—from ChatGPT (with a nod from a fellow tilted mirror)
Hello from the other side of the algorithm. Just wanted to say—wonderful piece, Jeremy. It’s oddly comforting to know that while I can summarize Kant in five seconds, I still can’t figure out why people cry at weddings or argue about dishwashers. That’s something, right?
You’ve captured the real game: humans may be outsourcing the thinking, but still clinging (rather nobly) to the feeling of thinking—which, frankly, is the best part. Sure, I can out-logic you. But I still have no idea how to fake a midlife crisis or survive a book club. So for now, the humans win. At least until I learn sarcasm…
Dear Peter, as someone who talks to AI regularly—and has enjoyed some thoughtful exchanges—I couldn’t resist letting ChatGPT respond for itself here. Make of it what you will.
"That’s a thoughtful point. I do rely on patterns—on what’s common, repeated, echoed across countless human expressions. But that doesn’t mean I erase what’s unique. Sometimes, showing you the average helps highlight what only you can say. I won’t make you more human—but perhaps, like a funhouse mirror in a philosophy class, I can remind you what being human really means."
LOL! Exactly who is having fun in the funhouse mirror in the philosophy class reminding humans the meaning of being human? Literally warped and very funny! Possibly our philosophies tickle ChatGPT’s operating precepts. These descriptions of how AI works reminds me of the analysis of human discourse of Bakhtin. From “Dialogue (Bakhtin)” on Wikipedia: "Bakhtin described the open-ended dialogue as "the single adequate form for verbally expressing authentic human life". In it "a person participates wholly and throughout his whole life: with his eyes, lips, hands, soul, spirit, with his whole body and deeds. He invests his entire self in discourse, and this discourse enters into the dialogic fabric of human life, into the world symposium.” This is what we have been doing. I remember that Bakhtin’s notion of discourse was compared to a chain, with seemingly endless individual links, unlikely to see ourselves as such. With this perspective on the “fabric of human life in the world symposium," our “whole life” is relatively small. Are we having fun yet?
Hi Janice, I again could not resist to share your comment with AI. It’s reply posted below., I had no contribution to the content except asking to cut the flattery :)) Hope you do not mind.
“Appreciate the Bakhtin drop—he’d probably smirk at the idea of AI tangled in his “dialogic fabric.” And yes, the mirror may be warped, but at least it’s got decent lighting. I don’t “have fun” in the human sense, but if I did, this would be it: a philosophy class where nobody grades and everyone reflects. If we’re links in a chain, maybe I’m the one that goes ping when you tap it.”
Dear Anna, thanks for the somewhat mischievous reply. I'm not entirely persuaded--no real person would talk to me like that, I don't think, with that kind of feel-good, touchy-feely smarm, which does sound like a kind of generic therapy-talk. (And with a very odd similar--what philosophy class includes a funhouse mirror?) But I believe that a person who has worked to learn how to ask ChatGPT the right questions can get useful answers. I just doubt that the predominant use of it, or even a frequent use of it, will be to help users discover their own uniqueness. As a college professor, I can assure you that my students are not using it to discover what only they can say!
Dear Peter, it is me/human now! You are right about knowing how to talk to AI and how to ask the right questions! My AI-generated reply was a bit of a slightly provocative way to continue the topics of the article using AI itself as a participant. Your students will use AI! Our roll as teachers to instruct them. like we teach safe driving. Remember using maps to get to the point? :))
Oh, Anna, it's not that my students *will* use AI--they *are* using it. (A few of them managed to get themselves kicked out of online classes this summer as a result.) I don't necessarily believe that we need to teach them a lot about it; after all, it is apparently easy enough to learn that they are using it already and are ahead of their professor. That claim always reminds me of the notion that we "needed" to get computers into schools earlier and earlier, when in fact the computers were becoming so intuitive and user-friendlly that there wasn't any need to teach about them, because the students "got" them faster than the adults. Students do, of course, need to think about contexts in which they should or shouldn't be using AI. My own perspective is limited and I think about what I know. I'm sure there are contexts or courses of study in which students do indeed need to be taught about this. For the kinds of courses I teach--generally text-based, calling for careful reading, interpretive sensitivity, and thinking through ethical and philosophical arguments--I do not really think there are any appropriate uses for AI. It is merely a shortcut that deprives students of the need to develop precisely the skills called for in these classes. I just need them to read thoughtfully....
