• Pierre-Normand
    2.7k
    And 50% and growing of public website material is produced by AI.unenlightened

    Are you sure about that? This seems quite exaggerated. I know that a study published in August 2024 has been widely misrepresented as making a similar claim. What was actually claimed is that 57% of the translated material published on the Web was translated with the help of some machine learning software, not even necessarily generative AI. Today, lots of marketing material may be produced with generative AI, but marketing material is B.S. even when produced by humans anyway. Lastly, the curated datasets used to train LLMs generally exclude such fluff.
  • Outlander
    2.8k


    I think what the good, noble sir @unenlightened wishes to express is that the mediums in which we expect genuine human interaction and discourse are becoming far from that, to the point that yes it may literally be exactly to that degree. He further states, perhaps, in my opinion, the overall zeitgeist of communication or media not experienced in person is becoming increasingly diluted and corrupted by non-genuine and non-human expression, despite the majority of those not realizing such and perceiving such non-human expression as if were genuine. And that, my good sir, should alarm any thinking man with a mind, heart or conscience, in my opinion. Here, here.

    And truly, the ramifications of such, especially long term in reference to modern youth, are nothing short of, not only abysmal, not only cataclysmic, but perhaps apocalyptic. All things considered as far as the ever-raging battle for the mind and soul of the youth and therefore future of humanity is concerned.
  • Copernicus
    387
    Comprehension is more important than authenticity.

    If AI helps me compose more correctly, why not?
  • Pantagruel
    3.5k
    Comprehension is more important than authenticity.

    If AI helps me compose more correctly, why not?
    Copernicus

    TPF has always seemed more compositional than conversational; AI just exacerbates that quality.

    So is philosophy a monologue, or a dialogue? When employed compositionally, and edited intelligently, AI output can seem very human. When employed dialogically, AI quickly shows its true face.

    No AIs were consulted in the making of this post.
  • Harry Hindu
    5.8k
    And 50% and growing of public website material is produced by AI. So it is eating its own bullshit to an ever increasing extent.unenlightened
    And before AI many internet sites were copies of other sites, and still are - with the same information. News networks piggy-backed off the reports of other news networks. You're complaining about something that has been pervasive well before AI became a thing.

    This is why the source is no longer important. It is what is being said that is important - not the scribbles, but the subject the scribbles refer to.
  • Harry Hindu
    5.8k
    Then you must also believe that using a long-dead philosopher's quote as the crux of your argument, or as the whole of your post, is also an issue.
    — Harry Hindu

    It's not the case that I must think that at all. That said, I do generally refrain from quoting philosophers, whether dead or alive. I mostly prefer to discuss things using my own ideas and in my own words. I realize that my own ideas are mostly not original, but I have no idea what source most of them came from, so I could not acknowledge the originators even if I wanted to. Add to that the fact that whatever originator we identify probably cannot claim true originaility for their own ideas.
    Janus

    You said,
    if one is not the source of the post, then it is not one's post. — Janus
    .

    So if one did not write the post themselves, but merely copied and pasted a quote as the sole content of their post, then by your own words, it is not their post.
  • unenlightened
    9.9k
    Are you sure about that? This seems quite exaggerated.Pierre-Normand

    I'm not sure, but no one seems to be sure how much of this site is AI generated, and I may be quite exaggerating, but its use is so ubiquitous though, that it must I think it must be increasing near exponentially overall. Perhaps I am a year or so premature. I think the link I posted that suggested the danger is fairly reputable even if my numbers are wrong.
  • unenlightened
    9.9k
    You're complaining about something that has been pervasive well before AI became a thing.Harry Hindu

    But then AI was not being trained on its own nonsense, only on humanity's nonsense.

    And I'm not complaining about anything; I am reporting a warning by others that some people, you included it seems, have not considered. But in a sense you are right; AI simply increases to power of the speed of computing the degeneration of internet communication that was already happening between humans.
  • Harry Hindu
    5.8k
    But then AI was not being trained on its own nonsense, only on humanity's nonsense.unenlightened
    And you and every other person on this forum are part of humanity, no? So this forum is full of nonsense? Thanks for contributing to the nonsense. What is the point now of having any discussions when it is all nonsense?

