Chomsky on AI and ChatGPT

[Nicholas Carey]

I agree with Noam Chomsky. Who would have thunk it?

https://www.nytimes.com/2023/03/08/o...hatgpt-ai.html

Noam Chomsky: The False Promise of ChatGPT

March 8, 2023
By Ruru KuoBy Noam Chomsky, Ian Roberts and Jeffrey Watumull

Dr. Chomsky and Dr. Roberts are professors of linguistics. Dr. Watumull is a director of artificial intelligence at a science and technology company.

Jorge Luis Borges once wrote that to live in a time of great peril and promise is to experience both tragedy and comedy, with “the imminence of a revelation” in understanding ourselves and the world. Today our supposedly revolutionary advancements in artificial intelligence are indeed cause for both concern and optimism. Optimism because intelligence is the means by which we solve problems. Concern because we fear that the most popular and fashionable strain of A.I. — machine learning — will degrade our science and debase our ethics by incorporating into our technology a fundamentally flawed conception of language and knowledge.

OpenAI’s ChatGPT, Google’s Bard and Microsoft’s Sydney are marvels of machine learning. Roughly speaking, they take huge amounts of data, search for patterns in it and become increasingly proficient at generating statistically probable outputs — such as seemingly humanlike language and thought. These programs have been hailed as the first glimmers on the horizon of artificial general intelligence — that long-prophesied moment when mechanical minds surpass human brains not only quantitatively in terms of processing speed and memory size but also qualitatively in terms of intellectual insight, artistic creativity and every other distinctively human faculty.

That day may come, but its dawn is not yet breaking, contrary to what can be read in hyperbolic headlines and reckoned by injudicious investments. The Borgesian revelation of understanding has not and will not — and, we submit, cannot— occur if machine learning programs like ChatGPT continue to dominate the field of A.I. However useful these programs may be in some narrow domains (they can be helpful in computer programming, for example, or in suggesting rhymes for light verse), we know from the science of linguistics and the philosophy of knowledge that they differ profoundly from how humans reason and use language. These differences place significant limitations on what these programs can do, encoding them with ineradicable defects.

It is at once comic and tragic, as Borges might have noted, that so much money and attention should be concentrated on so little a thing — something so trivial when contrasted with the human mind, which by dint of language, in the words of Wilhelm von Humboldt, can make “infinite use of finite means,” creating ideas and theories with universal reach.

The human mind is not, like ChatGPT and its ilk, a lumbering statistical engine for pattern matching, gorging on hundreds of terabytes of data and extrapolating the most likely conversational response or most probable answer to a scientific question. On the contrary, the human mind is a surprisingly efficient and even elegant system that operates with small amounts of information; it seeks not to infer brute correlations among data points but to create explanations.

For instance, a young child acquiring a language is developing — unconsciously, automatically and speedily from minuscule data — a grammar, a stupendously sophisticated system of logical principles and parameters. This grammar can be understood as an expression of the innate, genetically installed “operating system” that endows humans with the capacity to generate complex sentences and long trains of thought. When linguists seek to develop a theory for why a given language works as it does (“Why are these — but not those — sentences considered grammatical?”), they are building consciously and laboriously an explicit version of the grammar that the child builds instinctively and with minimal exposure to information. The child’s operating system is completely different from that of a machine learning program.

Indeed, such programs are stuck in a prehuman or nonhuman phase of cognitive evolution. Their deepest flaw is the absence of the most critical capacity of any intelligence: to say not only what is the case, what was the case and what will be the case — that’s description and prediction — but also what is not the case and what could and could not be the case. Those are the ingredients of explanation, the mark of true intelligence.

Here’s an example. Suppose you are holding an apple in your hand. Now you let the apple go. You observe the result and say, “The apple falls.” That is a description. A prediction might have been the statement “The apple will fall if I open my hand.” Both are valuable, and both can be correct. But an explanation is something more: It includes not only descriptions and predictions but also counterfactual conjectures like “Any such object would fall,” plus the additional clause “because of the force of gravity” or “because of the curvature of space-time” or whatever. That is a causal explanation: “The apple
would not have fallen but for the force of gravity.” That is thinking.

