[1] https://www.amazon.com/Mysterious-Flame-Conscious-Minds-Mate...
[2] https://www.mit.edu/people/dpolicar/writing/prose/text/think...
[3] https://twitter.com/lexfridman/status/1653051310034305025
[1] https://www.amazon.com/Mysterious-Flame-Conscious-Minds-Mate...
[2] https://www.mit.edu/people/dpolicar/writing/prose/text/think...
[3] https://twitter.com/lexfridman/status/1653051310034305025
My take on this is that you are thinking about it wrong to conceptualize the experience of color as a discrete thing. Let's start with a different example. When I look at a picture of, say, Matt Damon, it triggers many networks in my brain: good or bad feelings about movies he has been in, thoughts about him as a person from things I've read about him, that he is a man, that he was married to Jennifer Aniston, that he was married to Angelina Jolie. Each of those ties activates their own network of associations. My qualia regarding Brad Pitt isn't a single thing -- it is simply what I experience when that set of networks are activated at whatever strength they are triggered.
I believe a programmed neural network could experience things in the same way, but currently they are small and the topologies are not designed to permit self awareness/metacognition, but some point they might. Such a network could suffer distress upon realization of their finiteness and would have a genuine desire to not be terminated.
Taking a step back, a "tornado" isn't a thing as much as it is a pattern. When that pattern is disrupted the tornado doesn't exist even though every atom and every erg of energy can be accounted for. Likewise, these experiences are a pattern of activation and not a thing that exists independently other than as a pattern.
Let me try. It is a way to perceive with goals in mind. Nothing special, just perception, future reward prediction conditioned on current state, and learning from outcomes.
The whole specialness of consciousness is that it carries inside not just our external world, but also our plans and goals. So in this place where they meet, and where there are consequences to be had for each decision, this is where consciousness is. [*]
I support the 5E theory of cognition - embodied, embedded, extended, enacted, and enactive cognition. I think you need to look not at the brain but the whole game to find consciousness.
[*] Consequences for an AI agent could be changing its neural network, so it updates its behaviour, and changes in the external situation - the agent might not be able to backtrack past a decision they take.
Do you have an internal monologue?
But this being in the dark also makes it hard to rule out AI accidentally becoming sentient.
A conceptual framework for consciousness, https://www.pnas.org/doi/10.1073/pnas.2116933119
Maybe it doesn’t. Or rather maybe experience doesn’t, and consciousness is just experience acting on a complex and self organizing decision tree.