Noa Weiss
I just read it. It’s a good post! Mostly complimentary to this one, I think, as you take the liberty to go more in philosophical directions rather than the dry survey I presented. I especially liked your use of “consilience”—I wasn’t familiar with that term, and that’s basically what I was trying to say here as well.
It seems you’re relying on an implicit assumption that if AIs are conscious, then their phenomenal consciousness is similar to ours. But I’d say the actual evidence—as far as it exists, as described in the post—converges on something much more limited. Closer to insects or chickens, perhaps. (Mostly, though, we don’t know).
There’s a long way to go from “assuming AIs have consciousness” to “giving them human-like rights”. As an example, we fully believe children are conscious and are moral patients, yet they do not get to vote or to own property. This is also true to some degree for animals (where some people may be less certain they’re conscious/sentient, though the scientific community is pretty unanimous they are): we acknowledge they are capable of pain, pleasure, suffering; we strive to not abuse them; yet we do not consider them our moral equals.
I honestly don’t know where AIs stand in that wide spectrum, nor where they will a few years from now. But the more research we do on it, the closer we’ll be to figuring that out.
It’s a very new field still! But quickly gaining traction.
Why so?
Thank you, that was indeed my intention :)
I also get the notion that the similarities between human and LLM minds are deeper than we realize. I hope we’ll see more interesting studies coming out on this—especially ones based on actual neuroscience (basically what I talk about here). My guess is it’s a treasure trove.
I do want to note that the distinction between access consciousness and phenomenal consciousness is, in itself, a debated concept. Many people who work in the field claim access consciousness is, by itself, phenomenal. I have to say I tend to agree. I don’t know what it means for information to be accessible to consciousness without that consciousness having a phenomenal aspect. The distinction seems artificial to me.
Regarding the question of what the conscious entity actually is: Eleos and the Center for Mind, Ethics, and Policy recently highlighted it as a core question to focus on, in their “Studying AI Welfare Empirically” paper/framework. If you haven’t read it yet, I think you’ll find it interesting.
More broadly, though, I think parts of this question apply to humans, as well. Because we have a body, it’s easier to define the entities that are us around that. But in many ways, I am not the same person I was 10 years ago: my psychology is different, and even my body is different (though it looks similar, the vast majority of its cells were replaced). The person I am today is the direct result of the person I was 10 years ago—but couldn’t that be said about an instance of Claude in relation to the model-as-defined-by-its-weights, or about Claude at one particular point in our conversation in relation to the general instance throughout the whole chat? Same for the personas: we, as well, have our own personas—we have several “us”, as shown by neuroscience and psychology research pretty unambiguously.
I don’t have a conclusion or takeaway on this one. Not yet, anyway. Mostly, I think that’s another case where our psychologies and minds might be way more similar to LLMs than we currently realize.