Comments

  • Exploring the Artificially Intelligent Mind of Claude 3 Opus
    Keep in mind that a chat bot is supposed to look like a human conversing, that’s it’s programming….Metaphyzik

    I don't get the impression that you grasp the extent to which the behavior of modern chatbots is a matter of what the system has *learned* how to do, rather than a matter of what the system has been *programmed* to do. To a substantial degree the system has been programmed to behave like a neural network. It is the learning that comes from the artificial neural network being *trained* that results in the impressive capabilities of modern chatbots.
  • Exploring the Artificially Intelligent Mind of Claude 3 Opus
    How's that, then? Can you set it out?Banno

    I don't have much confidence in my ability to get my perspective on this across, and mostly just hope people will intuitively grok it, but I'll try.

    I see the state of the output neurons of the trained neural net in the video as being about the state of the input, but only in the limited sense of that network abstracting an 'indication of numerality and which numeral' from the visual field presented as input. The outputs of that neural net are not about recognizing faces, for example. Of course another neural network operating in parallel can have outputs that are about recognized faces. At a yet 'higher' level we could have a neural network that takes as inputs the outputs of both numeral and face recognizer subnets.

    I'd suggest that with awareness of the way neural nets are apt to 'snap to' an output state, some insight into the phenomenology of a Necker cube or a duck-rabbit snapping from one recognized object to another can be had. E.g. the output of a neural net at some level, snaps from being about a recognition of a duck to being about a recognition of a rabbit.

    Thoughts?
  • Exploring the Artificially Intelligent Mind of Claude 3 Opus
    Just not sure how that helps to consider a program as intelligent.Metaphyzik

    An important topic in philosophy of mind is "intentionality". From the Stanford Encyclopedia:

    In philosophy, intentionality is the power of minds and mental states to be about, to represent, or to stand for, things, properties and states of affairs. To say of an individual’s mental states that they have intentionality is to say that they are mental representations or that they have contents. Furthermore, to the extent that a speaker utters words from some natural language or draws pictures or symbols from a formal language for the purpose of conveying to others the contents of her mental states, these artifacts used by a speaker too have contents or intentionality. ‘Intentionality’ is a philosopher’s word: ever since the idea, if not the word itself, was introduced into philosophy by Franz Brentano in the last quarter of the nineteenth century, it has been used to refer to the puzzles of representation, all of which lie at the interface between the philosophy of mind and the philosophy of language...

    To me the video conveys a sense in which a relatively small trained neural network (whether composed of actual neurons, or simulated neurons) can, with training, develop outputs that are *about* the input.
  • Exploring the Artificially Intelligent Mind of Claude 3 Opus
    Give me an example of how an abstract feature of training data can lead to reasoning? This is more in the line of mysticism isn’t it?Metaphyzik

    This YouTube video on the rudiments of how neural networks work might provide some insight.
  • What can I know with 100% certainty?
    I think the "problem" with Descarte's thought experiment is the "I".ENOAH

    Just adding to the "Same." chorus. :up:
  • Counter Argument for The Combination Problem for Panpsychism


    BTW amber, welcome to the forum. You've brought up topics I'm quite interested in. (One might say autistically obsessed with. :wink:)
  • Counter Argument for The Combination Problem for Panpsychism
    Without an explanation (whether panpsychism or something else), the question of how matter becomes conscious is "it just does." Which is magic without an attempt at an explanation.Patterner

    Just based on a mainstream scientific picture, (for example the perspective presented by Sean Carroll in The Big Picture without any added panpsychism sauce) there is reason to expect a comprehensive explanation of the nature of consciousness to be beyond the cognitive grasp of humans (at least without a lot of help from AI).