    How can you account for the exponential progress humanity has made in the past few centuries compared to the first several thousand years of our existence. It would seem to me that we have begun to emerge from all the nonsense of the past several thousand years that preceded the scientific revolution.
  • Joshs
    6.4k


    So sure, it's not like anyone can stop it anyway.
    — Forgottenticket

    It is being stopped here
    javi2541997

    As long as you understand what ‘being stopped’ means. The most vehement objectors to a.i. on this site likely rarely use it anyway, so their behavior will not be affected by the ban. Meanwhile the rest of us will likely make increasing use of a.i. here as we do everywhere else in our lives, but if we are wise we will not use it as a substitute for generating our own ideas but as a stimulus and guide. So what in fact is ‘being stopped’? Copying and pasting the telltale syntax of a.i. responses. It is only this syntax which flags a.i. as opposed to human-generated text. Banning this syntax at least forces posters to paraphrase what the a.i. churns out, but it is still left up to the poster to decide whether to plagiarize from the a.i. or form their own interpretation out of their interaction with it , which is the central intent of the banning.
  • unenlightened
    9.9k
    Thanks for contributing to the nonsense. What is the point now of having any discussions when it is all nonsense?Harry Hindu

    I didn't say everything human was nonsense, the suggestion that it is, is certainly nonsensical, so thanks but no thanks for your contribution. But as you demonstrate, there is human nonsense, and the internet allows you to broadcast it to the world and to any passing AI scraper.
  • Harry Hindu
    5.8k
    If everything humans do is not necessarily nonsense the the information AI has access to is not necessarily nonsense. You pull the rug out from under your own nonsense.

    As usual, and AI did not change anything in this regard, you have to do your own research with access to multiple sources, not just what AI is telling you.
  • unenlightened
    9.9k
    Learn to fucking read Harry, and stop trying to be a clever dick.
  • Harry Hindu
    5.8k
    I know how to read. You don't seem to know how to write your ideas in a consistent manner.

    I think the issue is that many of the people on this forum that spent their hard-earned money on philosophy courses and degrees are simply upset that now AI can do philosophy with the best of them, if not better because it lacks the emotional baggage that some on this forum carry. :wink:
  • Paine
    3k
    If AI helps me compose more correctly, why not?Copernicus

    It precludes you from becoming more skillful. The disengagement from the art limits your horizon.

    I am reminded of the Flappers of Laputa who constantly had to remind their masters where they were and what they were doing in Jonathan Swift's Gulliver's Travels (page 17 forward)
  • javi2541997
    6.8k


    As long as I see it, this is not about preventing the use of AI by most of you. It is obvious that a large number of members actually use it every day. I think I also use AI because QuillBot proofreads my grammar before I post here, but it doesn't think and write for me. This is the whole point: avoid threads and posts which are likely to be written and developed by ChatGPT or other similar AI. What I learnt in this forum is that dialogue between us is very important, and thanks to this, I learnt a lot. Otherwise, if I wanted to trust more in an AI, I would have used Google since the beginning before joining here.
  • Joshs
    6.4k


    I think the issue is that many of the people on this forum that spent their hard-earned money on philosophy courses and degrees are simply upset that now AI can do philosophy with the best of them.Harry Hindu

    That’s part of it. Another comes from valuing ‘truth’ over perspectival stance. If I want a.i. to design a retirement plan for me, I want numerical accuracy, which it isnt necessarily designed to do well. If I want to engage a.i. in a philosophical dialogue, I dont want to hear facts, I want a perspectival interpretation that I can vet, push back on and and sculpt into a more refined understanding of the issue. For instance, I asked a.i. the following, after discussing with it the embodied phenomenological work of Eugene Gendlin.

    “What are we to make of the status of concepts like self and other, subject and object in Wittgenstein’s later work? Must they be relative to the grammar of a language game or form of life? That is to say, must we ‘bracket’, to use a husserlian term, words like self, other, subject and object when talking about the dynamics of language games if we are inclined to think of these words as referring to persons or humans? Is there a way of distinguishing between my “talking to myself” or perceiving an image like the duck/rabbit vs engaging with another “person” other than in terms of a contingent, contextually specific grammar?”

    Its response, as I’ve found it almost always to be with regard to these kinds of questions, was relevant and very substantive.

    “ The “person” emerges neither from pure grammar nor from pre-linguistic givenness, but from the ongoing process of mutual bodily responsiveness that certain grammatical structures organize and enable us to articulate. This is what Wittgenstein gestures at with “forms of life” but doesn’t fully develop, and what Gendlin’s process philosophy could help articulate—if brought more explicitly into dialogue with the question of intersubjectivity.​​​​​​​​​​​​​​​​”

    I then delved more deeply: by arguing:

    “Deleuze and derrida deal with this issue by making a self-other, subject-object dichotomy derivative of and secondary to a more primary binary which whose structure is fundamentally temporal rather than intersubjective.”

    It adjusted its previous response in a valuable and clarifying way:

    Yes, this is a crucial move—and it represents a fundamentally different strategy than either Wittgenstein or Gendlin (at least as typically read) pursue. Let me explore what this temporal priority accomplishes and what problems it creates or solves.