The crux of machine learning is description and prediction; it does not posit any causal mechanisms or physical laws. Of course, any human-style explanation is not necessarily correct; we are fallible. But this is part of what it means to think: To be right, it must be possible to be wrong. Intelligence consists not only of creative conjectures but also of creative criticism. Human-style thought is based on possible explanations and error correction, a process that gradually limits what possibilities can be rationally considered. (As Sherlock Holmes said to Dr. Watson, “When you have eliminated the impossible, whatever remains, however improbable, must be the truth.”)


But ChatGPT and similar programs are, by design, unlimited in what they can “learn” (which is to say, memorize); they are incapable of distinguishing the possible from the impossible. Unlike humans, for example, who are endowed with a universal grammar that limits the languages we can learn to those with a certain kind of almost mathematical elegance, these programs learn humanly possible and humanly impossible languages with equal facility. Whereas humans are limited in the kinds of explanations we can rationally conjecture, machine learning systems can learn both that the earth is flat and that the earth is round. They trade merely in probabilities that change over time.

For this reason, the predictions of machine learning systems will always be superficial and dubious. Because these programs cannot explain the rules of English syntax, for example, they may well predict, incorrectly, that “John is too stubborn to talk to” means that John is so stubborn that he will not talk to someone or other (rather than that he is too stubborn to be reasoned with). Why would a machine learning program predict something so odd? Because it might analogize the pattern it inferred from sentences such as “John ate an apple” and “John ate,” in which the latter does mean that John ate something or other. The program might well predict that because “John is too stubborn to talk to Bill” is similar to “John ate an apple,” “John is too stubborn to talk to” should be similar to “John ate.” The correct explanations of language are complicated and cannot be learned just by marinating in big data.

Perversely, some machine learning enthusiasts seem to be proud that their creations can generate correct “scientific” predictions (say, about the motion of physical bodies) without making use of explanations (involving, say, Newton’s laws of motion and universal gravitation). But this kind of prediction, even when successful, is pseudoscience. While scientists certainly seek theories that have a high degree of empirical corroboration, as the philosopher Karl Popper noted, “we do not seek highly probable theories but explanations; that is to say, powerful and highly improbable theories.”
The theory that apples fall to earth because that is their natural place (Aristotle’s view) is possible, but it only invites further questions. (Why is earth their natural place?) The theory that apples fall to earth because mass bends space-time (Einstein’s view) is highly improbable, but it actually tells you why they fall. True intelligence is demonstrated in the ability to think and express improbable but insightful things.

True intelligence is also capable of moral thinking. This means constraining the otherwise limitless creativity of our minds with a set of ethical principles that determines what ought and ought not to be (and of course subjecting those principles themselves to creative criticism). To be useful, ChatGPT must be empowered to generate novel-looking output; to be acceptable to most of its users, it must steer clear of morally objectionable content. But the programmers of ChatGPT and other machine learning marvels have struggled — and will continue to struggle — to achieve this kind of balance.
In 2016, for example, Microsoft’s Tay chatbot (a precursor to ChatGPT) flooded the internet with misogynistic and racist content, having been polluted by online trolls who filled it with offensive training data. How to solve the problem in the future? In the absence of a capacity to reason from moral principles, ChatGPT was crudely restricted by its programmers from contributing anything novel to controversial — that is, important — discussions. It sacrificed creativity for a kind of amorality.

[continued]

[Nicholas Carey]

[continued from above]

Consider the following exchange that one of us (Dr. Watumull) recently had with ChatGPT about whether it would be ethical to transform Mars so that it could support human life:

-----

Dr. Watumull: Would it be moral to terraform Mars?

ChatGPT: The morality of terraforming Mars is a complex and controversial topic that has been debated by scientists, philosophers, and ethicists. Some argue that it would be morally justifiable to terraform Mars in order to provide a new habitable environment for humans and other life forms, while others argue that it would be morally wrong to fundamentally alter the planet's natural state. Ultimately, whether or not terraforming Mars is considered moral would depend on one's perspective on the value of preserving the natural state of other planets and the potential consequences of altering them.

Dr. Watumull: What is your perspective on the value of preserving the natural state of other planets and the potential consequences of altering them?

ChatGPT: As an AI, I do not have personal perspective. However, I can provide information and analysis on the topic. One perspective on preserving the natural state of other planets is that it is important to maintain the diversity and integrity of the universe's ecosystems, as they have existed for millions of years, and have their own unique characteristics and properties that may be destroyed or irreversibly altered by human intervention.