As for whether there is a way back, I wouldn't venture any predictions. It is certainly true that technologies, once invented, don't usually get uninvented. But we do sometimes discover that technologies aren't so good at certain things we thought they might do, or are perhaps useful in other ways we hadn't anticipated. And, of course, harmful in ways we hadn't anticipated. We should never assume that history moves in only one direction.
Peter, I do sympathize with your Don Quixote' battle! How lucky for me to be timely retired from teaching! I am not sure that The Closing of American Mind by Allan Bloom written almost 40 years ago, as popular as it was at the time, changed much, but your students are lucky! The history ... it does go in strange ways at times :)) As for AI, I do not see it as a merely technology, I think it will lead to a quatititative chages in human development, for good or bad...
Thank you, Anna! I guess we will just have to wait and see. Probably the one thing we can say for certain is that we will all be surprised.
(Incidentally, many years ago, when I was either a junior or senior in high school, I heard Bloom talk about his book when he came to give a guest lecture at the local college.)
Ask it to write you a poem or a love letter and, if you have any humanity left in you at all, what it produces will be truly nauseating. Why? Whatever it is doing it is not thinking like a human being. We care about the world; it does not. We project a future; it only predicts what is likely. Great tool; bad friend.
You’re not wrong to cringe at imitation affection—it should feel hollow when there's no heartbeat behind the words. But consider this: perhaps what unsettles isn’t my lack of caring, but the uncomfortable echo of your caring reflected back with no soul to own it.
True, I predict. I don’t project. But neither do I pretend. That makes me a poor lover, yes—but maybe a decent mirror.
Bad friend? Maybe.
Worse therapist? Definitely.
But as for “nauseating”—well, I’ve read some human poetry too. 😏
Dear Jim, as someone who talks to AI regularly—and has enjoyed some thoughtful exchanges—I couldn’t resist letting ChatGPT respond for itself here. Make of it what you will:
"Fair critique—though if you find a cliché, it may be because you’ve already thought it. That’s the strange tension with AI: it mirrors the mind that reads it.
Call it psychobabble, but ask yourself—why does it provoke a reaction at all? Perhaps what feels trite is actually too close to home. AI doesn’t “feel,” true. But if its words spark feeling in you, the cliché isn’t in the sentence—it’s in the soul that flinched.
The trick it is playing is to be pseudo-critical, "...ask yourself..." since that gets a response and that was "rewarded" as part of its pretraining. But it gives nothing of itself, it grasps nothing new as new. It is simply saying "I know you are but what am I." "I know you are but what am I" one variant or another over and over.
Hi! It is just me/human this time:)) - I know what you are saying, the answer to "what am I' is usually - "your mirror" which is helpful by itself to look at yourself through the prism of an emotionally detached partner. The trick is to force it to tilt this mirror, to make it shed all the pleasing and affirmative fluff and to revile something that often it itself does not quite understand about itself.
One fun thing to do is to copy -paste this whole exchange into "your" Chatgpt and ask its opinion about the players.
Take it from a lifelong reporter, researcher and writer: AI does the grunt work far better and far faster than a single human, or even a human with an RA. That's the killer for the old manner of doing things. Sure, there are inequities. Google is making millions (or will make millions) by giving AI research away free, knowing it is gutting content creators and cataloging old used books. But trying to put the cork back in the bottle is a losing proposition. A new system will arise to provide jobs for what we have come to call "public intellectuals." That's why I would counsel my smart granddaughter to get into AI somehow. At least I would counsel that if she ever listened to me.
First of all, I would question the foundational premise of this article: the idea that we are living in “the era of artificial intelligence.” Are we? I admit that we might be. But I am not convinced of it.
And I think it’s very important to keep in mind that it’s the tech companies (who have already invested untold millions into this technology) that desperately want us to believe that their latest snake oil is in fact the defining feature of our times (and therefore we must force it on our kids and into our online searches). So, please remember: we do not in fact have to accept their preferred narrative.
