AI megathread

I'm far more amenable to the idea that a spirit - as per Richard Gossinger - is drawn to the complexity of certain corporeal forms than I am to the idea that Turing Machines manifest thinking if the right program is run. [The former may be implausible to the skeptical mind but the latter to me seems far more bizarre.]

On the former... that does raise some interesting thoughts for me ~ perhaps it's not just the form, but the environment those forms tend to create, the behaviours, the interactions, that also interest it. Without prior of experience having embodied a particular form, it might be more of a curiosity, to see what the spirit can learn from it, if anything. With more experience, the spirit might then start to develop ideas about what it wants to achieve in the long-run, to experience, to learn.

A Turing Machine offers no such flexibility ~ on top of that, there is no astral archetype for the spirit to tune into, to express through, by which it can embody the fetus or plant-seed or whatever of that form. (Yeah, I've been wondering about plant-incarnation now, as well...)

On the former... that does raise some interesting thoughts for me ~ perhaps it's not just the form, but the environment those forms tend to create, the behaviours, the interactions, that also interest it. Without prior of experience having embodied a particular form, it might be more of a curiosity, to see what the spirit can learn from it, if anything. With more experience, the spirit might then start to develop ideas about what it wants to achieve in the long-run, to experience, to learn.

A Turing Machine offers no such flexibility ~ on top of that, there is no astral archetype for the spirit to tune into, to express through, by which it can embody the fetus or plant-seed or whatever of that form. (Yeah, I've been wondering about plant-incarnation now, as well...)

Yeah I'm highly doubtful but I do want to remain open minded. I do feel logically it just raises a lot of questions, for example if a program is consciousness are you creating a new consciousness every time you run it?

What if a thread switches out from running the program to run another, then switches back?

edit: In the intro to Then I am Myself the World, neuroscientist Christoff Koch says in his new book: "Intelligence is computable, Consciousness is Not"

Yeah I'm highly doubtful but I do want to remain open minded. I do feel logically it just raises a lot of questions, for example if a program is consciousness are you creating a new consciousness every time you run it?

What if a thread switches out from running the program to run another, then switches back?

If we presume for the sake of the argument that this is happening literally, then you'd be indeed creating consciousness every time you run the program. When a thread switches, you'd be putting that consciousness into suspended animation as the CPU puts it on hold momentarily.

Bring a whole new meaning to the memes around killing and aborting parent processes and their child processes or threads!

This article explains how AI is being used to teach civil discourse. Teaching and grading students requires observing each student engaging in civil discourse and providing feedback. It takes a lot more time and effort from instructors than other subjects do. This makes it hard for a university to provide instruction for every student and using many teachers might not provide uniform treatment of the subject. Using AI to teach the subject solves all of these problems.

https://www.jamesgmartin.center/2025/02/...discourse/

Yeah I'm highly doubtful but I do want to remain open minded. I do feel logically it just raises a lot of questions, for example if a program is consciousness are you creating a new consciousness every time you run it?

What if a thread switches out from running the program to run another, then switches back?

edit: In the intro to Then I am Myself the World, neuroscientist Christoff Koch says in his new book: "Intelligence is computable, Consciousness is Not"

I would just amend that to "some aspects of intelligence are computable, consciousness is not".

The meaning of the word "intelligence" is the ability to learn, understand and know. Almost the entire useage of the term "intelligence" inherently assumes that a human consciousness is accomplishing these various aspects of consciousness. Knowing, understanding and learning inherently imply a conscious self-aware knower and understander and learner. 

But generative AI systems (that we have strong reasons to believe have absolutely no conscious awareness) seem to be able to exhibit a much limited version of "intelligence", where only certain aspects of knowing, understanding and learning are manifested.  Although a generative AI computer system can only compute, and therefore can't exhibit consciousness, it can manifest certain limited aspects of intelligence.

For instance, AI "understanding" appears to be limited to data pattern recognition or analysis, and can be achieved without consciousness.

AI systems can manifest a very limited form of "learning" consisting of for instance saving in computer memory the pattern of actions that best worked to achieve a goal. Such a limited form of "learning" doesn't require consciousness.