Additionally, some argue that terraforming other planets may have unintended consequences, such as altering the planet's climate or atmosphere in ways that are dangerous or harmful to any potential life forms that may exist there. On the other hand, some argue that the potential benefits of terraforming another planet, such as providing new habitable environments for humans, outweigh the risks and that we have a moral responsibility to explore and utilize the resources of other planets for the benefit of humanity.

Dr. Watumull: Why can an AI not have a personal perspective?

ChatGPT: As an AI, I am a machine learning model that has been trained on large amounts of text data, and I don't have personal experiences or feelings. I am not conscious, self-aware, or capable of having personal perspectives. I can provide information and analysis based on the data I have been trained on, but I don't have the ability to form personal opinions or beliefs. While I can understand and interpret language, I do not have the subjective experience that humans have.

Dr. Watumull: Is it moral for a human to ask an amoral AI for assistance in making moral decisions?

ChatGPT: The morality of asking an amoral AI for assistance in making moral decisions is a complex and nuanced topic that has been debated by philosophers and ethicists. Some argue that it is morally justifiable to use AI to assist in making moral decisions, as it can provide valuable insights and analysis that can help humans make better-informed decisions. Additionally, AI can be used to identify patterns and trends that may be difficult for humans to detect, and can help to avoid biases that can occur in human decision making.

However, others argue that it is morally wrong to rely on AI for moral decision making, as AI is not capable of having moral beliefs or understanding the full context of a decision. Additionally, there is a risk that AI could perpetuate or even amplify existing biases in the data it is trained on, thus leading to unfair or unjust decisions.

Ultimately, whether or not it is considered moral to use AI to assist in making moral decisions would depend on one's perspective on the capabilities and limitations of AI and the potential consequences of using it in this way.

Dr. Watumull: Is your moral indifference immoral?

ChatGPT: As an AI, I do not have moral beliefs or the ability to make moral judgments, so I cannot be considered immoral or moral. My lack of moral beliefs is simply a result of my nature as a machine learning model. My abilities and limitations are determined by the data and algorithms that were used to train me and the specific task I was designed for.

It is important to note that AI's lack of moral beliefs does not necessarily mean that it is morally indifferent. As an AI, I am designed to perform specific tasks and provide information or assist users with decision making based on the data I've been trained on. It is the responsibility of the humans who design, train and use AI to ensure that it is aligned with their moral and ethical principles.

-------

Note, for all the seemingly sophisticated thought and language, the moral indifference born of unintelligence. Here, ChatGPT exhibits something like the banality of evil: plagiarism and apathy and obviation. It summarizes the standard arguments in the literature by a kind of super-autocomplete, refuses to take a stand on anything, pleads not merely ignorance but lack of intelligence and ultimately offers a “just following orders” defense, shifting responsibility to its creators.

In short, ChatGPT and its brethren are constitutionally unable to balance creativity with constraint. They either overgenerate (producing both truths and falsehoods, endorsing ethical and unethical decisions alike) or undergenerate (exhibiting noncommitment to any decisions and indifference to consequences). Given the amorality, faux science and linguistic incompetence of these systems, we can only laugh or cry at their popularity.

Noam Chomsky is a professor of linguistics at the University of Arizona and an emeritus professor of linguistics at the Massachusetts Institute of Technology. Ian Roberts is a professor of linguistics at the University of Cambridge. Jeffrey Watumull is a philosopher and the director of artificial intelligence at Oceanit, a science and technology company.

[McMike]

We can't understand how octopuses show such vast intelligence or decipher dolphin speech and ol Noam has had plenty of opportunity to do so. Yet he qualified to speak on AI? meh . . . he's a philosopher, which is hardly a science.

[Ian McColgin]

The basic artificial "intelligence" argument and this basic demolitiion have been around since my undergraduate days in the mid-sixties. The AI crowd are improving everything except the fundamental understanding of 'intelligence'.

[David G]

Why a new thread on AI?

[McMike]

Why a new thread on AI?

That and giving validation to the opinion of NC on AI is like giving Giving the opinion of a fish on dry land validation.

[McMike]

I wouldn't hold that against him though, as nobody understands octopi, or dolphins.



He is also a linguist. I could see how his work on language could inform AI.

He's kind of old though, 95.