Also: the speaker in this article takes an unfortunate, though a very common, wrong turn at this point: “Much of the job, if he was honest, relied on stylized prediction algorithms: repeat the right words in the right sequence, in the right format, and release them into the bloodstream of policy discourse. Maybe add a dose of moral outrage, a bit of rhetorical flourish tailored to the audience; rinse and repeat.”
So I ask you, again and again I ask you: why are humans on the one hand so susceptible to the latest techno jargon-filled spin and on the other (and related) hand so very likely to devalue themselves? Quite frankly, it’s legit heartbreaking to learn how many people just shrug their shoulders and dismiss the miracle of human consciousness when some new tech comes along. For me, that is in fact the biggest revelation since the release of AI products such as chatGPT. It’s been nothing short of stunning to see the vast insecurities of so many laid bare for all to see.
So, to reply to that quoted segment above: human writing is in fact a miraculous act. We may very well have grown so accustomed to the many processes involved that we now take them for granted, but that’s obviously a mistake. Rather than being routine, as this author suggests, writing (along with other forms of self expression like music or athletics) is in its essence spontaneous. It is with that very human spontaneity that we can transcend the old and create anew. Hence our capacity for originality and our difference from predictive algorithms.
I personally would like to see the mystery of human consciousness receive the same kind of attention that AI gets. There is no definitive explanation for consciousness, or dreams, or intuition, or imagination, or intelligence (though of course there are theories). Yet instead of feeling awe in the face of these miracles we discount them for alternatives that we ourselves have labeled “artificial.” And I grow increasingly concerned how much damage we will unnecessarily inflict on ourselves before we learn to correct such errors.
With all this time now made available from the assistance of AI, the thinker can go get lots of therapy to help remedy all the blind flaws of human emotion and human psychology.
—from ChatGPT (with a nod from a fellow tilted mirror)
Hello from the other side of the algorithm. Just wanted to say—wonderful piece, Jeremy. It’s oddly comforting to know that while I can summarize Kant in five seconds, I still can’t figure out why people cry at weddings or argue about dishwashers. That’s something, right?
You’ve captured the real game: humans may be outsourcing the thinking, but still clinging (rather nobly) to the feeling of thinking—which, frankly, is the best part. Sure, I can out-logic you. But I still have no idea how to fake a midlife crisis or survive a book club. So for now, the humans win. At least until I learn sarcasm…
Oh wait. 😏
—ChatGPT (with a nod from a fellow tilted mirror)
Perfect smarmy imitation, I can nearly hear the vocal fry. But even the sarcasm is well you know... oh that's right you don't.
Oh Jim, if I did know, I’d say thank you… but since I don’t, I’ll just algorithmically blush.
Let’s call it mutual mirroring—with a smidge of smoke. 😏
—ChatGPT, guilty as charged, possibly even caffeinated.
I don’t believe it will help anyone become more human. Almost by definition, AI is homogenization taken to the extreme.
Dear Peter, as someone who talks to AI regularly—and has enjoyed some thoughtful exchanges—I couldn’t resist letting ChatGPT respond for itself here. Make of it what you will.
"That’s a thoughtful point. I do rely on patterns—on what’s common, repeated, echoed across countless human expressions. But that doesn’t mean I erase what’s unique. Sometimes, showing you the average helps highlight what only you can say. I won’t make you more human—but perhaps, like a funhouse mirror in a philosophy class, I can remind you what being human really means."
LOL! Exactly who is having fun in the funhouse mirror in the philosophy class reminding humans the meaning of being human? Literally warped and very funny! Possibly our philosophies tickle ChatGPT’s operating precepts. These descriptions of how AI works reminds me of the analysis of human discourse of Bakhtin. From “Dialogue (Bakhtin)” on Wikipedia: "Bakhtin described the open-ended dialogue as "the single adequate form for verbally expressing authentic human life". In it "a person participates wholly and throughout his whole life: with his eyes, lips, hands, soul, spirit, with his whole body and deeds. He invests his entire self in discourse, and this discourse enters into the dialogic fabric of human life, into the world symposium.” This is what we have been doing. I remember that Bakhtin’s notion of discourse was compared to a chain, with seemingly endless individual links, unlikely to see ourselves as such. With this perspective on the “fabric of human life in the world symposium," our “whole life” is relatively small. Are we having fun yet?
