m_‮f

@ m_f @discuss.online

帖子

1874
评论

336
加入于

12 mo. ago

管理

Cyanide and Happiness lemm.ee

Fun Loops ▶️ midwest.social

Cyanide & Happiness discuss.online

AskUSA discuss.online

5小时前

The Boondocks
跳过
1

m_‮f @discuss.online 5小时前
Sourcing your posts from microfiche is one of the more impressive ways of contributing to the Fediverse, congrats!

6小时前

The Sensory Biology of Plants

I think pointing out the circular definition is important, because even in this comment, you've said "To be aware of the difference between self means to be able to [be aware of] stimuli originating from the self, [be aware of] stimuli not from the self, ...". Sure, but that doesn't provide a useful framework IMO.

For qualia, I'm not concerned about the complexity of the human brain, or different neural structures. It might be hard with our current knowledge and technology, but that's just a skill issue. I think it's likely that at some point, humankind will be able to compare two brains with different neural structures, or even wildly different substrates like human brain vs animal, alien, AI, whatever. We'll have a coherent way of comparing representations across those and deciding if they're equivalent, and that's good enough for me.

I think we agree on LLMs and chess engines, they don't learn as you use them. I've worked with both under the hood, and my point is exactly that: they're a good demonstration that awareness (i.e. to me, having a world model) and learning are related but different.

Anyways, I'm interested in hearing more about your project if it's publicly available somewhere

15小时前

The Sensory Biology of Plants

跳过

m_‮f @discuss.online 15小时前

I think the definition of consciousness meaning "internal state that observably correlates to external state" would clarify here. Gravel wouldn't be conscious, because it has no internal state that we can point to and say it correlates to external state. Galaxies/the universe doesn't either, as far as we can tell. Galaxies don't have internal state that represents e.g. other galaxies, other than including humans in that definition, but it would be more proper IMO to limit the definition the minimum amount of state possible. You don't count the galaxy as having internal state that represents external state, if you can limit that definition to one tiny, self-contained part of the galaxy, i.e. a human brain.

15小时前

The Sensory Biology of Plants

跳过

m_‮f @discuss.online 15小时前

I made another comment pointing this out for a similar definition, but OK so awareness is being able to "recognize", and recognize in turn means "To realize or discover the nature of something" (using Wiktionary, but pick your favorite dictionary), and "realize" means "To become aware of or understand", completing the loop. I point that out, because IMO the circularity means the whole thing is useless from an empirical perspective and should be discarded. I also think qualia is just philosophical navel-gazing for what it's worth, much like common definitions of "awareness". I think it's perfectly possible in theory to read someone's brain to see how something is represented and then twiddle someone else's brain in the same way to cause the same experience, or compare the two to see if they're equivalent.

As far as a computer process recognizing itself, it certainly can compare itself to other processes. It can e.g. iterate through the list of processes and kill everything that isn't itself. It can look at processes and say "this other process consumes more memory than I do". It's super primitive and hardcoded, but why doesn't that count? I also thinking learning is separate but related. If we take the definition of "consciousness" as a world model or representation, learning is simply how you expand that world model based on input. Something can have a world model without any ability to learn, such as a chess engine. It models chess very well and better than humans, but is incapable of learning anything else, i.e. expanding its world model beyond chess.

If you created a computer program capable of learning patterns in the behavior of its own process(es) and learning how those behaviors are similar/dissimilar or connected to those of other processes, then yes, I’d say your program is capable of consciousness. But just adding the ability to detect its process id is simply like adding another built in sense; it doesn’t create conscious self awareness.

I think we largely agree then, other than my quibble about learning not being necessary. A lot of people want to reject the idea of machines being conscious, but I've reached the "Sure, why not?" stage. To be a useful definition though, we need to go beyond that and start asking questions like "Conscious of what?"

15小时前

The Sensory Biology of Plants

跳过

m_‮f @discuss.online 15小时前

What do "sense" and "perceived" mean? I think they both loop back to "aware", and the reason I point that out is that circular definitions are useless. How can you say that plants lack a sense of self and consciousness, if you can't even define those terms properly? What about crown shyness? Trees seem to be able to tell the difference between themselves and others.

As an example of the circularity, "sense" means (using Wiktionary, but pick your favorite if you don't like it) "Any of the manners by which living beings perceive the physical world". What does "perceive" mean? "To become aware of, through the physical senses". So in your definition, "aware" loops back to "aware" (Wiktionary also has a definition of "sense" that just defines it as "awareness", for a more direct route, too).

I meant that plants don't have thoughts more in the sense of "woah, dude", pushing back on something without any explanatory power. But really, how do you define "thought"? I actually think Wiktionary is slightly more helpful here, in that it defines "thought" as "A representation created in the mind without the use of one's faculties of vision, sound, smell, touch, or taste". That's kind of getting to what I've commented elsewhere, with trying to come up with a more objective definition based around "world model". Basing all of these definitions on "representation" or "world model" seems to the closest to an objective definition as we can get.

Of course, that brings up the question of "What is a model?" / "What does represent mean?". Is that just pushing the circularity elsewhere? I think not, if you accept a looser definition. If anything has an internal state that appears to correlate to external state, then it has a world model, and is at some level "conscious". You have to accept things that many people don't want to, such as that AI is conscious of much of the universe (albeit experienced through the narrow peephole of human-written text). I just kind of embraced that though and said "sure, why not?". Maybe it's not satisfying philosophically, but it's pragmatically useful.