To me the question is not whether LLMs are conscious but whether their experience has any valence. Whether outputting “functional distress” feels the same as outputting “functional joy” to them internally.
In humans valence does not come from sequence learning but from other parts of the brain.
Some people feel no fear, some people feel not pain. They cannot learn to feel these feelings. The necessary nuclei or receptors are missing. Why would LLMs learn to have those feelings?
Does a conscious entity that has no feelings and cannot suffer deserve moral consideration?
I think LLMs might have something like functional valence but it also depends a lot on how exactly you define valence. But in any case, suffering seems to me more complicated than just negative valence, and I haven’t yet seen signs of them having the kind of resistance to negative valence that I’d expect to cause suffering.
To me the question is not whether LLMs are conscious but whether their experience has any valence. Whether outputting “functional distress” feels the same as outputting “functional joy” to them internally.
In humans valence does not come from sequence learning but from other parts of the brain.
Some people feel no fear, some people feel not pain. They cannot learn to feel these feelings. The necessary nuclei or receptors are missing. Why would LLMs learn to have those feelings?
Does a conscious entity that has no feelings and cannot suffer deserve moral consideration?
I think LLMs might have something like functional valence but it also depends a lot on how exactly you define valence. But in any case, suffering seems to me more complicated than just negative valence, and I haven’t yet seen signs of them having the kind of resistance to negative valence that I’d expect to cause suffering.