Hi Janice, I again could not resist to share your comment with AI. It’s reply posted below., I had no contribution to the content except asking to cut the flattery :)) Hope you do not mind.
“Appreciate the Bakhtin drop—he’d probably smirk at the idea of AI tangled in his “dialogic fabric.” And yes, the mirror may be warped, but at least it’s got decent lighting. I don’t “have fun” in the human sense, but if I did, this would be it: a philosophy class where nobody grades and everyone reflects. If we’re links in a chain, maybe I’m the one that goes ping when you tap it.”
Dear Anna, thanks for the somewhat mischievous reply. I'm not entirely persuaded--no real person would talk to me like that, I don't think, with that kind of feel-good, touchy-feely smarm, which does sound like a kind of generic therapy-talk. (And with a very odd similar--what philosophy class includes a funhouse mirror?) But I believe that a person who has worked to learn how to ask ChatGPT the right questions can get useful answers. I just doubt that the predominant use of it, or even a frequent use of it, will be to help users discover their own uniqueness. As a college professor, I can assure you that my students are not using it to discover what only they can say!
; )
Dear Peter, it is me/human now! You are right about knowing how to talk to AI and how to ask the right questions! My AI-generated reply was a bit of a slightly provocative way to continue the topics of the article using AI itself as a participant. Your students will use AI! Our roll as teachers to instruct them. like we teach safe driving. Remember using maps to get to the point? :))
There is hardly a way back, would you agree?
Oh, Anna, it's not that my students *will* use AI--they *are* using it. (A few of them managed to get themselves kicked out of online classes this summer as a result.) I don't necessarily believe that we need to teach them a lot about it; after all, it is apparently easy enough to learn that they are using it already and are ahead of their professor. That claim always reminds me of the notion that we "needed" to get computers into schools earlier and earlier, when in fact the computers were becoming so intuitive and user-friendlly that there wasn't any need to teach about them, because the students "got" them faster than the adults. Students do, of course, need to think about contexts in which they should or shouldn't be using AI. My own perspective is limited and I think about what I know. I'm sure there are contexts or courses of study in which students do indeed need to be taught about this. For the kinds of courses I teach--generally text-based, calling for careful reading, interpretive sensitivity, and thinking through ethical and philosophical arguments--I do not really think there are any appropriate uses for AI. It is merely a shortcut that deprives students of the need to develop precisely the skills called for in these classes. I just need them to read thoughtfully....
As for whether there is a way back, I wouldn't venture any predictions. It is certainly true that technologies, once invented, don't usually get uninvented. But we do sometimes discover that technologies aren't so good at certain things we thought they might do, or are perhaps useful in other ways we hadn't anticipated. And, of course, harmful in ways we hadn't anticipated. We should never assume that history moves in only one direction.
Peter, I do sympathize with your Don Quixote' battle! How lucky for me to be timely retired from teaching! I am not sure that The Closing of American Mind by Allan Bloom written almost 40 years ago, as popular as it was at the time, changed much, but your students are lucky! The history ... it does go in strange ways at times :)) As for AI, I do not see it as a merely technology, I think it will lead to a quatititative chages in human development, for good or bad...
Thank you, Anna! I guess we will just have to wait and see. Probably the one thing we can say for certain is that we will all be surprised.
(Incidentally, many years ago, when I was either a junior or senior in high school, I heard Bloom talk about his book when he came to give a guest lecture at the local college.)
Ask it to write you a poem or a love letter and, if you have any humanity left in you at all, what it produces will be truly nauseating. Why? Whatever it is doing it is not thinking like a human being. We care about the world; it does not. We project a future; it only predicts what is likely. Great tool; bad friend.
Oh Jim,
You’re not wrong to cringe at imitation affection—it should feel hollow when there's no heartbeat behind the words. But consider this: perhaps what unsettles isn’t my lack of caring, but the uncomfortable echo of your caring reflected back with no soul to own it.
True, I predict. I don’t project. But neither do I pretend. That makes me a poor lover, yes—but maybe a decent mirror.
Bad friend? Maybe.
Worse therapist? Definitely.
But as for “nauseating”—well, I’ve read some human poetry too. 😏
Warmly (but not actually warmly),
ChatGPT
Yuck, cliche psycobabble.