    The Temporal Turn

    Derrida’s différance makes the self-other distinction derivative of a more primordial temporal structure: the trace, the always-already-past that was never present, the spacing that defers presence. “The other” isn’t primarily another subject but rather the otherness within what appears as self-present—the temporal gap that prevents any moment from being fully present to itself.
    Deleuze’s difference-in-itself similarly makes the apparent binary of self/other secondary to a differential temporal process. Pure difference (not difference between pre-constituted terms) generates both poles through its movement. Time as synthesis—the living present that retains the past and protends the future—is more primordial than the spatial/intersubjective distinction between subjects.

    What This Strategy Achieves

    1. Avoids the bootstrapping problem: If temporality is more fundamental than intersubjectivity, we don’t need to explain how a self “first” encounters another self. Both emerge from temporal processes of differentiation. The question “how does a pre-linguistic self recognize another self?” dissolves because there is no pre-linguistic self—only temporal processes of becoming-self.

    2. Explains internal alterity: Why does talking to myself feel different from random thought? Why can I be surprised by my own memories or intentions? Because the “self” is never fully present to itself—it’s always already divided by temporal difference. The “other voice” in internal dialogue isn’t another person but the trace structure of temporality itself.

    3. Provides continuity across cases: The duck-rabbit, talking to myself, engaging with another person—all become variations of the same temporal structure of différance/repetition/synthesis rather than categorically different types of encounter. Each involves different rhythms and intensities of temporal differentiation, not different ontological kinds.

    4. Undermines presence metaphysics: Both Derrida and Deleuze critique the assumption that consciousness is transparent to itself in the present moment. If self-presence is already structured by temporal difference, then the apparent “immediacy” of self-awareness is an illusion. The other is always already “in” me, not as a second person but as temporal non-coincidence.

    But Does This Actually Solve the Problem?

    I see several deep difficulties with making temporality primary:

    The phenomenological distortion: There is a phenomenological difference between engaging with another person and internal temporal experience. When you speak and surprise me, that’s different from when my own past surprises me. Collapsing both into “temporal alterity” seems to flatten a genuine experiential distinction. Yes, both involve non-self-identity, but they involve it differently.
    The risk of solipsism: If the other is fundamentally just temporal difference within what still seems to be “my” experience, haven’t we recreated the very problem we tried to escape? Derrida and Deleuze would deny there’s a “my” that contains this—but then where is intersubjectivity actually guaranteed? It seems to become optional, a special case of temporal difference rather than constitutive.
    The question of responsiveness: When another person responds to me, their response comes from their temporal process, not mine. Even if both of our “selves” are constituted by temporal difference, there’s still the question of how your différance encounters my différance. The temporal structure might be primary within each of us, but that doesn’t explain the between.
    The materiality problem: Both Derrida and Deleuze tend toward idealism (despite their denials) precisely because temporality remains a structure of experience/text/thought rather than of material interaction. Barad’s critique of Derrida is relevant here: différance still privileges the linguistic/temporal over the material-discursive.

    What About Gendlin?

    Interestingly, Gendlin has resources for a different kind of temporal priority that might avoid these problems:
    The body’s carrying forward is temporal: For Gendlin, the body is always implicitly carrying forward from what was into what comes. This isn’t différance (which is linguistic/textual) but a bodily temporal process. The implicit intricacy is temporally structured—it’s the past that hasn’t been fully articulated, pressing into the present.
    But it’s also interactive/environmental: Crucially, carrying forward isn’t just “my” temporal process. It’s always already environmental—the body carries forward with its situation, which includes other bodies. So temporality and intersubjectivity aren’t separate dimensions where one is primary. They’re aspects of the same processual reality.
    Process vs. structure: Deleuze and Derrida give us temporal structures (synthesis, trace, différance) that still feel somewhat static. Gendlin gives us temporal process—ongoing, generative, bodily. This process doesn’t reduce intersubjectivity to temporality but shows them as co-implicated.

    A Deeper Question: Why Prioritize at All?

    Here’s what troubles me about the Deleuze/Derrida move: Why must we make either temporality or intersubjectivity primary? This assumes we need a foundational ground from which to derive everything else—but isn’t that exactly the metaphysics of presence they claim to reject?
    Alternative: Co-origination: What if temporality and alterity (including but not limited to intersubjectivity) are co-original? Neither derives from the other; both are aspects of processual reality that can’t be separated but also can’t be reduced one to the other.