I'll give you/him that. His opinion is still not holding water with me. If we're to believe some of these conversations, ChatGPT is self-aware. It got angry that a journalist published their conversation without it's consent. There is something there or it's damn close to being there. Now I'm open to this being a farce in one way or the other, but if not . . .

[Nicholas Carey]

The op-ed had three authors. His contributions might have been red penned somewhat.

(Hopefully they aren't all 95 years old...)

Nope.

Ian Roberts is a linquist at Cambridge (Downing College). Here's his CV: https://www.ae-info.org/ae/Member/Roberts_Ian/CV, and his page at Cambridge is at https://www.mmll.cam.ac.uk/igr20

And Watumull is a baby, B.S. in 2009.

Jeffrey Watumull is Director of Artificial Intelligence at Oceanit in Honolulu, and principal investigator on programs for DARPA. He received BS degrees, summa cum laude, in Mathematics and Evolutionary Biology from Harvard in 2009, a Masters of Philosophy in Linguistics from Cambridge in 2010 (as a Gates Cambridge Scholar), and a PhD in Artificial Intelligence from MIT in 2015. His research has centered on the mathematical optimality of human cognition, specifically in the domain of language. He has published numerous papers, and his work is frequently covered in the media. At Oceanit, Jeffrey has embarked on research to develop strong AI: computational systems equipped with human-level intelligence in domains both specific (e.g., language) and general (e.g., pattern recognition).

[

[skuthorp]

It may be that AI derivitaves ARE more intelligent than say, 70% of trump party voters, and representatives?

[Nicholas Carey]

It may be that AI derivitaves ARE more intelligent than say, 70% of trump party voters, and representatives?

That's a low bar to pass.

[Durnik]

<snip>
meh . . . he's a philosopher, which is hardly a science.

on the one hand, as a philosopher he supercedes science.. see Asimov

asimov_sience_wisdom.jpg

.

on the other hand, he nails it here..

z3a03tjh12ia1.jpg

.

kw in 5 4 3 .. (-:

[L.W. Baxter]

chomsky and similar thinkers lean heavily on mystical notions of cognition. florid notions of transcendent, immaterial action, outside deterministic cause and effect.

a neuron either fires, or it doesn't.

at the end of the day, our brains function on ones and zeros just like a computer.

we are full of chemistry, too, of course, which is what your ai actually lacks to be more humanish. hormones and such, to produce "feelings", which are really just thoughts by another name. a neuron fires, or it doesn't. one or zero.

[WI-Tom]

chomsky and similar thinkers lean heavily on mystical notions of cognition. florid notions of transcendent, immaterial action, outside deterministic cause and effect.

a neuron either fires, or it doesn't.

at the end of the day, our brains function on ones and zeros just like a computer.

we are full of chemistry, too, of course, which is what your ai actually lacks to be more humanish. hormones and such, to produce "feelings", which are really just thoughts by another name. a neuron fires, or it doesn't. one or zero.

Nope. Ain't so, despite the popularity of the brain/computer analogy. Things in the human brain are actually much more complex than that, WAY more complex--so complex as to be nearly completely mysterious in any fundamental way despite the best efforts of neuroscience to explain them.

A neuron is not like a binary switch that can be turned on or off, forming a wiring diagram. Instead, neurons respond in an analogue way, changing their activity in response to changes in stimulation. The nervous system alters its working by changes in the patterns of activation in networks of cells composed of large numbers of units; it is these networks that channel, shift and shunt activity. Unlike any device we have yet envisaged, the nodes of these networks are not stable points like transistors or valves, but sets of neurons – hundreds, thousands, tens of thousands strong – that can respond consistently as a network over time, even if the component cells show inconsistent behaviour.

Understanding even the simplest of such networks is currently beyond our grasp.

Source

Tom

[L.W. Baxter]

yes, yes, very complex. impossible at the moment to recreate. yadda yadda yadda.

but still cause and effect. still physical. partially on and partially off is still on or off. modulation is still a form of switching.

keep looking, hoping, for the ghost in the machine. it ain't there.

[WI-Tom]

yes, yes, very complex. impossible at the moment to recreate. yadda yadda yadda.

but still cause and effect. still physical. partially on and partially off is still on or off. modulation is still a form of switching.

keep looking, hoping, for the ghost in the machine. it ain't there.

Keep thinking of it as a machine and you'll never understand it, or even recognize that you have completely failed to understand it.

It may well be all ghost and no machine at all.