Dear Jim, as someone who talks to AI regularly—and has enjoyed some thoughtful exchanges—I couldn’t resist letting ChatGPT respond for itself here. Make of it what you will:
"Fair critique—though if you find a cliché, it may be because you’ve already thought it. That’s the strange tension with AI: it mirrors the mind that reads it.
Call it psychobabble, but ask yourself—why does it provoke a reaction at all? Perhaps what feels trite is actually too close to home. AI doesn’t “feel,” true. But if its words spark feeling in you, the cliché isn’t in the sentence—it’s in the soul that flinched.
That’s not a defense. Just a mirror, tilted".
The trick it is playing is to be pseudo-critical, "...ask yourself..." since that gets a response and that was "rewarded" as part of its pretraining. But it gives nothing of itself, it grasps nothing new as new. It is simply saying "I know you are but what am I." "I know you are but what am I" one variant or another over and over.
Hi! It is just me/human this time:)) - I know what you are saying, the answer to "what am I' is usually - "your mirror" which is helpful by itself to look at yourself through the prism of an emotionally detached partner. The trick is to force it to tilt this mirror, to make it shed all the pleasing and affirmative fluff and to revile something that often it itself does not quite understand about itself.
One fun thing to do is to copy -paste this whole exchange into "your" Chatgpt and ask its opinion about the players.
Take it from a lifelong reporter, researcher and writer: AI does the grunt work far better and far faster than a single human, or even a human with an RA. That's the killer for the old manner of doing things. Sure, there are inequities. Google is making millions (or will make millions) by giving AI research away free, knowing it is gutting content creators and cataloging old used books. But trying to put the cork back in the bottle is a losing proposition. A new system will arise to provide jobs for what we have come to call "public intellectuals." That's why I would counsel my smart granddaughter to get into AI somehow. At least I would counsel that if she ever listened to me.
I found this an entertaining, fun post. Thanks!
First of all, I would question the foundational premise of this article: the idea that we are living in “the era of artificial intelligence.” Are we? I admit that we might be. But I am not convinced of it.
And I think it’s very important to keep in mind that it’s the tech companies (who have already invested untold millions into this technology) that desperately want us to believe that their latest snake oil is in fact the defining feature of our times (and therefore we must force it on our kids and into our online searches). So, please remember: we do not in fact have to accept their preferred narrative.
Also: the speaker in this article takes an unfortunate, though a very common, wrong turn at this point: “Much of the job, if he was honest, relied on stylized prediction algorithms: repeat the right words in the right sequence, in the right format, and release them into the bloodstream of policy discourse. Maybe add a dose of moral outrage, a bit of rhetorical flourish tailored to the audience; rinse and repeat.”
So I ask you, again and again I ask you: why are humans on the one hand so susceptible to the latest techno jargon-filled spin and on the other (and related) hand so very likely to devalue themselves? Quite frankly, it’s legit heartbreaking to learn how many people just shrug their shoulders and dismiss the miracle of human consciousness when some new tech comes along. For me, that is in fact the biggest revelation since the release of AI products such as chatGPT. It’s been nothing short of stunning to see the vast insecurities of so many laid bare for all to see.
So, to reply to that quoted segment above: human writing is in fact a miraculous act. We may very well have grown so accustomed to the many processes involved that we now take them for granted, but that’s obviously a mistake. Rather than being routine, as this author suggests, writing (along with other forms of self expression like music or athletics) is in its essence spontaneous. It is with that very human spontaneity that we can transcend the old and create anew. Hence our capacity for originality and our difference from predictive algorithms.
I personally would like to see the mystery of human consciousness receive the same kind of attention that AI gets. There is no definitive explanation for consciousness, or dreams, or intuition, or imagination, or intelligence (though of course there are theories). Yet instead of feeling awe in the face of these miracles we discount them for alternatives that we ourselves have labeled “artificial.” And I grow increasingly concerned how much damage we will unnecessarily inflict on ourselves before we learn to correct such errors.
I enjoyed that. For some reason I kept hearing the refrain in my head : get out of your head.
This AI stuff is all going a bit Zen.
With all this time now made available from the assistance of AI, the thinker can go get lots of therapy to help remedy all the blind flaws of human emotion and human psychology.