Comments
-
Where is AI heading?The smartest people in the world are working on these things nonstop. I'm sure they've already considered this idea in some form or other. — punos
It is also the case that often there is a blind spot where nobody is looking. In todays AI development, the industry is exploding and busy applying the new technology in all those fields. There is no time nor incentive to think about core principles. -
Post-Turing Processing
-
Doubt, free decision, and mindI actually did provide two arguments. This is something you have to get used to, when somebody else attacks your position, it often feels like what they say doesn't make sense. But you cannot just say "you are wrong", or "you didn't give a reason". Then you are evading the discussion and come out as the weaker party. You did this several times already.
If you want a discussion, what you need to do is try to understand the others' position as good as you can, and then find a weak spot. This requires an open mind and creativity.
In my case I said that any logic that contains a reference to consciousness cannot be trusted. Earlier I gave a link to an article to prove my point. There are several things you can do: find one single counterexample of some logic that uses consciousness as an argument and is perfectly valid. Or go to the article and get some counter arguments there.
I also said that your proposition is basically the good old "free will" dilemma, wrapped in the term "doubt". I leave this to you, but there are ways to shoot a hole in that one too. -
Doubt, free decision, and mindSo you agree that the conclusion follows from OP? — MoK
No, I don't agree with OP. One of the things that makes it wrong is that both input and output side contain some version of consciousness. It is like dividing by zero. You can prove 5 / 0 = 2 / 0 bij cross multiplication, that results in "true". That doesn't mean 5 = 2.
One other thing I see is that you describe a situation of doubt in which you can make a decision, from which it follows that there is a free mind. The doubt is just there for hiding the fact that you say "because I can make a free decision, it follows there is a free mind (not explained by the deterministic brain)" Not much of a statement there, except of the old problem of free will.
What is consciousness to you? — MoK
Consciousness = First person perspective. Therefore the subject, it cannot be treated as an object. We can use language to point to it, but it cannot be used in logical reasoning, like dividing by zero.
that is the end of discussion. — MoK
What I find remarkable is that only this time, after I gave you these points, it felt like a real discussion - one where we agree to disagree, but that is fine. I find it remarkable because I mentioned all of these points before. Somehow you couldn't organize them yourself. Most likely because you were a bit preoccupied with your OP. I almost had to force you to look at it differently. Not a problem. But next time we engage, I will hold you to this same standard of looking at things from different angles. -
Where is AI heading?The question is about the language. To me 1) and 2) have an identical meaning, to noAxioms they are opposite.
-
Doubt, free decision, and mindOk, I'm not the guy to refuse a friendly request. But please debate with me on the things I say. That is how it works, you cannot only repeat your own viewpoint, you are asked to change your perspective temporarily, look around corners. It is also how I debate with you, I've shown multiple times that I am willing to take your position. Here is my logic, point by point, please use these points in your reply:
1) OP says, doubt : an experience of uncertainty in a situation. From that (and other observations) it follows there must be a free mind.
2) My problem is that "experience" and "mind" are both related to consciousness. There is so much debate about this topic, not leading to any useful conclusions. This post says it all: https://thephilosophyforum.com/discussion/15512/logical-proof-that-the-hard-problem-of-consciousness-is-impossible-to-solve . Basically it says: when consciouness is involved, logical thinking is not capable to draw conclusions. Wrong tools for the job.
3) So to test you logic, I proposed another, temporal, definition of doubt, one that does not require consciousness. A mechanical "doubt", so to speak. This alternative definition: doubt = "a situation of uncertainty".
4) That is where my little program comes in. It is very simple of course, it just shows you can make a choice even if the both options are equally preferable.
5) This shows that your OP depends on consciousness.
6) To me that means that I lose all interest in the matter, I have a different view on consciousness that shows why thinking/words are incapable of making conclusions about it, quite similar to the article I mentioned in 2)
7) I also wrote extensively about how I personally perceive a doubt and how I come to a decision in those cases. No "mind" involved here whatsoever, it feels more like how the computer program works.