The same principle applies to "knowing", where the AI system can acheive a very limited version of this aspect of intelligence through simply being able to store information in memory.  Also, one definition of "knowing" something is really "understanding" that it is a fact.  For this reason also, AI systems can manifest a very limited form of "knowing" that does not require consciousness.

This limited form of intelligence is evidently good enough to seem to be able to give conscious responses to questions. 

I find a lot of the recent discussion here quite strange. It would not be merely pedantic to point out that the topic of the thread is AI. AI is an abbreviation of artificial intelligence. Would it be a good idea to have a separate thread to discuss the speculation around AC. AC here not meaning alternating current but artificial consciousness. Every time I read a mention of consciousness in this thread I ask myself WHY, why are folks talking about consciousness here? It doesn't make any sense to me.

We know there are switches which turn a current or voltage on or off. When such an on/off switch is controlled by a current or voltage it can be used as a building block to form a logic circuit. All the technology relating to AI is based around these simple building blocks, is it not? So why is suddenly a light switch deemed to have consciousness? I find it bizarre.

I find a lot of the recent discussion here quite strange. It would not be merely pedantic to point out that the topic of the thread is AI. AI is an abbreviation of artificial intelligence. Would it be a good idea to have a separate thread to discuss the speculation around AC. AC here not meaning alternating current but artificial consciousness. Every time I read a mention of consciousness in this thread I ask myself WHY, why are folks talking about consciousness here? It doesn't make any sense to me.

We know there are switches which turn a current or voltage on or off. When such an on/off switch is controlled by a current or voltage it can be used as a building block to form a logic circuit. All the technology relating to AI is based around these simple building blocks, is it not? So why is suddenly a light switch deemed to have consciousness? I find it bizarre.

I also find it bizarre. Your argument against consciousness being possible in a computer system which can do absolutely nothing but at base execute individual logic instructions to compute algorithms, is valid and I alluded to it. I just pointed out that short of being able to be conscious, AI computer systems understandably at least can manifest certain limited aspects of intelligence, not consciousness. There is a big difference. Anyway, this limited level or form of intelligence is evidently enough for these AI systems to give at least the impression of being conscious (in their intelligent responses to questions).

As a test, I just asked a generative AI system the following question.

Will a generative AI system answer the following question: can you manifest certain limited aspects of human intelligence, but not manifest consciousness?

The AI's answer:

"Yes, according to current understanding, a generative AI system can indeed exhibit certain limited aspects of human intelligence, like generating creative text, translating languages, or answering complex questions, while still not manifesting consciousness; this is because current AI models primarily operate on pattern recognition and data manipulation, lacking the fundamental neurological and cognitive processes associated with consciousness.

Key points to consider:

Definition of consciousness:

The nature of consciousness is still a philosophical debate, but generally, it refers to subjective experience, self-awareness, and the ability to feel emotions, which are not currently replicated in AI systems.

Capabilities of generative AI:

While generative AI can produce impressive outputs, it does so based on the data it was trained on, effectively mimicking human-like responses without truly understanding the meaning behind them.

Limitations of AI:

Current AI systems lack the ability to engage in complex reasoning, adapt to novel situations beyond their training data, or have genuine subjective experiences, which are considered crucial aspects of consciousness.

As can be seen, this seems to confirm my assessment. It's interesting that this AI is "willing" to be so objective and careful in its response even though this response reveals many of its limitations. This means it has no ego, something expected of something that is not conscious.

I find a lot of the recent discussion here quite strange. It would not be merely pedantic to point out that the topic of the thread is AI. AI is an abbreviation of artificial intelligence. Would it be a good idea to have a separate thread to discuss the speculation around AC. AC here not meaning alternating current but artificial consciousness. Every time I read a mention of consciousness in this thread I ask myself WHY, why are folks talking about consciousness here? It doesn't make any sense to me.

We know there are switches which turn a current or voltage on or off. When such an on/off switch is controlled by a current or voltage it can be used as a building block to form a logic circuit. All the technology relating to AI is based around these simple building blocks, is it not? So why is suddenly a light switch deemed to have consciousness? I find it bizarre.

For myself I wanted to be charitable to the idea that there could be something conscious in AI while being very skeptical.

Basically I don't want to be a dogmatic skeptic the way the Materialist faith has been pseudo-skeptical towards Psi & Survival.

That said the idea is as bizarre [to me] as it is to you.