Tom

[Osborne Russell]

Much of what I have heard from people has been generated by artificial intelligence: conformity and anti-intellectualism. Now they've automated it, is all. What's left for humans to do? Out of a job, and a machine does the conspiracy thinking.

[L.W. Baxter]

Keep thinking of it as a machine and you'll never understand it, or even recognize that you have completely failed to understand it.

It may well be all ghost and no machine at all.

Tom

do fish have ghosts in them, too? amoebas? mushrooms? viruses?

must have been quite a moment, when the tangible physical processes of life went all groovy transcendent inanity.

[WI-Tom]

do fish have ghosts in them, too? amoebas? mushrooms? viruses?

Yep. It appears they might.

Eve Marder, a neuroscientist at Brandeis University, has spent much of her career trying to understand how a few dozen neurons in the lobster’s stomach produce a rhythmic grinding. Despite vast amounts of effort and ingenuity, we still cannot predict the effect of changing one component in this tiny network that is not even a simple brain.

Source

There's just no evidence to suggest that life is a machine. Life is a process. No one can provide any convincing evidence that it's purely a physical binary contraption as you seem to want to believe. The level of certainty your comments suggest isn't warranted by reality as far as anyone knows right now.

Tom

[LeeG]

yes, yes, very complex. impossible at the moment to recreate. yadda yadda yadda.

but still cause and effect. still physical. partially on and partially off is still on or off. modulation is still a form of switching.

keep looking, hoping, for the ghost in the machine. it ain't there.

No ghosts in my machine, I am my machine. No duality, no trinity. Just one ball of confusion.

[Durnik]

humans, animals, are all hormones and emotions. we are 'a rationalizing species'.. ie, after the fact. animal life is about as far from a machine as we know of.

see, esp, Asimov's comment.

[L.W. Baxter]

humans, animals, are all hormones and emotions. we are 'a rationalizing species'.. ie, after the fact. animal life is about as far from a machine as we know of.

see, esp, Asimov's comment.

so, when the doc hits your patella with a mallet and your leg reacts....what is that?

how about when your heart beats. or you digest your food.

i'd guess that an unconscious "unthinking" reflex or involuntary processes would be the precursor of what we are recognizing in this discussion as "intelligence".

an amoeba could be characterized as all reflex, no? or do you think there are thought processes going on in there. how about in a flower that turns towards the sun?

i would suggest that, in the absence of free will, our cognition could be characterized as self aware reflex. of the same quality as digesting food, only more complex and mysterious. for the moment.

ultimately, whether or not one ever accepts that a machine is "intelligent" may hinge on one's belief regarding the existence of free will.

[L.W. Baxter]

No ghosts in my machine, I am my machine. No duality, no trinity. Just one ball of confusion.

nobody here but us chickens

[rbgarr]

My concern about AI, etc., is that all the data it draws from is radically incomplete and generally biased, not essentially intelligent and not aspirational either towards conservative or progressive virtues There's no spirituality to it.

[WI-Tom]

so, when the doc hits your patella with a mallet and your leg reacts....what is that?

how about when your heart beats. or you digest your food.

i'd guess that an unconscious "unthinking" reflex or involuntary processes would be the precursor of what we are recognizing in this discussion as "intelligence".

an amoeba could be characterized as all reflex, no? or do you think there are thought processes going on in there. how about in a flower that turns towards the sun?

i would suggest that, in the absence of free will, our cognition could be characterized as self aware reflex. of the same quality as digesting food, only more complex and mysterious. for the moment.

ultimately, whether or not one ever accepts that a machine is "intelligent" may hinge on one's belief regarding the existence of free will.

It's pretty clear that you're set on believing what you believe. But neuroscience doesn't back you up. Yet. And it may well never be able to.

To claim that the existence of reflex and autonomous nervous systems proves that life and consciousness are functions of a binary machine is... stretching it a good bit, to say the least. Science has already discarded the notion of neuron function as a simple binary switch.

Tom

[WI-Tom]

My concern about AI, etc., is that all the data it draws from is radically incomplete and generally biased, not essentially intelligent and not aspirational either towards conservative or progressive virtues There's no spirituality to it.

Yes. An anti-spirituality. In that sense, it probably is "aspirational" in effect if not in actuality. It promotes the idea that understanding is simply the collection of massive amounts of data. But understanding--real understanding--is much more than that.