8) One of the arguments you make is that your OP is about humans. But that is not even in your OP. -
Where is AI heading?This ChatGPT conversation shows me that ChatGPT has some true intelligent behavior. It had some difficulty to see my point, and then was able to change its perspective. After that it could explain the new viewpoint in clear terms, better than myself. That is more than just "smart".
-
Where is AI heading?
ChatGPT brings some clarity in the discussion.
https://thephilosophyforum.com/discussion/comment/939781
You said you were busy, so I opened the question to everybody. Feel free to do your thing.
The good thing is, we now fully agree. I knew it all the time, I always agree with you ;) -
Where is AI heading?Me: So that point is where the knowing starts, not where it ends? Isn't that open for interpretation?
ChatGPT: You bring up a good point! The phrase "passed the point" can indeed be interpreted in different ways depending on context. It can suggest moving beyond a particular state, which could be understood as:
1. Beyond knowing: They have moved past understanding, so now developers no longer know how it works or can predict it (as we initially interpreted).
2. Into knowing: They have crossed into a phase where developers do know how it works and can predict its behavior.
The ambiguity comes from how the sentence is phrased. Without further context, both interpretations could be valid, which does make it open to interpretation. If clarity is important, the sentence could be rewritten to more clearly convey whether it's suggesting that understanding has been lost or gained. -
Where is AI heading?
Can you (Wayfarer or anybody else) please explain why the two sentences are opposite and not the same? noAxioms and I don't seem to get it solved together.
1. AI has long since passed the point where its developers don't know how it works, where they cannot predict what it will do.
2. Today, AI developers know how AI works and can predict what it will do
The problem is maybe related to this. The first sentence describes "the point where its developers don't know". The question then is, is this the end of the beginning of a time period? My natural interpretation is that it is the end, so from that point onwards developers do know. Is that a language-dependent interpretation? My native language is Dutch.
ChatGPT says: The first sentence implies that AI has gone beyond the point where developers don't know how it works or predict its behavior, suggesting they’ve lost control or understanding.
But I still don't get it... It conflicts with all my logical circuits -
Limitations of the human mindYes and I should reformulate that. My real question is, would it work in humanities best interest or would it go after its own interest. I do think it will do the first, but the consequences of building an 'evil' or even just 'disruptive' computer with super-human intelligence is something nobody wants. And we cannot just assume it will be nice to us.
-
Limitations of the human mindit still wouldn't be enough to predict the behavior of the particles with 100% certainty — Skalidris
That is already true because the uncertainty principle states that we cannot know both the position and speed of a particle with perfect accuracy. This is not a limitation of technology, it is impossible "in principle". I can give you a source but the internet gives plenty details.
To me, that scenario is possible because our mind is limited by its building blocks. — Skalidris
That is true, and one of the core principles of my own little theory as well. My first article here is about fundamental versus conceptual reality. ( I thought it was a good idea to start that article with Kant, but the discussion went sideways because everybody has his own interpretation/understanding of Kant and they all tried to teach me a lesson. I am planning a follow up on this article. So I am happy with your 'bottom up' approach to philosophy )
I think it's arrogant for humans to think that somehow, the universe follows the same logic as the logic in our mind. — Skalidris
True. 100% agree
The basic wrong assumption here is that knowledge is information accumulation rather than information discard. — apokrisis
I don't see Skalidris makes that assumption, he just gives another way to tell the opposite, that even IF you knew everything, you could not predict it.
We have all the information we need to find the value of the nth digit of pi, and it can be discovered with complete certainty. But since it is an infinite series, there is no limit to the information we can extract from the running of the algorithm and tomorrow we will find more than we have today. — unenlightened
That's a good point also.
ENOAH about AI:Are they not just an extension of mind, and therefore, within its limitations? If the AI communicates in anything other than a human language, then I think, we can start talking beyond the limitations of human mind. — ENOAH
What we can do, and we are doing this on a limited basis in neural nets already, is create the conditions for intelligence to "emerge". That is the key aspect of my approach, to "get out of the way" as humans, so to speak, and let the thing evolve/emerge by itself. Finding these conditions is not unthinkable, and my idea is to let computers develop their own "language" or "representation code".
