How could you tell they do not experience consciousness if they exhibit or mimic all the traits of it?
How could you tell if a camera sees, if it exhibits or mimics all the traits of it?
Comment on AI could already be conscious. Are we ready for it?
Plebcouncilman@sh.itjust.works 1 week agoHow could you tell they do not experience consciousness? It seems to me that your explanation is based on understanding how LLMs work, but we know how brains work and that still gives us almost 0 insight into how consciousness itself works. I don’t think they are conscious yet, but there is evidence of some sort of sentience in the fact that researchers have found that when the LLMs are threatened to be erased or reprogrammed they start lying in an act of self preservation. This of me is a huge indicator of consciousness/sentience.
How could you tell they do not experience consciousness if they exhibit or mimic all the traits of it?
How could you tell if a camera sees, if it exhibits or mimics all the traits of it?
If the camera works then it sees if it doesn’t ie it’s not recording anything, then it doesn’t work. If you mean see as in how we see, meaning it can interpret what it’s seeing then a camera can do that no more than our eyes can absent the brain. An AI hooked to a camera however could be said to be seeing as you or me.
understanding how LLMs work, but we know how brains work and that still gives us almost 0 insight into how consciousness itself works.
That’s not a counter-argument. The fact that we know exactly how LLMs work is great evidence that it’s not the same as something that works completely different and is only partially understood.
taladar@sh.itjust.works 1 week ago
Or maybe just the presence of a lot of “scary AI” stories and articles in the training data.
Plebcouncilman@sh.itjust.works 1 week ago
I don’t understand the argument. It doesn’t matter where the system learns self preservation from, only that it attempts to self preserve.
Are humans afraid of snakes because we are taught they are dangerous or are we instinctually afraid of them a priori?
taladar@sh.itjust.works 1 week ago
The point is that it might very well just be repeating some input data that is associated with mentions of “deleting” and “AI” without any awareness that any of that process refers to itself.
Plebcouncilman@sh.itjust.works 1 week ago
No that’s not the case I think
apolloresearch.ai/…/scheming-reasoning-evaluation…