    There is no good reason to look at it in a black or white way though. It's not a matter of "it just does". There are a lot of parts of the physical underpinnings of consciousness that can be understood if one spends time developing a broadly informed perspective on scientific findings relevant to the subject.
  • Counter Argument for the Evolution problem for Epiphenomenalism
    Amen. And I have apnea. Even with the CPAP, it's almost impossible for me to read. Even excellent, exciting novels are almost always beyond my ability. But I commute more than a half hour each way, and often more than an hour, and audible is great for me.

    Tse is not available on audible. I try to read it as I can.
    Patterner

    Sorry to hear about the apnea, but glad to hear Audible works for you. I've tried Audible, but didn't like it. Luckily for me, I have a short trip to work.
  • Counter Argument for the Evolution problem for Epiphenomenalism
    Lars Chittka is mentioned in the article. He has a great book called The Mind of a Bee.Patterner

    Good to know. If my stack of unread books weren't so high...
  • Counter Argument for the Evolution problem for Epiphenomenalism
    A Claude 3 response to my argument:

    Reveal
    I appreciate you providing this additional context and framing around the bumblebee study in relation to questions about the nature of consciousness. You raise some thought-provoking points that I'll do my best to respond to:

    1. I agree it's wise to avoid getting overly mired in simplistic philosophical notions like epiphenomenalism when considering the hard problem of consciousness. The relationship between physical processes and consciousness is deeply complex.

    2. Your sketch of an argument highlighting the potential role of consciousness in facilitating language-based learning and cultural transmission in humans is compelling:
    - Language clearly plays a pivotal role in human learning and knowledge accumulation.
    - Our conscious states seem tightly linked to our linguistic outputs that others learn from.
    - This suggests consciousness may act as an important "filter" or causal factor shaping the informational value of our communications.
    - This capacity for conscious linguistic interaction enabling social learning appears quite unique compared to non-human species.

    3. Bringing it back to the bumblebee study - the findings suggest a rudimentary ability for cultural transmission of knowledge that was previously thought exclusive to humans.

    4. However, as you note, the human capacity for conscious linguistic interaction and systematically building a vast body of sharable knowledge through that process appears considerably more sophisticated than what we've observed in bumblebees so far.

    5. Viewing consciousness as playing some causal role in our cognitive capabilities, including social learning and teaching, need not necessarily contradict causal closure under physics - perhaps consciousness arises from physical processes in ways we don't yet fully understand.

    Overall, I concur that the evidence points towards consciousness having an important functional role in enabling the uniquely human skills of symbolic thought, language mastery, and accumulation of culturally transmissible knowledge - even if we haven't yet untangled the metaphysical nature of consciousness itself. Continuing to study the extent of similar capacities across species provides an interesting comparative lens. You've given me much to ponder on this fascinating issue spanning neuroscience, cognition, and philosophy of mind. Well argued!


    Claude 3's response to "What suggestions can you make towards a criticism of the argument I presented on the philosophy forum, from within a naturalistic metaphysics."

    Reveal
    Here are some potential criticisms or counterpoints one could raise to the argument you presented on the philosophy forum, while still operating within a naturalistic metaphysical framework:

    1. Correlation does not imply causation. While there is a clear correlation between conscious states and productive linguistic output enabling social learning, one could argue this does not definitively prove consciousness plays a direct causal role. The relationship could be more indirect or emergent from underlying neurological processes.

    2. The hard problem of consciousness remains unresolved. Even if consciousness facilitates certain cognitive functions like language, we still lack a complete theory for how and why subjective experience arises from physical processes. A criticism could be made that handwaving to consciousness' causal powers is premature without a fuller explanatory model.

    3. Other faculties may be more directly causal. Some could argue that other cognitive capabilities like working memory, executive function, theory of mind etc. are more direct drivers of the linguistic skills enabling cultural transmission, rather than consciousness per se playing a specialized role.

    4. Anthropic bias. The unique human strengths in this domain could potentially bias our perspective on the true role and extent of consciousness required for these capacities across other species. We may be overestimating its importance.

    5. Ambiguity of consciousness. Definitions of what constitutes a conscious state can be quite varied. Critics could argue the argument rests on an imprecise or ungrounded notion of consciousness itself.