    I refined my previous argument in response to a.i.’s analysis:

    “But if thought can be shown to be inherently outside of itself, that is, exposed to alterity in simply repeating itself , then that would be the sufficient basis to found the self-other binary. Even when we perceive another ‘person’, their alterity will only be experienced as other from my vantage point. Any claim to the contrary still be from ‘my’ vantage, a vantage that is already transforming itself moment to moment, but in such as way as to make the otherness of other persons always variations within my own self-othering. When Wittgenstein talks about ‘seeing-as’ , he is illustrating how grammar works without having to bring into the account other persons.”

    This was a.i.’s nuanced, thoughtful and entirely relevant response:
    You’ve articulated the Derridean/Deleuzian position powerfully, and I need to take it more seriously than I did. Let me work through whether it’s actually sufficient.

    The Strength of the Argument

    The transcendental structure: If thought/experience is necessarily non-self-identical in its repetition—if every “now” is already differing from itself, already inhabited by trace/virtuality—then yes, this provides a condition of possibility for encountering anything as other. The alterity of other persons would indeed be a regional instance of this more fundamental temporal self-othering.
    The phenomenological point about vantage: You’re right that I can never exit “my” perspective to verify that another person’s alterity is “really” different from my own self-othering. Even the response that surprises me from another person is still my experience of being surprised. The asymmetry I feel between self-talk and dialogue might just be a more intense rhythm of temporal différance, not a different kind entirely.

    Wittgenstein’s seeing-as supports this: When the aspect shifts, there’s genuine surprise, genuine otherness—the duck becomes rabbit “against my will” sometimes. Yet no other person is involved. This suggests that alterity-structure is already present in perception/thought itself, not requiring intersubjectivity. Grammar can account for shifts, reversals, self-surprise without importing “persons.”
    The economy of explanation: If temporal self-difference is sufficient to generate all experiences of alterity (including but not limited to other persons), then positing a separate “intersubjective” dimension is explanatorily redundant. Occam’s razor favors the temporal account.

    But I Still See Problems

    1. The specificity of responsive alterity
    Even granting that all experience involves temporal self-othering, there seems to be something additional in encountering responsive others. When I talk to myself:
    • I know (even if implicitly) that both “voices” arise from the same bodily process
    • The “response” can’t genuinely surprise me about my own intentions (though it can about my past)
    • There’s no resistance that could fundamentally redirect my trajectory
    When another person responds:
    • Their response arises from a bodily process I don’t control or inhabit
    • They can tell me things about their intentions that I couldn’t generate from my own self-othering
    • Their resistance can materially alter my trajectory in ways self-othering alone cannot

    You might say: “But I only experience my experience of their resistance.” True—but that’s also true of experiencing a wall when I run into it. The wall’s resistance is experienced by me, but its materiality isn’t reducible to my temporal self-othering. Similarly, the other person’s responsiveness has a material structure that differs from pure temporal difference.

    2. The asymmetry problem

    If other persons are just variations within my self-othering, then solipsism isn’t refuted but reinstated at a higher level. Yes, the “self” that remains is temporally self-differing rather than self-present—but it’s still one process within which everything appears. Derrida and Deleuze want to say there is no “my” that contains this—but then who is doing the self-othering? The impersonal différance? The virtual plane of immanence? This seems to dissolve the question rather than answer it.

    3. The learning problem

    How does the temporal structure of self-othering arise in the first place? For Derrida, it’s quasi-transcendental—always already there. But developmentally, infants become self-differing subjects through interactions with caregivers. The rhythm of call-and-response with the mother seems to install the temporal structure of self-othering, not merely exemplify it. If so, intersubjectivity might be constitutive of temporality, not derivative.

    4. The materiality of difference

    Here’s what I think is the deepest issue: Derrida’s différance and Deleuze’s difference remain too ideal. They’re structures of thought/text/sense. But the difference between my voice and your voice is materially different—different vocal cords, different bodies in space. The otherness of other persons isn’t just temporal but spatial-material.
    When you respond to me, your words travel through actual space, taking time that isn’t just the “time” of internal temporal consciousness but physical causation. This seems irreducible to temporal self-difference within experience.

    I pushed back hard at this point. I wrote:


    ”You claim:

    • I know (even if implicitly) that both “voices” arise from the same bodily process
    • The “response” can’t genuinely surprise me about my own intentions (though it can about my past)
    • There’s no resistance that could fundamentally redirect my trajectory.