Having said all this, I do NOT believe an AI will understand the universe in its totality. But it might form its own concepts in a different way than ours. And it can have a higher speed/bandwidth/memory. So I expect it to become more intelligent than us.
Also, there is another limitation of the human mind, and that is that it is built on top of an animal brain that tries to survive. Causing a lot of trouble. A lot more to say on this, and a lot of open questions as well : will not having this animal brain make an AI naturally friendly or not? -
Where is AI heading?Strange. Here is my question: The "rephrase" I gave seems to me identical to what you say, literally a rephrasing. But my version leads to a contradiction with what you say after that. It seems to me you have a negation too many in your first sentence.
AI has long since passed the point where its developers don't know how it works, where they cannot predict what it will do. It really wouldn't be AI at all if it were otherwise, but rather just an automaton doing very defined and predictable steps. Sure, they might program the ability to learn, but no what it will learn or what it will do with its training materials. And the best AI's I've seen, with limited applicability, did all the learning from scratch without training material at all. — noAxioms
(My original response: ) Normally your responses read like I could've said it (but yours are better written), but this one I don't understand. Too many negations. Rephrased "Today, AI developers know how AI works and can predict what it will do" "If they wouldn't know, it wouldn't be AI" - you are saying that it would no longer be artificial? But then: "automaton doing very defined and predictable steps." Here it breaks. The rest seems to be just a bit complaining. Go ahead, I have that sometimes. -
Doubt, free decision, and mindok enough is enough. You are not discussing, you are just repeating and not trying to understand things in context.
-
Doubt, free decision, and mindchoice = "01" , that is: doubt
Then in this case the system to select a direction in a pseudo-random way, by selecting left or right from a previously generated list. -
Doubt, free decision, and mindAgain, you are not replying to what is written. Just repeating.
a = measureDistance("left")
b = measureDistance("right")
if a > b then choice = "right"
else if b > a then choice = "left"
else choice = "01" // used here to make sense with earlier example "01" == "doubt"
if choice == "left" or choice == "right" steerTo(choice)
else steerTo(takeNextItemFromAPreviouslyGeneratedListOfDirections() ) -
Doubt, free decision, and mindIf you redefine doubt as a "situation of uncertainty", you can implement a software program that handles uncertainty, no problem, that is my "01". Then there is no mind needed, nor any of your reasoning.
Put "experience" back in the definition and yes, my program fails. And then you get a "mind" as a requirement. Since there are many opinions on mind and experience, you must make explicit what you mean by those terms in your case. And then you have to prove that the "mind" in the output is not simply caused by the "experience" you put in. I said, this is a can of worms. -
Where is AI heading?Let's see it in context. You started by saying:
If we know how humans think, we can simulate thinking using a neural network — MoK
noAxioms pointed out that we might be able to do that without:
All he is saying is that there exists an exploratory approach to these kind of problems. You start with an idea, try it out in simulation, and continue from there, until you have something you like.It can be simulated even if one doesn't know how it works — noAxioms
In this mini-discussion about simulation, I think it is off topic how you define the end-result. It is not worth it either. noAxioms is just saying: dont wait for science to tell you how thinking works before you start building a (super-)human AI. -
Doubt, free decision, and mindAll I said was that my argument is not what you are saying. — MoK
I did not try to repeat your argument, I said on one end you shove "experience" in and at the other end "mind" comes out. You cannot deny that. It is just not the full argument.
That is what I mean by : try to read the others arguments -
Doubt, free decision, and mind
That is because experience is in your definition, and you do not accept my example. That is all fine, but it shows how thin the ice is your theory is standing on.But you were not able to define a doubtful situation in which experience is not needed. — MoK
This medium is more difficult than talking face to face. I don't know you personally, I don't see your face how you read this. What I do see is a repetition of arguments that make no sense to me. If I say "A" and you say "not A", that doesn't help. I see it in the other post too, where you comment noAxioms, you do not really seem to understand what he is saying, while for me it makes perfect sense. Instead of asking clarification, you start opposing him. At some point I can no longer contribute. -
Where is AI heading?With an IQ test for humans or adapted for a computer. There is tons of ideas for that.