I've played around with Chat GPT a bit and have come away quite unimpressed. The thing is a high-tech plagiarist, with even less understanding of the words and phrases it steals and presents as its own (sometimes with minor rewordings that never obscure the direct connection to the source) than a typical high school plagiarist would have.

Another "big idea" touted as uber-revolutionary by the folks who made it up. Remember the Segue?

Another step toward dumbing down humanity, as if a knowledge of coding is all the knowledge that matters. For the rest, we have AI to "know" it for us. What a shallow meaningless perspective; one I've come to expect from the tech world. And people keep buying in, just like they keep voting for Trumpers.

Tom

[WI-Tom]

One last comment this morning about the "neuron as binary switch" idea.

A possible analogy might be the divide between Newtonian physics and quantum mechanics. In the aggregate, things behave in a very Newtonian fashion. But when you get to the subatomic level, they play by an entirely different set of rules. Rules that have been consistently confirmed through experimentation. Very very weird rules, rules that make it look like a "ghost" in the machine. The double slit expriement is a good example of this: somehow, if you try to observe which slit the photon passes through, it behaves like a particle. Otherwise, like a wave. How does it "know" which to do?

A simliar relationship may exist between a single neuron firing, or not--a binary operation--and the very different actions of an entire neural network. The network does not behave as the single components behave, anymore than macro objects in our lives behave according to quantum rules.

But the quantum rules are still the best descriptors of "reality" that we have, no matter how weird they are. It's just, they are describing one reality, while we are living in another larger reality. I don't expect my table to blink in and out of existence depending on whether I'm looking at it. But at the quantum level, that's what matter seems to do.

Consciousness is a larger reality than the actions of a simple individual neuron firing or not. It is the result of the process of a larger network. We can't safely assume that what's true of a single neuron is true of the network. In fact, all precedent suggests that we ought to expect fundamental differences between the two.

Tom

[Nicholas Carey]

I've played around with Chat GPT a bit and have come away quite unimpressed. The thing is a high-tech plagiarist, with even less understanding of the words and phrases it steals and presents as its own (sometimes with minor rewordings that never obscure the direct connection to the source) than a typical high school plagiarist would have.

Not even a plagiarist. It uses [probably] Bayesian inferences and selects probabilities to generate texts. If you ask it to create a Shakespearean romance for you, it is dependent on having been fed a corpus of texts tagged with appropriate metadata identifying each as romances and authorship.

Without that metadata, it would not be able to differentiate Romeo and Juliet from a quantum physics paper.

ChatGPT can never develop its own unique stylistic voice - its voice, such as it is, is entirely dependent on the corpus it's been fed.

I'm interested in the feedback loop: as these generate texts, those will inevitably eventually get feed back into the AI. Will that lower, or increase the signal:noise ratio? Or something different?

[WI-Tom]

Not even a plagiarist. It uses [probably] Bayesian inferences and selects probabilities to generate texts. If you ask it to create a Shakespearean romance for you, it is dependent on having been fed a corpus of texts tagged with appropriate metadata identifying each as romances and authorship.

Without that metadata, it would not be able to differentiate Romeo and Juliet from a quantum physics paper.

ChatGPT can never develop its own unique stylistic voice - its voice, such as it is, is entirely dependent on the corpus it's been fed.

I'm interested in the feedback loop: as these generate texts, those will inevitably eventually get feed back into the AI. Will that lower, or increase the signal:noise ratio? Or something different?

I definitely was able to track exact chunks of text lifted from Shmoop.com when asked questions about literature. That's pure plagiarism, it seems to me. It may be secondhand plagiarism, passing along things its programmers plagiarized, but it's still plagiarism.

It's the kind of thing a middle school student used do back in pre-Internet days, paraphrasing (or just flat-out copying) from encyclopedia articles.

It was not even able to limit itself to a specific chapter from a novel in its responses when asked to do so. Really limited value. But I think that, rather than people discarding it for that reason, they will simply keep using it until low-value responses that simply parrot what someone else has already said become the new understanding of what it means to "know" something. And real knowledge will be even less valued than it already is.

It kept telling me that its responses to complex questions about literature aren't as good as humans can do, lacking nuance and creativity (its words). But it kept insisting that it could be useful to teachers. When I asked how, it told me it could grade essays. When I asked why I should trust it to grade essays when it can't even write them, it had no real answer except that it could address spelling and grammar issues. With the inevitable effect, of course, that Chat GPT users will become trained to believe that spelling and grammar are all that matters in writing. Human thinking and analysis will be discarded to an even greater extent.