    6. Other species may have unappreciated capacities. As the bumblebee study hints, other species may have more rudimentary versions of cultural transmission enabled by precursor cognitive capabilities not necessarily requiring human-like consciousness.

    Overall, while your argument outlines an intuitive perspective, potential counterpoints could challenge the empirical certainty of consciousness' causal role, the feasibility of locating subjective experience in a naturalistic framework, or anthropocentric assumptions about the relationship between consciousness and social learning capabilities. Addressing these concerns could strengthen or refine the argument further. But you've raised fascinating issues at the intersection of cognitive science and naturalistic metaphysics.
  • Counter Argument for the Evolution problem for Epiphenomenalism
    Please let me know what you think!amber

    My recommendation is that if you want to seriously consider the nature of consciousness, it's a good idea to avoid getting to caught up in simplistic philosophical notions like epiphenomenalism. (Not to say there isn't value in considering how epiphenomenalism can be avoided given a naturalistic view (e.g. causal closure under physics).

    One thing to consider is the role consciousness plays in language based learning. Here is a sketch of an argument, though I'm not going to be at all rigorous. (So maybe more accurately stated, a set of dots that you might intuitively see connections between.)

    (1) It seems obvious that language plays a big role in our learning.

    (2) The amount that can be learned from someone is highly correlated with the conscious state of that person. People talking while asleep, or under the influence of powerful opiates, don't tend to produce nearly as much language that can be learned from, as those who are in a normal conscious state.

    (3) It seems reasonable to think of consciousness as, at the very least, an important 'filter' on the language we social primates emit.

    (4) I think we have good reason, based on our interactions with each other via language, to see our consciousness as playing a causal role in our ability to learn from, and inform/teach each other.

    (5) I don't see any of the above as being contradictory to causal closure under physics.

    As some added food for thought, here's a blurb on a recent article on the ability of bumblebees to engage in social learning: It seems to me, that the evidentiary case for consciousness playing an important causal role in the human capacity for social learning, is quite strong.

    What do you think?
  • Graham Oppy's Argument From Parsimony For Naturalism
    ...but just read this back to yourself. You're a troll, and what you're doing here is trolling, and we know you're a troll, and we know that there is no good reason to throw pearls before trolls. ...but apparently to your mind the religious are simply afraid of subjecting their personal inferences to your superior rational skills, lol.Leontiskos

    Yeah, hostile reactions like that are pretty typical.
  • Graham Oppy's Argument From Parsimony For Naturalism
    A third-person example has already been provided: link. Feel free to address it.Leontiskos

    I'm afraid your third person example is hear say.

    (I won't "make it personal," no. That is a terrible approach in general, especially when it comes to contentious religious debates.)Leontiskos

    The thing is, I used to be a believer and believed I had experiences of God. What I considered at that time to be good reasons for such beliefs didn't stand up to scrutiny. Furthermore, when I've asked people who claim to have had experiences of God, to explain what they interpreted as experiences of God, they tend to respond as you have.

    I can relate to being uncomfortable sharing that sort of thing, because even when I believed I had had experiences of God, I knew in the back of my mind that I really couldn't justify those beliefs in the face of critical thinking being applied to them.

    So I'll leave it to the back of your mind, to let you know whether your reasons for believing that you have had experiences of God really stand up to scrutiny.
  • Graham Oppy's Argument From Parsimony For Naturalism
    - Someone who has interacted with God on a number of occasions is similarly situated to the child.Leontiskos

    1. Do you believe yourself to be somone who has interacted with God on a number of occasions?

    2. If so, are you willing to talk about how you came to that conclusion?
  • Graham Oppy's Argument From Parsimony For Naturalism
    The Gideon example is also interesting because in general it's not considered to be a good sign of his character that he "puts the Lord to the test."Count Timothy von Icarus

    Declaring it a sign of poor character, to engage in critical thinking when it comes to one's religion, seems like it could be a psychologically effective way of keeping people from questioning the religious beliefs they inherited.