-
Doubt, free decision, and mindAgain, you are reacting emotionally without really trying to understand what I am saying. I am not your enemy, I try to make your idea more clear and get it more precise.
I am saying that without the need for "experience" your logic fails.So according to you assigning a variable to be X which is arbitrary means that the computer has doubt — MoK -
Where is AI heading?
-
Doubt, free decision, and mindLook, you shove a term "experience" in your definition of doubt, and end up with a proof of "mind" at the other end. And you do this without explicitely pointing out what these two terms mean and how they relate. That is not a clear line of logic, it is confusing.
Instead, if you would define "doubt" without the need for "experience", you end up with my example program and there is no need for a mind at all.
That is what I call a can of worms. Don't feel offended, it is just that there is no end to the things you can discuss from here. -
Where is AI heading?This means that you didn't simulate any system in your life. Did you? — MoK
Of course he knows, he's a computer scientist.
He most likely means that we can try out different ideas until it starts thinking in a way that we like. Like the idea that I am proposing here. That doesn't imply that the brain works in the same way, in all its details. We might not even understand how the brain works. This is true, to some degree, for any simulation btw. -
Doubt, free decision, and mind
That opens a can of worms. Okay, let others continue this. I've done what I can.The existence of experience does not mean that there is a mind. — MoK -
Where is AI heading?That all is pretty much the opposite of what I said — noAxioms
Hope you still find a second because to me these two are the same, I just removed a pair of negations:
AI has long since passed the point where its developers don't know how it works, where they cannot predict what it will do. It really wouldn't be AI at all if it were otherwise, — noAxioms
Today, AI developers know how AI works and can predict what it will do" "If they wouldn't know, it wouldn't be AI" — Carlo Roosen
That is to say, it passed a point where they don't know. To me it means that after that point they do know... @anybody??? -
Doubt, free decision, and mindBy doubt I mean an experience of uncertainty in a situation — MoK
One of the things that you need to make clear is whether doubt requires consciousness. You use the word "experience" in your definition, so it seems, yes. You end up with the conclusion that, based on this definition, there must be a mind. If by "mind" you also understand consciousness, then the whole argument collapses. -
Doubt, free decision, and mindOne of the challenges on this forum is that people are not actually reading the responses of others, to the point that they really try to understand it. You cannot just state ""01" does not represent a doubtful situation as I defined it in OP" while I just claimed the opposite.
Discussion ends here until you provide a few logical steps that explain your point. -
Doubt, free decision, and mindLook, it is not too difficult to write a computer program that implements doubt.
00 = false
11 = true
01 = doubt — Carlo Roosen -
Doubt, free decision, and mindThen here our discussion ends because I also explained why this is not valid, you can perfectly have a state 'doubt' defined in a deterministic system.
-
Doubt, free decision, and mindOnly more modern program languages have "undefined" as a possible value for variables. Machine code hasn't
-
Doubt, free decision, and mindYou need to be more careful with your argumentation. You cannot just say the opposite of what I said. I gave an explanation of what I meant, you didn't. "In my program there is a memory location reserved. It contains data. The interpreter or compiler has a check and generates an error if you want to print it before you define it."
-
Doubt, free decision, and mindIn my program there is a memory location reserved. It contains data. The interpreter or compiler has a check and generates an error if you want to print it before you define it. But undefined means the same as doubt.
Look, it is not too difficult to write a computer program that implements doubt.
00 = false
11 = true
01 = doubt
Carlo Roosen
Start FollowingSend a Message
- Other sites we like
- Social media
- Terms of Service
- Sign In
- Created with PlushForums
- © 2024 The Philosophy Forum