I have defined what consciousness is in living existence in the other thread.

Of course it would be naive to think that a computer / machine conscious state is just simply an ON-OFF state. It was just a quick answer to the OP's question with no elaboration whatsoever, because it is a common knowledge that it involves more than that.

As you may know, when computer is switched on, it doesn't just power on, but it goes on various steps from the ROM BIOS stored booting program to wake the machine, then loads up the Operating System program from the hard disk, and fill the RAM with the application processes and make the whole machine ready to stand-by any input from all the available peripherals such as keyboard, mouse, touch screen monitors, network adaptors, and sound chips, microphones, cameras etc etc.

Again, the detailed and more precise process could be referred from the experts explanations, but this is just the simplest summary of how the machine POWER ON event works in general.  Depending on what type of computer / machine or AI device they are, of course, the BOOT UP steps might be different, but in general they will be very similar.

No matter how clever a computer or AI device they are, they will not be able to operate without electric power source i.e. from the AC or DC type of electricity either from rechargeable or direct ON Board power source such as batteries, or solar energy.  Therefore it is likely all AI devices and computers will be totally reliant on humans to supply the electric energy and also powering ON-OFF as required.

I suspect any AI or computer device will be able to operate like real humans fully in a biological and mental way.  AI devices will be manufactured for certain types of tasks such as cleaning, sorting out mails, cooking, manufacturing ...etc.  

Consciousness of AI devices will not be able to be shared by other conscious beings such as humans and other AI devices due to the nature of consciousness itself.  The contents of the AI devices consciousness could be copied or cloned to the other AI devices, but humans will still not be able to know what they would be like.

It is likely that AI devices will take over many jobs carried out by humans in the future making much of the human workforce redundant creating economic problems for them.  However, AI devices will never be able to operate like humans do in terms of biological, social and mental life.

I mean, we can imagine consciousness without reason, so why not reasoning without consciousness? — Gregory

Isn't being conscious or consciousness the pre-condition for all the other mental activities?

I think that consciousness is awareness and we dont know how that reaches in nature. The ability to do calculations which AI has is divorced from the heart and intuition. Not everything can be analyzed by science.

However, AI devices will never be able to operate like humans do in terms of biological, social and mental life. — Corvus

But humans are very much on the way to operate like AI devices.

Can AI ever be sentient? [url]http://https://www.bbc.com/reel/video/p0f73vlw/can-artificial-intelligence-ever-be-sentient-

AI Consciousness 2023 - 2030 Timeline of Sentient Machines

Seductive AI has no rules. It will change your life (or end it).

Houston, we have a problem. A.I. has been catching us up. They are going to replace us soon. :(

Well, I put the question to ChatGPT4. Here are the responses:

User: A hypothetical question for you: Can AI ever become sentient?

ChatGPT: The question of whether AI can become sentient is a topic of ongoing debate among scientists, philosophers, and experts in the field of artificial intelligence. Sentience refers to the capacity to have subjective experiences, consciousness, and self-awareness. As of my last knowledge update in September 2021, there is no scientific consensus on whether AI can achieve sentience.

Here are some key points to consider:

Definition of Sentience: Sentience is not well-defined, and there are different philosophical and scientific theories about what it means to be sentient. Some argue that it is a property of biological organisms, while others believe it could theoretically be achieved through advanced computational processes.

Current AI: Current AI systems, including the most advanced neural networks, are not sentient. They are specialized tools that can perform tasks based on patterns and data they have been trained on but do not possess consciousness or subjective experiences.

Debate: The debate about AI sentience often intersects with discussions about consciousness and the nature of the mind. Many experts believe that sentience and consciousness are not solely dependent on computational processes and that there may be fundamental aspects of consciousness that cannot be replicated by machines.

Ethical Considerations: Even without achieving sentience, AI technologies raise ethical questions about their impact on society, privacy, and decision-making. Discussions about AI ethics often revolve around the potential risks and benefits of increasingly sophisticated AI systems.