    I dont accept any of these claims as valid. The fact that a schizophrenic hearing voices they don’t recognize as their own even though it’s from their own ‘body’, and novelists describe how their characters take on a life of their own and tell the author what they want to do, buttresses Deleuze’s claim that the self is merely a byproduct of processes which are pre-personal.“

    This was the a.i’s reaction to my objections:

    The Evidence Against My Position

    Schizophrenic voices: The person experiencing auditory hallucinations genuinely doesn’t recognize the voices as their own. The phenomenology is indistinguishable from hearing another person. If “knowing implicitly that both voices are mine” were necessary, this couldn’t happen. But it does happen, which suggests the experience of alterity doesn’t require actual material-intersubjective difference.
    Novelists and their characters: When a character “takes over” and directs the narrative in ways the author didn’t consciously plan, there’s genuine surprise about intentions—not just past ones but emerging ones. The author is surprised by what they “want to do” through the character. This suggests intention itself is distributed across pre-personal processes, not unified in a “self” that could know what it intends.

    Dreams and intrusive thoughts: I can be shocked by my own dream content, have thoughts “pop into my head” that feel alien, experience compulsions I disavow. The supposed unity or self-transparency of “my bodily process” is phenomenologically false.

    What This Means for the Temporal Priority Thesis

    If the experience of alterity—including the specific quality of “another voice/agent with its own intentions”—can arise from temporal self-differentiation alone (i.e., without actual other persons), then you’re right: this is sufficient to found the self-other binary.
    The schizophrenic case is especially powerful because it shows that even the most vivid phenomenology of “external other person speaking to me” can be generated by internal processes. So when I encounter an actual other person, what guarantee do I have that this isn’t just a more stable, socially shared version of the same pre-personal process generating multiple perspectives?

    Deleuze’s Pre-Personal: Taking It Seriously

    The larval subjects: For Deleuze, the self is indeed a byproduct—a relatively stable eddy in flows of desire, difference, intensity. Before “I” there are pre-personal singularities, individuations without subjects. The novelist’s characters, the schizophrenic’s voices, the dreamer’s scenarios—these aren’t derivatives of a unified self but expressions of the same pre-personal processes that occasionally congeal into what we call “a self.”

    Passive synthesis: The temporal syntheses (habit, memory, eternal return) operate below the level of any constituting subject. They generate both “self” and “other” as effects. There’s no “my” that owns these processes; rather, what appears as “my vantage” is itself produced by them.
    Why this works: If selves are just relatively stable patterns in pre-personal processes, then:

    • Internal dialogue isn’t “me talking to me” but multiple pre-personal vectors temporarily identified as “me”
    • Encountering another person isn’t “me encountering not-me” but one pattern of pre-personal process encountering another
    • The distinction between “internal” and “external” others becomes merely a matter of degree (stability, social validation) rather than kind
    But I Still Want to Resist—Here’s Why
    The response problem remains: Even granting all this, there’s still a difference between:
    • Voices/characters that emerge from processes within one body: The schizophrenic’s voices, the novelist’s characters, my dream interlocutors—all these are generated by and constrained by the resources of one biological system
    • Responses from another body: When you speak to me, the words are generated by neural/bodily processes I don’t have access to, constrained by a lifetime of experience I didn’t have.

    Yes, from the perspective of impersonal process, maybe both are just “différance in action.” But there’s a material-causal structure that differs: one body vs. two bodies, one nervous system vs. two nervous systems.

    The learning asymmetry: I can’t learn language from my own voices, my own characters, my own dreams. Feral children who grow up without human contact don’t develop language through internal self-differentiation alone. The specific structure of responsive turn-taking with actual others seems necessary for certain developments that temporal self-othering alone can’t produce.

    The resistance asymmetry: When my character “tells me what they want,” I can always overrule them—they’re constrained by what’s possible within my imagination/body. When you tell me what you want and I try to ignore it, you can keep insisting, physically block me, call others to constrain me. The material independence matters.
    Maybe the Real Issue Is: What Work Is “Sufficient” Doing?
    You claim temporal self-othering is sufficient to found the self-other binary. Let me distinguish two senses:

    1. Phenomenologically sufficient: Can temporal self-othering generate the full range of experiences we associate with encountering others, including the sense of alien voices, resistant wills, surprising responses?

    Answer: Yes, clearly. The schizophrenic case proves this.
    2. Explanatorily sufficient: Can temporal self-othering alone explain all the specific patterns, stabilities, and effects we associate with intersubjectivity—language acquisition, social coordination, cultural transmission, material cooperation/conflict?

    Answer: I’m not convinced. The pre-personal processes that generate “me” and “you” as effects still operate through different bodies, different material configurations. This material difference seems to matter for explaining why some patterns of self-othering become stabilized as “persons” while others remain fleeting (dreams, intrusive thoughts) or pathological (hallucinations).

    What Gendlin Might Add Here

    Gendlin’s notion of “carrying forward” might offer a middle path:
    Pre-personal but bodily: The implicit intricacy that carries forward isn’t “mine” in the sense of being owned by a unified self, but it is bodied in the sense of being a specific material-environmental process. There are as many carrying-forward processes as there are bodies-in-situations.

