab at UC Irvine, possibly. Dr. Edelman's roadmap to a conscious machine is at https://arxiv.org/abs/2105.10461
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.