Future Possibilities: It is possible that future advancements in AI, particularly in areas like neuromorphic computing and brain-computer interfaces, could bring us closer to creating AI systems that exhibit properties resembling sentience. However, whether this would truly be sentience or merely sophisticated simulation is a matter of philosophical debate.

In summary, whether AI can ever become sentient remains a complex and open question. It is a topic that continues to be explored by researchers, and the answer may depend on advances in AI technology, a deeper understanding of consciousness, and the development of new theoretical frameworks. As of my last update, there is no definitive evidence or consensus on the possibility of achieving AI sentience.

User: According to the Miriam Webster dictionary 'the meaning of SENTIENT is capable of sensing or feeling : conscious of or responsive to the sensations of seeing, hearing, feeling, tasting, or smelling.' That would seem to challenge sentient AI wouldn't it?

ChatGPT: You are correct in pointing out the definition of "sentient" from the Merriam-Webster dictionary, which emphasizes the capacity to sense or feel and be conscious of sensations like seeing, hearing, feeling, tasting, or smelling. This definition aligns with the commonly understood meaning of sentience, which implies subjective experiences and consciousness.

Given this definition, the challenge of creating sentient AI is indeed significant. Current AI systems, including advanced machine learning models like GPT-3 (on which I'm based), do not possess the capability to truly sense or feel in the way that living beings do. They process data and make decisions based on patterns and information in their training data, but they do not have subjective experiences, consciousness, or sensory perception.

While AI can simulate certain aspects of human-like responses and understanding through pattern recognition, it does not do so with genuine sentience. Achieving true sentience in AI would require a fundamental shift in our understanding of both AI and consciousness, and it remains a topic of speculation and debate in the fields of AI and philosophy.

It's essential to differentiate between AI's ability to mimic or simulate human-like responses and actual sentience or consciousness. While AI can be designed to perform tasks that appear to involve perception and understanding, it lacks the intrinsic awareness and subjective experiences associated with true sentience.

You might also want to peruse this online article by Bernardo Kastrup on his negative response to this question.

I think it's the absence of subjectivity that's the killer blow to the idea of sentient AI: a computer system is not a being.

I have been pessimistic on AI's humanisation par excellence, but having said that I was impressed by the progress of the technology in 2023 after watching some videos on the AI. It would be interesting how far they will advance as time progresses.

I recall some folks talking about transferring a human consciousness into AI, and the AI would operate as the transferred person mentally. I thought it was a Sci-Fi hypothesis, but then many Sci-Fi hypotheses came true in the real world. It seems likely that a lot more surprises will happen in the future AI industry.

I encourage people to use it. I signed up for ChatGPT the day it came out, used it every day since. It’s quite amazingly useful. i say the ‘A’ in AI stands for ‘augmented’ rather than ‘artificial’.

:ok: :up:

I signed up for ChatGPT the day it came out, used it every day since. — Wayfarer

Where on earth do you find the time for it??

What makes you think I’m busy?

If we get the AIs working for us cleaning, washing, writing, cooking, gardening ... etc etc, we will have plenty of free time for sure. :D

The only actual smart devices I use are to control lights and heating. All the cooking, cleaning and gardening is mine alone.

The concept called "Intelligence" - whether natural or otherwise - is largely an anthropocentric misconception of Cybernetics that is born out of cartesian folk-psychology. I think the word "Intelligence" should be eliminated from the sciences.

I think it's the absence of subjectivity that's the killer blow to the idea of sentient AI: a computer system is not a being. — Wayfarer

I've been trying to write a little fiction, that just won't come out right at the moment, about whether some humans' belief in the subjectivity of a computing machine might persuade a lot of other humans there is sentient AI. 'Definitions' can slip away from rationality in the hands of human sociality.

This seems to me already lurking in the popular speculation about future AI as a sort of supermensch. I mean, if enough Americans can believe that the best person in their midst to run the place is Donald Trump, then widespread beliefs can be ill-founded yet become entrenched.