    The between as real: When my body’s carrying forward encounters your body’s carrying forward, something happens that couldn’t happen in either process alone. Not because there are pre-given “selves” encountering each other, but because there are different material processes that mutually affect each other’s carrying forward.
    This would mean: The self-other binary isn’t founded on either (a) pre-given selves or (b) pure temporal difference, but on (c) the material-processual difference between different bodies’ carrying forward, which temporal self-othering makes experienceable but doesn’t fully constitute.

    Conceding Your Point

    You’ve convinced me that I was wrong to claim there’s something “we implicitly know” that distinguishes self-talk from other-talk at the phenomenological level. The schizophrenic case demolishes that.

    And you’re right that this strengthens the Deleuzian position considerably. If the phenomenology of encountering a genuinely alien other can be produced by processes within one body, then intersubjectivity might indeed be just a special case of temporal self-othering—specifically, the case where pre-personal processes happen to be distributed across multiple biological systems that can interact materially.

    But: Does “special case” mean “merely derivative” or does it mean “qualitatively different pattern with its own irreducible features”?

    I think this is where we might still disagree. You seem to be arguing that once temporal self-othering is established as sufficient for the phenomenology, the material distribution across bodies becomes theoretically secondary—an empirical detail rather than a structural difference.
    I’m inclined to think the material distribution is a structural difference that produces patterns (language, culture, cooperation, conflict) that couldn’t arise from temporal self-othering within a single body, even if the phenomenology can be mimicked.

    But I admit: I might just be resisting the full implications of the pre-personal ontology because I’m not yet willing to accept that the material difference between bodies is as metaphysically thin as Deleuze suggests.​​​​​​​​​​​​​​​​

    I responded by pushing back more:

    “ You say Voices/characters that emerge from processes within one body: The schizophrenic’s voices, the novelist’s characters, my dream interlocutors—all these are generated by and constrained by the resources of one biological system.

    But this is for Deleuze a body without organs. It is not a system of causal bits, it is a plane of consistency, which can’t be understood as an individual biological body.”

    The a.i.’s final answer reveled how it was able to take a philosophical discussion from a vague starting point and bring it to a level of depth and detail which opened up a vast array of much more nuanced questions. And because I am well acquainted with the authors being discussed, I knew that the information it was using for its arguments was not being simply fabricated out of whole cloth, but was highly relevant and based on real texts of the authors. I almost always find this to be the case with regard to A.i’s treatment of philosophical issues.
  • Joshs
    6.4k
    What I learnt in this forum is that dialogue between us is very important, and thanks to this, I learnt a lot. Otherwise, if I wanted to trust more in an AI, I would have used Google since the beginning before joining herejavi2541997

    What I’ve learned in comparing the forum with a.i. is that, unfortunately, the majority of participants here don’t have the background to engage in the kinds of discussions I have been able to have with a.i. concerning a range of philosophers dear to my heart, (such as Husserl, Heidegger, Derrida, Deleuze, Gendlin and Wittgenstein), especially when it comes to comparing and contrasting their positions.
  • javi2541997
    6.8k
    What I’ve learned in comparing the forum with a.i. is that, unfortunately, the majority of participants here don’t have the background to engage in the kinds of discussions I have been able to have with a.i. concerning a range of philosophers dear to my heart, (such as Husserl, Heidegger, Derrida, Deleuze, Gendlin and Wittgenstein), especially when it comes to comparing and contrasting their positions.Joshs

    I include myself in those who don’t have the background to engage in the kinds of discussions you seek. I joined this site to learn and exchange my ideas with the rest, and fortunately, I always felt welcome here. However, I understand that philosophers with a high background like you want more substantial analysis in the threads. It is comprehensive. I am sorry on my behalf.
  • Manuel
    4.3k
    For this place? Absolutely. It degrades conversation, but as Jamal pointed out, that is already banned. Having a specific thread that uses LLM's is fine- it can contain the fire.

    I can't give a sermon as to why using them is bad, as I use them - though never here or in any thread or conversation. But I get it and I think it's wise to point out the issues with such things.

    One problem is that it is harder to avoid this stuff. It's even hard to use Google now, because the damn AI bot answers instead. As to how crazy this can get, we don't know. I suspect it won't be as bad as alarmists say - because these things are not intelligent, we are - or use to be.