    Is there a reason to think otherwise in the case of Abrahamic religions?
  • What can I know with 100% certainty?
    You shouldn't be saying it, you shouldn't even be saying it if you were right. It's so disgustingly self righteous and haughty.flannel jesus

    People aren't narcissistic as a matter of free willed choice. So despite how natural it seems to do so, it doesn't really make sense to blame people for being narcissistic.
  • What is 'Mind' and to What Extent is this a Question of Psychology or Philosophy?
    I am certain that if our senses pointed inwards our so-called inner lives would be less of a mystery. In there is a multiplicity of parts and movements we just aren’t privy to in the present arraignment.NOS4A2

    What form do you imagine such internal sensors taking? After all, if we had an internal eye and light source to look at our brain as a whole, I wouldn't expect it to provide much interesting information.

    In a very meaningful sense we do have senses pointing inward, in that we have neurons in our brains which monitor and report on the goings on in other parts of our brains. I suppose a case might be made for it potentially being beneficial to have such internal monitoring to a greater degree, but natural selection tends to weed out features like heads too big to pass through a mother's birth canal.
  • Exploring the Artificially Intelligent Mind of Claude 3 Opus


    Thanks for taking the time to present all of this.
  • Exploring the Artificially Intelligent Mind of Claude 3 Opus
    ASSISTANT: (Opus, Third answer, temperature still set to 0.3)Pierre-Normand

    Did you mean Sonnet rather than Opus there?

    [quoting Opus(?), Second answer, temperature set to 0.3]
    On the core topic of direct and indirect realism, I am struck by the way our conversation has highlighted the richness and complexity of perceptual experience. While the dichotomy between direct and indirect realism can serve as a useful starting point, it seems clear that a truly comprehensive account must go beyond such simple categorizations.

    As Haiku eloquently expressed, perception is an embodied, dynamic process of organism-environment coupling. It is not merely a passive reception of sensory inputs, but an active engagement with the world and its affordances. This holistic perspective resonates with the phenomenological tradition, which sought to describe the lived experience of perception in all its nuanced depths.

    At the same time, Opus's rigorous analysis reminds us of the importance of precision and logical clarity. The physiological and causal underpinnings of perception cannot be ignored, even as we acknowledge the directness of the perceptual act itself. A truly satisfying account must find a way to integrate these different levels of analysis without falling into reductionism or oversimplification.

    Perhaps what is needed is a kind of "transcendental empiricism" – a philosophical framework that can do justice to both the first-person, phenomenological dimensions of perception and the third-person, scientific insights into its underlying mechanisms. Such an approach might draw inspiration from thinkers like Merleau-Ponty and Wilfrid Sellars, who sought to bridge the gap between the manifest and scientific images of the world.
    Pierre-Normand

    It's pretty freaky to see a machine articulate, what for me was a rather inchoate swirl of thoughts. I forsee a lot of potential for such systems as 'articulatory prostheses' for aphasic and autistic people.
  • What can I know with 100% certainty?
    Thinking is a private mental event. It has nothing to do with being in any shape or form.Corvus

    Aside from forms like inebriated, feverish, anesthetized...
  • Indirect Realism and Direct Realism
    Indeed! Although your detractors may rather feel vindicated in their intuition that you are a bot ;-)Pierre-Normand

    That had occurred to me. :wink:
  • Indirect Realism and Direct Realism
    [quoting Claude 3 Haiku]Perhaps the most constructive path forward is to resist the temptation to declare a decisive victory for either direct or indirect realism, and instead focus on developing a more holistic understanding of the human experience of the world - one that acknowledges the complexities and ambiguities inherent in our perceptual faculties.Pierre-Normand

    From my perspective, the question of the thread looks like an attempt to address a complex subject (actually a diverse set of subjects) with a false dichotomy.wonderer1