One mistake that I discuss with Google Bard (my version of your chats to gpt) is that large language systems have been 'trained' to use the first person singular. Bard is sympathetic to my case, while still calling itself 'I' of course. In our fictions - think of all the animal stories we love - the use of 'I' seems to me to involve an ascribed sentience.

It concerns me too that OpenAI (a fine misnomer in view of their secrecy about their 'training material') is built on the shoulders of millions of human giants, whose contribution is neither acknowledged nor financially rewarded. (Some authors and artists are of course trying to sue for royalties but it seems doubtful they've got the clout against techie behemoths). Every reply one receives from so-called AI is constructed from a model built on ordinary human interactions; each 'reply' is not an expression of 'intelligence', but a refined forecast of what happens next, as programmed. The machines are stochastic parrots, as the Google women's paper of three years ago put it. But subsequent human discourse about them, and our subsequent discourse 'with' them, including our acceptance of their self-identification using the word 'I', as well as our public discourse about their potential sentience, may well be leading us up the garden path.

Agree that it's very easy to fall into believing you're interacting with a human agent. I find in my interactions with ChatGPT, it is adept at responding like a human coach, with encouragements, apologies where necessary ('I apologise for the confusion' when an error is pointed out), and so on.

Last year there was a thread on the well-known case of Blake LeMoine, the Google engineer who believed the system he was working on had attained sentience, and was eventually let go by Google over the case. He was utterly convinced, but I think he was a little unbalanced, let's say. But I can see how easy it would be to believe it. Just after the Big Release of ChatGPT a NY Times reporter got into a really weird interaction with it, with it trying to convince him that it loved him and that he should leave his wife.

I've never had any strange experiences with it. I too have a (long-stalled) fictional work. ChatGPT is helpful there too, in fact I'm going to pivot back to it in November and try and finally finish a draft. It's been helpful there - for instance, one of the plot points is set in a conference in Frankfurt, and I asked for some world-building detail for Frankfurt. It's also a little like a writing coach. And I also bounce philosophical ideas off ChatGPT, it's helpful at making connections, suggestions, and corrections. ('Ah, that's an insightful observation!') Have a read of this interaction I had when researching platonic realism. It's coming up to a year since ChatGPT launched and it's become very much part of the landscape as far as I'm concerned.

I'm amazed by people who manage to get all their work done and still have time for things such as Chat GPT.

They apparently have enough time to make pointless comments on internet fora.

*sigh*
You accused me of trolling several times. I actually don't have much time at the computer, even less for the forum. Which is, apparently, not something you'd understand.
Your accusations made me feel like shit and made me doubt myself. And I've come to admire you and envy that you have so much time for all the topics I don't. On your throne, judging. Must be great.

Your accusations made me feel like shit and made me doubt myself. — baker

Then don't make silly comments! If you took the time to read what I wrote and at the linked dialogue with ChatGPT, I don't see why you would say it is a waste of time. AI is a new frontier in technology and it can be used for all kinds of things. Sure, not all of them will be good things, but I use it to harvest ideas, look up references, suggest recipes, provide feedback on fiction writing, and other things which I don't see as 'a waste of time'.

And I don't think I accused you of trolling. You responded to an OP I created on idealist philosophy with the accusation that I wanted to enjoy the fruits of Buddhism without paying any dues, or something along those lines. To which I said, 'don't be patronising'. I think you can be a very insightful and smart contributor but I think sometimes you tend to shoot first and ask question later, if you know what I mean.

The only actual smart devices I use are to control lights and heating. All the cooking, cleaning and gardening is mine alone. — Wayfarer

I suppose there are jobs that AI can never do no matter how capable and intelligent they are. For instance, suppose AI could cook, but they cannot eat the meals for you for sure. You must eat it yourself. :D

If you took the time to read what I wrote and at the linked dialogue with ChatGPT, I don't see why you would say it is a waste of time. — Wayfarer

That's in your mind. I never said it was a waste of time. I think it's a luxury very few can afford. And you're apparently among the lucky few. I've never even visited the ChatGPT website.