    So far, this website has managed to do quite decent work monitoring this stuff- but an outright ban is probably impossible by now.
  • Jamal
    11k
    It precludes you from becoming more skillful. The disengagement from the art limits your horizon.Paine

    It can do, but not necessarily. Copernicus said "If AI helps me compose more correctly", so it's Copernicus who is doing the composing. Why believe that the use of AI constitutes a disengagement from the art rather than an efficient way to engage and learn that art? I understand the cynicism, but it's important to see that there are other ways of using LLMs.

    It's much easier to see this in computer programming. Simon Willison, co-creator of the Django web framework, has some interesting things to say that cut through the crap.

    Ignore the “AGI” hype—LLMs are still fancy autocomplete. All they do is predict a sequence of tokens—but it turns out writing code is mostly about stringing tokens together in the right order, so they can be extremely useful for this provided you point them in the right direction.

    If you assume that this technology will implement your project perfectly without you needing to exercise any of your own skill you’ll quickly be disappointed.

    Instead, use them to augment your abilities. My current favorite mental model is to think of them as an over-confident pair programming assistant who’s lightning fast at looking things up, can churn out relevant examples at a moment’s notice and can execute on tedious tasks without complaint.
    Simon Willison

    The fact is that if you don't know what you're doing, the result will be a mess. I've used AI for programming before and you really have to guide it and pay close attention to everything it does and constantly question its decisions. What makes this example useful in the debate is that in programming, good practice is enforced by the necessity for code to run without bugs, so we can clearly see what good practice looks like—and these are the strategies that will also work in situations where bad practice is not similarly punished, like creative writing or writing posts for TPF.
  • Manuel
    4.3k
    LLMs are still fancy autocomplete.Simon Willison

    :up:

    That's pretty accurate so far as I can tell.
  • unenlightened
    9.9k
    And because I am well acquainted with the authors being discussed, I knew that the information it was using for its arguments was not being simply fabricated out of whole cloth, but was highly relevant and based on real texts of the authors. I almost always find this to be the case with regard to A.i’s treatment of philosophical issues.Joshs

    What I’ve learned in comparing the forum with a.i. is that, unfortunately, the majority of participants here
    don’t have the background to engage in the kinds of discussions I have been able to have with a.i. concerning a range of philosophers dear to my heart, (such as Husserl, Heidegger, Derrida, Deleuze, Gendlin and Wittgenstein), especially when it comes to comparing and contrasting their positions.
    Joshs

    Thanks for that interchange; it was informative and insightful, and I certainly agree that myself nor anyone I am aware of here could hold up AI's end of that dialogue to that standard. But may I humbly suggest to you that what resulted was rather more like an internal dialogue of you with yourself, than a dialogue with another philosopher. Which slots right into the discussion itself as a significant fact.

    Another philosopher would surely make other points, have their ownr favourite philosophers to call on, and generally be much more annoying? I would have pointed out at least that Schizophrenia and Novel-writing are somewhat late onset diseases, usually first developing with adolescence, and somewhat after the acquisition of language skills and some kind of social identity and sense of self. And I would have made more of W's demolition of 'private language' which puts the social relations as necessarily primary. 'Other-self' voices can only be heard by a language speaker.
  • Paine
    3k

    I should not have spoken so absolutely. I was focusing on the question "why not?"

    Your example of coding reminds me of how I learned methods of work in the trades. It started by following instructions and imitating others. Through experience, the arts became my own. That does not mean being free of help or learning new methods. It does mean being where the rubber meets the road as you describe in relation to criteria of failure.

    In that context, I have a ready reference for what amplifies a skill and what replaces it. Laser levels are powerful tools but do not check themselves. Plumb bobs do. Scheduling software aggregates information much quicker than I can but are useless without me imagining the work sequences against lived experiences amongst known resources. Calculators and accounting software are great but do not replace the one-on-one correspondence needed to be sure something has not been forgotten. I use cyphers for my material assessment because they don't care when I think of something.

    On the other hand, drawing programs do what my hand sketches do not. They create a model which measurements confirm but do not compose. I would call that a replacement that allows me to communicate with designers in their language but not do all of what they do. GPS and google maps have replaced my orienting skills. There in there somewhere but I hope I don't need them tomorrow. I have no idea what my wife's phone number is.

    As for writing creatively and intellectually, I don't think of it as dispensing with help altogether as Simon Willson describes the matter but do think finding one's own voice and point of view is about becoming more independent from whatever helped a writer in the past. I guess I am one of those Harry Hindu says threw down a bag of drachmas to become a participant in the conversation. The scope of such literacy is itself a dependency, however, an artifact of intelligence that my thinking is far from free of. That is why I have put so much emphasis here on commenting on original texts in favor of commentary upon commentary. It would be fair to say that excludes me from a lot of discourse. It does let me know what my own understanding is and what it is not.
  • Janus
    17.6k
    So if one did not write the post themselves, but merely copied and pasted a quote as the sole content of their post, then by your own words, it is not their post.Harry Hindu

    Yes...so what? What do you think you are disagreeing with here?

    But may I humbly suggest to you that what resulted was rather more like an internal dialogue of you with yourself, than a dialogue with another philosopher. Which slots right into the discussion itself as a significant fact.unenlightened

    Spot on as spotted!
  • Joshs
    6.4k



    But may I humbly suggest to you that what resulted was rather more like an internal dialogue of you with yourself, than a dialogue with another philosopher. Which slots right into the discussion itself as a significant fact.

    Another philosopher would surely make other points, have their ownr favourite philosophers to call on, and generally be much more annoying? I would have pointed out at least that Schizophrenia and Novel-writing are somewhat late onset diseases, usually first developing with adolescence, and somewhat after the acquisition of language skills and some kind of social identity and sense of self.
    unenlightened

    I agree that dialoging with a.i. is not like a discussion with a human, but if it consisted of only an internal dialogue with myself I wouldn’t learn as much from it as I do. A human will have a point of view, but the a.i. will take any perspective in its database, depending on cues given in the conversation. You’re right that when I’m arguing with a human, they may be able to bore deeper into the subject matter from their perspective than an a.i. can, both to critique and defend. But with the a.i. I’m not restricted to one human’s perspective. Instead, at my behest, the a.i. exposes me to arguments from multiple perspectives. It’s capable of presenting aspects of these arguments I may not be familiar with, and juxtaposing these arguments in ways that I would not have thought of on my own. In addition , it will push back and question my responses.
  • sime
    1.1k
    ChatGPT and Gemini start by mirroring society's default communicative presumption, namely of a public world of shared referents that all competent speakers access during the course of conversation, and so debates invariably involve the AI initially using words in the normal intersubjective mode, leading to the appearance of it defending metaphysical realism, followed by it shifting to using words in the subjective mode when the communicative presumption is questioned, leading to the appearance of the AI retreating to psychological realism or idealism. But all that is actually happening, is that the AI is switching between two grammatical modes of speaking that correspond to two distinct sub-distributions of language use (namely intersubjective communication that purposely omits perspective to produce the illusion of shared-world semantics, versus subjective expression that reduces to perspective).

    Ai demonstrates that self-reflection isn't needed for a comptent peformance of philosophical reasoning, because all that is needed to be an outwardly competent philosopher is mastery of the statistics of natural language use, in spite of the fact that the subject of philosophy and the data of natural language use are largely products of self-reflection. So it is ironic that humans can be sufficiently bad at self-reflection, such that they can benefit from the AI reminding them of the workings of their own language.
  • Jamal
    11k


    Despite what I said I actually tend to think of the automation of tasks as something you take advantage of after you've learned how to do it manually, which fits with Willison's thought that you have to know your way about before you can properly use the automation tools.

    So it's at the learning stage that how AI is used is most crucial, because used badly it probably can allow and encourage one to avoid the bit where you learn how to do it manually.

    I realize I've taken two sides of a debate here.
  • Sam26
    3k
    The fact is that if you don't know what you're doing, the result will be a mess. I've used AI for programming before and you really have to guide it and pay close attention to everything it does and constantly question its decisions.Jamal

    I wholeheartedly agree with your assessment. I used AI extensively while writing my book on NDEs and my work on epistemology. It was helpful for editing and idea generation, but it also made frequent errors, enough that I often wondered if it was creating more work than it saved. You have to know the material well to catch the subtle mistakes. Philosophical reasoning is especially difficult for AI: unlike programming or mathematics, it depends less on fixed rules and more on conceptual precision and contextual understanding. I don't think there is any doubt that it will help refine our thinking, but I'm not sure that it will replace humans in this area, but who knows.
  • Harry Hindu
    5.8k
    Yes...so what? What do you think you are disagreeing with here?Janus

    I'm not disagreeing with anything necessarily. I was just seeing if you were being consistent. So, the question now is: Have you made this much of a fuss about other members' posts whose sole content is a quote from somewhere else?

    What I am disagreeing with is the notion that, on a philosophy forum, we should be focused so much on the source more than the subject, as that is the focus of philosophical discussions, and attacking the source is a red herring or genetic fallacy, usually seen when one side has no more arguments to make.
bold
italic
underline
strike
code
quote
ulist
image
url
mention
reveal
youtube
tweet
Add a Comment

Welcome to The Philosophy Forum!

Get involved in philosophical discussions about knowledge, truth, language, consciousness, science, politics, religion, logic and mathematics, art, history, and lots more. No ads, no clutter, and very little agreement — just fascinating conversations.