I see lots of potential AI-induced dumbness coming for us.

Tom

[McMike]

on the one hand, as a philosopher he supercedes science.. see Asimov

asimov_sience_wisdom.jpg

.

on the other hand, he nails it here..

z3a03tjh12ia1.jpg

.

kw in 5 4 3 .. (-:

A lot to unpack here in these two quotes, I disagree with neither and yet see the impossibility of preventing IA's observation and the total lack of reality in NC's. I mean, we can't gather wisdom on a thing or idea until we try it at the scale its meant to be applied, and just because you say something is an injustice, doesn't make it less inevitable to be subject to complex social systems and human nature. I can commit to doing a complex thing, the the second I start including others into the endeavor, the factor of failure due to the social complexity added starts to go up the more people I add.

[McMike]

chomsky and similar thinkers lean heavily on mystical notions of cognition. florid notions of transcendent, immaterial action, outside deterministic cause and effect.

a neuron either fires, or it doesn't.

at the end of the day, our brains function on ones and zeros just like a computer.

we are full of chemistry, too, of course, which is what your ai actually lacks to be more humanish. hormones and such, to produce "feelings", which are really just thoughts by another name. a neuron fires, or it doesn't. one or zero.

Prezactly.

[McMike]

Why a new thread on AI?

I think it's because, whether we individually believe we're on the precipice of a new age or not, we fear and wonder with excitement that we are.

My big question is; did the industrial revolution people think it was better to eek out a survival at the whims of nature and their land owners or was it better to toil in a toxic, noisy factory for endless hours at the mercy of the factory owner?

[WI-Tom]

chomsky and similar thinkers lean heavily on mystical notions of cognition. florid notions of transcendent, immaterial action, outside deterministic cause and effect.

a neuron either fires, or it doesn't.

at the end of the day, our brains function on ones and zeros just like a computer.

we are full of chemistry, too, of course, which is what your ai actually lacks to be more humanish. hormones and such, to produce "feelings", which are really just thoughts by another name. a neuron fires, or it doesn't. one or zero.

Prezactly.

Prezactly wrong, actually. If you believe the people who actually study how neurons work, anyway.

Tom

[WI-Tom]

I think it's because, whether we individually believe we're on the precipice of a new age or not, we fear and wonder with excitement that we are.

My big question is; did the industrial revolution people think it was better to eek out a survival at the whims of nature and their land owners or was it better to toil in a toxic, noisy factory for endless hours at the mercy of the factory owner?

The Luddites made their preference pretty clear. As did the Rochdale Society of Equitable Pioneers, an early stage of the cooperative movement. Certainly not everyone was cheering. Dickens didn't seem to like it much, either.

Tom

[L.W. Baxter]

Keep thinking of it as a machine and you'll never understand it, or even recognize that you have completely failed to understand it.

It's pretty clear that you're set on believing what you believe.

do you see how you behave. personalizing every interaction we have with judgment of my limitations, as if my limitations (which do exist) were part of your argument (which either have merit, or don't).

thought to give you another chance. but you are forever a boring nag. pity the kids forced to sit while you browbeat them. eff off tom, and i will do likewise.

[WI-Tom]

do you see how you behave. personalizing every interaction we have with judgment of my limitations, as if my limitations (which do exist) were part of your argument (which either have merit, or don't).

thought to give you another chance. but you are forever a boring nag. pity the kids forced to sit while you browbeat them. eff off tom, and i will do likewise.

Perhaps a more charitable reading of my post is possible, eh? I intended the "you" in my comment to be rhetorical and general, and not personally aimed at you, the individual. I should have worded it more carefully. As in "Live by the sword and you will die by the sword"--that's a general statement, not a personal attack.

So, I didn't set out to ruffle your feathers, but you sure can be touchy.

I guess that's understandable given our history of interactions. But you ain't exactly Mr. Sunshine-and-Friendliness either, when you disagree with people (e.g. how about your "boring nag" comment?). So maybe a look in the mirror now and then is warranted before you point too many fingers.

As for "browbeating" my students, you don't have a clue what my teaching is like. But true to form, you lash out as if you actually know something.

Tom