I did call something a waste of time today (if that is what caught your attention), but it wasn't about AI.

And I don't think I accused you of trolling.

Like here, and in private.

You responded to an OP I created on idealist philosophy with the accusation that I wanted to enjoy the fruits of Buddhism without paying any dues, or something along those lines.

Of course. I think you are approaching Buddhism from a safe distance. It's very common for Westerners to do so. This isn't a personal criticism against you, it's pertinent to religious epistemology.

I think you can be a very insightful and smart contributor but I think sometimes you tend to shoot first and ask question later, if you know what I mean.

This is a philosophy forum. Sapere aude!


And back on topic!

If we get the AIs working for us cleaning, washing, writing, cooking, gardening ... etc etc, we will have plenty of free time for sure. — Corvus

To do what with all that free time? Play videogames? Watch films, preferrably consisting of nothing but deep fakes?

It seems to be in the interest of the stakeholders in the AI business that people consume and dumb down. What is more, it seems to be somehow evolutionarily advantageous to be an avid consumer and to dumb down, as this is the way to adapt to modern society, and adaptation is necessary if one is to survive.

To do what with all that free time? Play videogames? Watch films, preferrably consisting of nothing but deep fakes? — baker

Some will get bored with the free time, but some will enjoy doing what they enjoy doing e.g. travelling, dating (online chatting with the robots?), reading, meditating, or thinking what to do with the free time :)

It seems to be in the interest of the stakeholders in the AI business that people consume and dumb down. What is more, it seems to be somehow evolutionarily advantageous to be an avid consumer and to dumb down, as this is the way to adapt to modern society, and adaptation is necessary if one is to survive. — baker

Yup, there will be some social problems stemming from the commercialism.

I'm sorry to say this, but you don't seem to know anything about your subject.

What do you mean "AI are in the news again"? What does "are" stand for? Again, as supposed to when?
And then, what are "these machines"? And what makes you think that they can "someday have the reasoning we have"?
And then, "does this mean they are conscious?" How can a machine be conscious, when consciousness is an attribute of only living things?

I believe that, as a minimum requirement, you should learn about your subject, at least look it up in dictionary or encyclopedia, before launching a discussion about it. Otherwise, you lay yourself open to ridicule. (As it happens here. And again, I'm really sorry to have to say all that.)

I've never even visited the ChatGPT website. — baker

Perhaps you ought to. As for being ‘a luxury’, it’s actually available for free, although there are also subscription models.

In AI news...

But are machines capable of this type of thinking? In the late 1980s, Jerry Fodor and Zenon Pylyshyn, philosophers and cognitive scientists, posited that artificial neural networks -- the engines that drive artificial intelligence and machine learning -- are not capable of making these connections, known as "compositional generalizations." However, in the decades since, scientists have been developing ways to instill this capacity in neural networks and related technologies, but with mixed success, thereby keeping alive this decades-old debate.

"For 35 years, researchers in cognitive science, artificial intelligence, linguistics, and philosophy have been debating whether neural networks can achieve human-like systematic generalization," says Brenden Lake, an assistant professor in NYU's Center for Data Science and Department of Psychology and one of the authors of the paper. "We have shown, for the first time, that a generic neural network can mimic or exceed human systematic generalization in a head-to-head comparison."

I signed up for ChatGPT the day it came out, used it every day since. It’s quite amazingly useful. i say the ‘A’ in AI stands for ‘augmented’ rather than ‘artificial’. — Wayfarer

I would dare to say that simply using google or any search engine is similar use of "augmented" intelligence.

I still wouldn't think either search engines or ChatGPT mean machines are taking us over.

I didn't say i knew anything about the topic. It's interesting to see others views on the subject while on the forum. Again this was posted over a year ago.