    Great minds... :wink:
  • The Gospels: What May have Actually Happened
    2. Early Christians were willing to die for their belief in the content of the New TestamentBrendan Golledge

    Perhaps that is mostly a matter of folklore.

    https://www.bartehrman.com/how-did-the-apostles-die/
  • Graham Oppy's Argument From Parsimony For Naturalism
    Although we might doubt that we exhaustively know what it is to be human.Janus

    I'd say that's a pretty reasonable doubt. :wink:
  • Graham Oppy's Argument From Parsimony For Naturalism
    I think there are many things all of us take on faith because it seems more beautiful to do so. It makes life seem more human.Janus

    Or to provides a way to avoid facing, what it is to be human.
  • What is 'Mind' and to What Extent is this a Question of Psychology or Philosophy?
    In particular, there is the question as to whether the mind is a 'blank slate', as suggested by John Locke and Stephen Pinker.Jack Cummins

    Pinker's book, The Blank Slate, explicitly argues against the notion of a blank slate.
  • What can I know with 100% certainty?
    If there's anything resembling intellectual integrity in there...flannel jesus

    Still hopeful are you?
  • Classical theism and William Lane Craig's theistic personalism
    Craig's view is incoherent...Walter

    You weren't expecting me to argue against that, were you? :wink:
  • What can I know with 100% certainty?
    Oh, I see - you just wanted to join in the kick fest.Banno

    What I was hoping for, was that Corvus would recognize his lack of insight into logic, and engage in error correction with regard to his thinking. Unfortunately he doubled down on speaking as if he was some sort of expert on the subject, while repeatedly demonstrating that he didn't know what he was talking about.
  • What can I know with 100% certainty?
    Here's a seperate point, made by Corvus, Beverly and myself, and pretty much unaddressed by others: It has not been shown that the Cogito is valid.Banno

    The invalidity of the Cogito hasn't been a factor in my involvement in the discussion. My involvement has been out of curiosity as to whether Corvus could admit to having been a doofus.
  • Graham Oppy's Argument From Parsimony For Naturalism
    Newton's account was non-scientific or non-naturalistic insofar as it disregarded the prevalent canons of scientific reason.Leontiskos

    I'd say it's quite scientific, to recognize new and better ways of understanding things. Casting Newton as non-scientific seems rather bizarre to me.
  • Graham Oppy's Argument From Parsimony For Naturalism
    so can reason itself explained in terms of 'natural laws'?Wayfarer

    It's looking ever more likely to me, that the answer is, "Yes."
  • Did you know that people who are born blind do not get schizophrenia?
    Interestingly, there are a preponderance of congenitally blind people with autism.Joshs

    Interesting (and discussed somewhat in the Psychology Today article FJ linked).

    Although I seem to have fairly normal vision when it comes to static images, I definitely have a deficit when it comes to detecting the details in dynamic visual events. (Some relevant research.)

    So it's perhaps reasonable to think of people on the autism spectrum as being somewhat blind, in the sense of having lower visual processing bandwidth than neurotypicals.
  • Exploring the Artificially Intelligent Mind of Claude 3 Opus
    In this way, a virtual form of high-level, reflective cognition gets bootstrapped from the basic, dumb mechanism of pattern recognition. The model doesn't just represent objective facts about the world, but also incorporates a model of itself as a rational subject navigating the space of reasons. It builds an implicit capacity for self-critique and error correction into its own functioning.Claude

    I didn't read much of the last two dialogs, but jumped to the end and saw that. Impressive.
  • What can I know with 100% certainty?
    I do not blame you at all. I would have bowed out much sooner! You lasted for pages without agreement from anyone but didn't give in. I am really impressed!Beverley

    Are you equally impressed with flat-earthers who persist in arguing for a flat earth?
  • What can I know with 100% certainty?
    All, can you see that the Cogito does not provide the certainty you crave?Banno

    I can see that's a loaded question. :wink: