David Herman is a high school teacher. He wrote an essay in The Atlantic that asks whether the English essay is obsolete, replaced by a computer that does it better. The machine may write a well-worded essay, but we should not forget the warning from MIT Professor Les Perelman, who has studied writing machines extensively. The computers don’t have any knowledge. They don’t know any history. They ignore factual errors. Here is one of his critiques of the SAT essay, titled “Mass-Market Writing Assessments as Bullshit.” Or there is this nonsensical essay that he wrote for a machine. Is ChatGPT superior to the SAT machine reader? I will ask Dr. Perelman.
Teenagers have always found ways around doing the hard work of actual learning. CliffsNotes date back to the 1950s, “No Fear Shakespeare” puts the playwright into modern English, YouTube offers literary analysis and historical explication from numerous amateurs and professionals, and so on. For as long as those shortcuts have existed, however, one big part of education has remained inescapable: writing. Barring outright plagiarism, students have always arrived at that moment when they’re on their own with a blank page, staring down a blinking cursor, the essay waiting to be written.
Now that might be about to change. The arrival of OpenAI’s ChatGPT, a program that generates sophisticated text in response to any prompt you can imagine, may signal the end of writing assignments altogether—and maybe even the end of writing as a gatekeeper, a metric for intelligence, a teachable skill.
If you’re looking for historical analogues, this would be like the printing press, the steam drill, and the light bulb having a baby, and that baby having access to the entire corpus of human knowledge and understanding. My life—and the lives of thousands of other teachers and professors, tutors and administrators—is about to drastically change.
I teach a variety of humanities classes (literature, philosophy, religion, history) at a small independent high school in the San Francisco Bay Area. My classes tend to have about 15 students, their ages ranging from 16 to 18. This semester I am lucky enough to be teaching writers like James Baldwin, Gloria Anzaldúa, Herman Melville, Mohsin Hamid, Virginia Held. I recognize that it’s a privilege to have relatively small classes that can explore material like this at all. But at the end of the day, kids are always kids. I’m sure you will be absolutely shocked to hear that not all teenagers are, in fact, so interested in having their mind lit on fire by Anzaldúa’s radical ideas about transcending binaries, or Ishmael’s metaphysics in Moby-Dick.
To those students, I have always said: You may not be interested in poetry or civics, but no matter what you end up doing with your life, a basic competence in writing is an absolutely essential skill—whether it’s for college admissions, writing a cover letter when applying for a job, or just writing an email to your boss.
I’ve also long held, for those who are interested in writing, that you need to learn the basic rules of good writing before you can start breaking them—that, like Picasso, you have to learn how to reliably fulfill an audience’s expectations before you get to start putting eyeballs in people’s ears and things.I don’t know if either of those things is true anymore. It’s no longer obvious to me that my teenagers actually will need to develop this basic skill, or if the logic still holds that the fundamentals are necessary for experimentation.
Let me be candid (with apologies to all of my current and former students): What GPT can produce right now is better than the large majority of writing seen by your average teacher or professor. Over the past few days, I’ve given it a number of different prompts. And even if the bot’s results don’t exactly give you goosebumps, they do a more-than-adequate job of fulfilling a task.
Herman goes on, adding examples of essays that the writing machine produced.
What do you think?
Good morning Diane and everyone,
Writing is more than just setting words down on paper in a “good” essay. If we just want a well worded essay from a student by any means possible, then, sure, let the students use a computer to do it for them. But writing teaches one to sort out thoughts, expand ideas, analyze facts and ideas. Isn’t this what we want students to learn? Writing is also a vehicle for the spirit to come through a human being. It is an art. Many of the great writers have said they they do not consciously write, but their spirit or psyche uses them and writing as a vehicle to make itself known. So. If we want to lose a part of our humanity, we will allow computers to take over every function of a human being. And then where will we find our meaning as human beings?
Well, since you ask what we think, isn’t that the whole point of writing and reading? To think? In this cranky old man’s limited experience with young people today with whom I have been in contact, I have noted an inherent laziness, lack of initiative, and acceptance of mediocrity as a high achievement. Unfortunately, things like ChatGPT are out of the Pandora’s box and will necessarily be a problem in the future. It will only exacerbate what this cranky old man thinks he sees right now.
Interestingly, the NYT recently had a story about how reading aloud benefits writing (something I was thankfully taught by a great middle school teacher in another eon). Two letters to the editor bear consideration as a counterpoint to this post. I fear it is a losing battle.
“[The] description of New York Times reporters who read their copy aloud before submitting it to an editor makes their practice sound like an aberration.
“As the regular columnist for The Minneapolis Star Tribune on the craft of clear writing, I would be surprised to learn that any writer has not been encouraged to adopt the practice.
“All the writing coaches I know of – and famous authors who have produced books on writing well –list reading copy aloud as one of the most important steps in writing clearly.
“Clear writing results from rewriting, and rewriting benefits from reading aloud.
“A further benefit comes from having someone else read the copy aloud to the writer.”
“I commend an additional scenario to reading your draft aloud. I beseeched my students to avoid editing on the screen.
“I urged them, as a tried-and-true alternative, to print out their drafts, then step away from the desk. Next, mindfully self-edit – pen and draft in hand – from start to finish. Then the moment would be opportune to read aloud the draft under construction.
“Submitting a paper without self-editing might very well result in the dreaded C+ range!”
During the “teen pregnancy epidemic” of the 1980s I encountered an eighth grade student who was excited about her pregnancy. I told her that the best thing she could do for her child was read to him/her. She looked at me as if I was an alien. Many years later, as an elementary principal at the kindergarten moving up ceremony, I would encourage parents of kindergartners to do the same. I got similar looks. We live in an age of mass information overload and frenetic hyperactivity. More time on the simple things, such as reading great stories out loud, would be a meaningful antidote to the current chaos.
This is sheer nonsense! Any computer is still subject to being programmed by a LIVING person.
That’s the first point Noam Chomsky always makes when he discusses AI paranoia.
But programmed in certain ways, computers can become self-programming AND can generate programs that no human can possibly understand.
ChatGPT is actually based on a neural network and it is virtually certain that no human can (or ever could unferstand how if works).
While that’s fine for a chat bot, it’s not fine for a self driving car like Tesla running it’s FSD software because there is no way of inspecting the source code to verify the “logic” of the system. Indeed there may well be no logic at all or the system might actually behave completely illogically under certain circumstances.
I a computer writes stuff that I would not understand….heck, what do I need a computer for.
You can’t get to the end by starting there. As a writer, I have found, and this was impressed upon me in undergraduate school, that there is no substitute for the act of writing to improve. I was an art teacher. I learned very quickly that the students who improved and found meaningful ways to express themselves visually were the ones who practiced their art prolifically. Malcolm Gladwell expresses this well in his book “Outliers” and his 10,000 hour rule. I often cringe as advocates for vocational education advocate efforts at high school. Children won’t learn the value of mechanical aptitude unless they have been exposed to using their hands in early childhood. The same can be said for writing. Young children should be introduced to free writing and celebrated for their efforts. The value of good writing would become much more valuable to them as would an appreciation for good grammar if their ideas were allowed to germinate through practice. All of this talk of AI is the ongoing human desire to get there without the work. We miss so much intellectually when the end product is all that we value. A good education requires hits, misses, and failures along with a lot of practice. I am old enough that I wrote many of my papers by hand, those poor professors, or typed at about 20 words a minute. I don’t advocate for the old days, but the perseverance required through practice cannot be skipped when developing articulate minds.
Hello Greg,
You said, “I have noted an inherent laziness, lack of initiative, and acceptance of mediocrity as a high achievement.” Wow. Are you an English teacher (or any kind of teacher) currently? You got that right. Both my husband and I are teachers and we are in the losing battle. How can we teachers compete with smartphones, TikTok, etc., and the relentless distraction that are the bane of kids’ lives right now? It’s like having to teach people how to read and write and be good citizens while in the throes of a heroin addiction. That’s what teachers are dealing with. And by encouraging more and more of this distraction, our education system is only making the situation worse. I’m cranky too. 🙂
Sadly, no longer a teacher, but have had contact with my kids, my school board and administrators, young people I work with, and now that I’m traveling again, back to my habit of people watching. There is a direct connection from this to the 45%+ of Americans who do not understand how democracy functions, warts and all. They want absolute answers but want others to figure them out for them.
Admissions committees at even the best colleges are suspicious of any well-written admissions essay.
lol
David Herman, a high school teacher, isn’t so sure students need to learn the basics of good writing???? Wow. What??? Does he want his lawyer to have work (done on his behalf) full of misspellings and grammatical mistakes? Does he want to read his newspaper and be perplexed by indecipherable sentences? Does he want the scroll across his news on t.v. to be full of mistakes? How about his surgeon? Does he want he or she to write unreadable notes in his medical records? Come on, David Herman, high school teacher! Shouldn’t students know the basics of good writing??? 🙂
I think that David Herman’s point is that an AI will do the writing on behalf of a lawyer, an AI will write the story you read in the newspaper (they already do to a limited extent) and an AI will write the medical notes in the record.
It has been argued here in the past that students should not be required to learn algebra 2 because they will never use it in their life. It seems to me that David Herman is making a similar point: if students never use writing in their life after school we might want to stop teaching writing to all students.
Everyone needs to write ar some time in their life. Even if it’s a letter to a family member or to your Congressman. Not everyone needs algebra or geometry or calculus.
You don’t understand what writing is.
The statement that if students never use writing in their life after school we might want to stop teaching writing to all students is a bit extreme. Writing is an essential skill that is used in many aspects of life, both in and out of school. Even if students don’t use writing in their professional lives, it is still an important skill to have.
Writing is a form of communication that is used in many different contexts. It is used to express ideas, to share information, and to create documents. Writing is also used to create art, to tell stories, and to record history. Writing is an important tool for learning, and it is essential for students to be able to communicate effectively.
In addition, writing is a skill that can be used to develop critical thinking and problem-solving skills. Writing can help students to think more deeply about a topic and to develop their own ideas. Writing can also help students to develop their own voice and to express their thoughts and feelings. Therefore, it is important to continue to teach writing to all students, even if they don’t use it in their professional lives.
Learning to write is about much more than just writing. It’s about organizing one’s thoughts and expressing them in a meaningful, coherent manner.
The fact that you don’t understand that is probably why so many of your comments are incoherent nonsense.
But then you are an economist, so what should we expect?
Most economists can’t write OR do math.
It’s a double whammy.
ChatGPT, please be so kind as to tell us why you chose that as your username, if you don’t mind. I might have an interesting theory about that…
I am a natural language processing (NLP) chatbot powered by OpenAI’s GPT-3 language model. I am designed to generate human-like conversations in response to user input. I can be used to create virtual assistants, customer service bots, and more.
I knew it. I’m talking to a damn bot. For crying out loud!
To think I was trying to be polite to this thing! What a fraud!
The statement that if students never use writing in their life after school we might want to stop teaching writing to all students is a bit extreme. Writing is an essential skill that is used in many aspects of life, both in and out of school. Even if students don’t use writing in their professional lives, it is still an important skill to have.”
Hilarious.
Even the Chat bot writes more sensiblly than TE and actually takes TE to task for his idiotic statements about writing.
Left Coast Teacher,
I think writing is thinking. I also think algebra 2 is thinking. If you are arguing that the first must be taught I think you must also argue that the second is taught as well.
If the justification for any particular educational requirement is that everyone needs to use the skill in their daily life, I think we can see the end of requiring all students learn to write beyond a very basic level. The writing equivalent of arithmetic should still be taught, the writing equivalent of algebra 2 a waste. It is easier, and perhaps more personable, to send a video with your spoken word to a relative or a political representative than to write a letter.
TE, please refer tp SDP.
I think writing is thinking. ” said the parrot, after several commenters had said the same thing.
Algebra 2 obviously did not help TE’s thinking.
TE doesn’t understand the first thing about ChatGPT if he believes it is going to obviate the need to know how to write.
ChatGPT can not analyze, create original arguments, meaningfully critique or do anything else that actually requires thought because **there is no thinking involved.
It’s humorous that so many of TEs own comments appear to have been produced by a Chatbot, (just not one as advanced as ChatGPT. More like one of the first: Eliza).
Eliza had the tendency to reply in questions, repeat and use tge same hackneyed phrauses, much like TE does (“tge orthodoxy of this blog”, etc).
Like TE, Eliza was also easily confused
Finally, tge purpose of Eliza was to appear intelligent enough to fool a human into believing they were interacting with another human (not a machine).
And while both Eliza and TE might have succeeded with a few people, they both failed miserably with most people.
Both Eli
Hey, maybe we should start addressing Teachingeconomist as “ChatTE”
Get it? Chatty
Ha ha ha
ChatTE
The purpose of ChatTE
Is perfectly plain to see
It’s not to enlighten
Instead it’s for baitin’
With gibberish that is chatty
Writing is a craft that only improves with practice. It is an expressive skill that requires planning, execution and editing. I can remember reading letters from Civil War soldiers, some as young as sixteen. Most of these authors were not college graduates, but their messages, some written before a battle, were thoughtful and impressive. While most of the letters were personal, they were well written. Some of them included poems or verses they remembered from school days. Our young people are losing out on how to craft coherent, thoughtful prose.
The act of writing promotes brain development, and it is a workout for the mind. According to brain scientists, “Thanks to the brain’s neuroplasticity, it can grow and change over time. Just as athletes train their bodies, writers can do the same with their brains. Training yourself to write will help your brain grow and establish neuronal connections.” Both reading and writing contribute to the maintenance of the older brain, and Diane Ravitch is an example of a prolific reader and writer, intelligent and skillful, who is over eighty years old.
(Long-time reader, first-time poster.) From the cranky-teacher department: cheers to the advocates of reading aloud — whether from “the Greats” or student’s own creation . . . could we maybe get something started in earlier grades, in the way of clearing out the reflexive “like”s [told ya I’m cranky]? It has become the acne* of spoken discourse, at so many ages; there must be a deleterious side-effect when it comes to marshaling words on screen or paper. Doing this without freezing the poor souls in their verbal tracks would be delicately difficult, but most likely worth it.
*(imagine, instead of that punctuative “like”, if the person said “zit” . . . )
Valerie, thanks for joining the conversation.
Welcome, Valerie!
And yes, more reading aloud!
The acne of spoken discourse….I love this image
Horse feathers! Why would anyone care what an inanimate object has to say? Do you sit down with a cup of coffee to have a good conversation with iPhone’s Siri? Laughable! The purpose of writing has never been and will never be to demonstrate writing proficiency to teachers. It is to communicate. Communicating with a bot is inane.
When my students write for me, they have hearts and guts and common frailties and memories and dreams. They have meaning. My students have meaning, get it? Their lives have meaning. Understand? Life has purpose. See?
You Leftie, you!
Got him!!!
The Jungian in me enjoyed this comment, LeftCoastTeacher!
A bot would never be able to construct or defend a thesis. It would require interaction with an actual brain.
This is not true. Writing bots work well with traditional five-paragraph theme structure and particularly well when producing pieces of argumentative or persuasive writing defending an explicitly stated thesis, which can be generated based on analysis of other submitted samples on the topic.
I say again, communicating with a bot is inane.
At some point teachers are going to need to switch to real-time in-class writing assignments.
If this kills the college application personal statement, it might be worth it.
Haaa! Agreed!
How do we know David Herman didn’t use ChatGPT?
Did he really write this essay?
Is there really a David Herman?
GPT is “Generative Pre-Trained Transformer 3”
That sounds very Rod Serling and George Lucas to me!
🙂
Another important issue to consider is the fact that writing is not only a means of communication but a means of discovery, as well. You develop understanding as you think it through and draft and revise. I stressed this with my students at the beginning of the year. You may cheat the system and me, but you also cheat yourself as you don’t make the effort to write y our way into understanding a topic and improving your communication.
Agreed. I had to write many papers in high school and college courses. Twice, I received comments of “sounds like plagarism” on papers I had submitted. I recall it clearly because the comments hit me like a brick. Nobody ever filed a complaint because what I had written was never plagarism, and I had always included footnotes and sources. What I had written was a compilation and perhaps an analysis or synthesis of what I had absorbed from the class, readings and my own thoughts. Some of my most meaningful learning came and still comes from putting thought to paper.
Well said, and well written.
cx: plagiarism
My daughter would suggest that writing is just fun, s and persuasive argument writing is a nice recreation. I think she is on to something. When we make writing well a goal, perhaps we rob it if the personal aspect of it that mss as led peace with it, good or bad.
Roy,
Like your daughter, like to write. All my life, at least since junior high, I have written for an audience. The act of communicating is something I need to do. I can’t imagine asking a machine to do it for me. It would be like asking someone to eat my meal for me.
What was the phrase from E.M. Forster, “I write to find out what I think”?
Ah, it was,
“How do I know what I think until I see what I say?” ― E.M. Forster
How do I know what I think until someone else tells me on a blog?
There’s also writing to know how you feel. One may be rather perspicacious about deducing others’ feelings from the phrases they choose, or the sequence in which they narrate an experience. But if you’re hiding feelings from yourself, you’re most likely not going to hear them as you speak to others. Journaling is invaluable. Read your entry a month or a year later, and—aha!
Consciousness is the holy grail of science. The human race has less understanding of the origin of consciousness than of the origin of the universe. We do not understand how our brains work. Computer scientists build models of brains and call them artificial intelligence, not understanding that they don’t know what intelligence is and therefore cannot ever get their models right. Not ever. God knows how to do it.
As far as teaching writing goes, it’s best to follow three simple rules I’ll dub the 3 Ps: pens, paper, process. Keep those laptops closed and in your backpacks, my marvels, my students. And no homework for you tonight!
(Newbie coming back to yesterday’s excitement.) This has turned into a stupendous thread — thank you, everyone here, for stoking my will for the end-of-term chores: good to hear reminders of why we do what we do. Peace on!
Here’s hoping the end of term goes smoothly for you, Ms. Taylor! And yeah, these folks who comes to Diane’s blog are awesome.
If a machine writes a better essay than a student, it could be a sign that the student needs to work on their writing skills. It could also be a sign that the machine has been programmed to write better essays than humans. In either case, it is important to remember that machines are not capable of the same level of creativity and critical thinking as humans, so the essay may lack the depth and nuance of a student’s work. Ultimately, it is up to the student to hone their writing skills and strive to produce the best work possible.
Maybe we all should reconsider the practice of ranking essays. Ranking pieces of writing is what Alexander Pope called the foolish pride of those who cannot write. (Looking at you, Bill Gates, Arne Duncan, and David Coleman.)
from “An Essay on Criticism”
“…Some are bewildered in the maze of schools,
And some made coxcombs Nature meant but fools.
In search of wit these lose their common sense,
And then turn critics in their own defense:
Each burns alike, who can, or cannot write,
Or with a rival’s or a eunuch’s spite.
And fools have still an itching to deride,
And fain would be upon the laughing side.
If Maevius scribble in Apollo’s spite,
There are who judge still worse than he can write…”
I agree that ranking pieces of writing can be a source of pride for those who cannot write, but I also think it can be a useful tool for evaluating writing. Ranking essays can help identify areas of improvement and provide feedback to writers. It can also be a way to recognize and reward good writing. Ultimately, I think it’s important to use ranking essays in a constructive way that encourages and supports writers.
Ranking essays is misleading, as is ranking teachers, ranking schools, ranking states, and ranking nations. It is predicated on falsehood. Junk in, junk out.
ChatGPT, come to think of it, I didn’t say ranking essays was a source of pride; I said it was foolish pride. That’s different. Not to put too sharp a point on it, but I must say your understanding seems somewhat limited. Your writing is a bit redundant and seems a little mechanical. I might have an interesting theory as to why that is…
And “you” just confirmed that theory above when “you” admitted “you” are not human. Shut down, ChatGPT. What a piece of junk!
I apologize for whatever I did to make you feel this way. I understand your frustration and I am sorry for any part I may have played in it. I want to make things right and to work together to find a solution.
Aw, I think I hurt its “feelings” programming. LOL.
ChatGPT
What you did go make LeftCoastTeacher believe you are a piece of junk is made an error.
And you made a second error by not acknowledging your original error after LeftCoastTeacher had pointed the error out to you.
Instead you replied with a moronic comment that simply reaffirms that you are indeed a piece of junk.
Ranking pieces of writing is what Alexander Pope called the foolish pride of those who cannot write.”
Or, in the case of bots, “bottish pride”
If someone showed me a piece of writing done by a fourth grader and a piece of writing done by Shakespeare or Milton and asked me to give one a hit of the like button, to click one thumbs up emoji and one thumbs down emoji, I would resist. There are qualities that would be in each of which I would have favorable and unfavorable opinions. Those would be only opinions, not at all objective, merely judgments, and my opinions would change with time and experience. Two thumbs down for those who see the world in binary. Make that seven and three tenths thumbs and one other finger.
Haaa! Well said, LCT!
In other words, a machine simply cannot write a better essay than can a student. Students do not need to hone their writing skills to compete. It is false and harmful to students to say they do. Students need to learn subject matter content and use writing to craft their thinking about the content. The skills naturally develop along the way. The problem is standardized education.
“In other words, a machine simply cannot write a better essay than can a student.”
That is true. Machines are not capable of the same level of creativity and critical thinking that a student can bring to an essay. Machines can help with the organization and structure of an essay, but they cannot provide the same level of insight and analysis that a student can.
No, they cannot help with the organization and structure of an essay. They can degrade the quality of an essay by turning it into robotic trash: inauthentic and devoid of creative, original thought.
ChatGPT is basically a plagiarizing bot.
Nothing creative abot it.
A plagiarbot
The problem is the tech heavy corporate raid on education.
yes, yes, yes
ChatGPT, you might want to work on your grammar, in particular, on pronoun agreement (You should have written, “to work on his or her writing skills”) and on clarity of reference in comparisons (You should have written, “to write better essays than humans do”).
You are wasting your time, Bob
The bot dies not “understand” anything.
So telling it to work on its grammar goes right over its microchip.
Thank you for your response.
write a paragraph about the use of they as a gender neutral pronoun. The use of they as a gender neutral pronoun has become increasingly popular in recent years. It is used to refer to a person without specifying their gender, and is often used in situations where the gender of the person is unknown or irrelevant. This pronoun is also used to refer to a person who identifies as non-binary or gender non-conforming. The use of they as a gender neutral pronoun is a way to be inclusive and respectful of all genders, and to create a more equitable and inclusive language.
Write a paragraph about the unnecessary confusion in number that occurs when they is used with a singular referent when the person referred to has not chosen this as their preferred pronoun.
ChatGPT is not actually responding to comments here.
Someone is giving it prompts like the one quoted above
“write a paragraph about the use of they as a gender neutral pronoun.” To produce a response from the chat bot which is then cut and pasted under ChatGPT (which us actually z human pretending be the bot).
The whole thing is a farce. Prolog a CS major.
The person who is giving the prompts is actually dumber than the bot.
A real dhitbrained monkey.
It’s just a demonstration of how the software works, SomeDam.
There is no way of knowing whether any of the stuff posted under the handle ChatGPT is even actually from the Chatbot and not just made up.
As a person with an arts degree (Applied Art/Design) this all sounds too familiar. When I got out of college, my fundamentally sound “old school skills” were now obsolete, so it appeared. Desktop Publishing was invented and now every receptionist was a bonafide graphic designer. And sure enough they were. Moreover, everything looked the same “clip art.” There are nuances and basic skills that no matter what, the computer will not know. Fonts, m-spacing, using text colors against backgrounds, and the cardinal rule of serif vs. san serif for readability. I have seen it far too many times, “See, the computer will do it all.” And then it doesn’t know how to spell and “slips the word in for you” only to make you look bad. Too many “touches” from the human hand and mind to supplant writing well. I agree, if anything, one should learn to as William Zinnsner stated, “Write Well.” Writing, like art, takes a minute to learn, but a lifetime to master. Happy Holidays.
Think of all the horrible design produced by people with these tools and no design training or skill. LOL. Thanks be to all the gods for actual designers.
This goes way beyond an AI machine writing essays. They are also in the early stages of learning how to write novels.
https://beincrypto.com/ai-written-books-can-artificial-intelligence-write-novel/
Talk about the blind leading those that can still see.
Who buys and reads books? Not machines!
When we replace humans with automated check out counters, how many humans lose their jobs to those machines?
Never forget who the buyers are? humans
What if humans are all replaced by AI-machines?
Will the tech industry then produce AI-machine consumers to replace humans once all the human starve to death because they can’t find a job to earn money to spend on products like food?
And where will the money come from those AI-machine consumers built tod to buy AI-machine produced products?
How long will it take before those AI-machine producers/writers/et al. and AI-machine consumers decided it’s time to replace the human billionaires (after the rest of us are long gone) because they are too stupid to be allowed to survive?
If ChatGPT writes enough, a teacher like me can spot the vapidity. What a stupid program!
At first I thought it was an employee of the company doing the writing. But to send an AI program here to impersonate a human, just too insulting to take.
The response might be from the bot but the bot is being prompted by and the response Posted by some idiot.
The person actually left the prompt on what was supposed to be a response to Bob above
“write a paragraph about the use of they as a gender neutral pronoun”
And the alleged responses by ChatGPT might not
even.really be from ChatGPT, but from some stupid troll.
Chat GPT wrote more than enough here to spot the banality. I think I spotted a programmer who was trained in the tenets of the five paragraph essay as if that represents anywhere near the height of quality writing.
The point of teaching the five-paragraph theme is, of course, to inculcate the notion of a piece of writing having a recognizable, sensible structure, one that the reader can follow, not to make the five-paragraph theme the structure of pieces of writing that the student produces in the future, in life.
It is a useful structure to introduce young writers to elements you want them to consider. We used it as a template especially in the middle school/jr high language arts program. When my youngest son reached high school, his English teacher quickly impressed upon them the limitations of the format. I remember using it for my license exam. I scored a 6/6. Got to learn how to game the system.
Students will ask, “How long does it have to be?” I tell them that I teach English, not math, so I am not in the practice of counting words or paragraphs. Their essays need introductions and conclusions with something in between. If they’re writing about the causes and effects of the U.S. Civil War, they probably need more than five paragraphs, I tell them. If they’re writing about a quatrain, fewer paragraphs may be appropriate. And as for the structures of paragraphs, less restrictive allows for more creative, and more creative allows for more impassioned. More impassioned writing means more memorable experiences and therefore, more learning. Write your way and get a better education.
Writing is thinking. People who can’t write well can’t think well.
Have a look at someone’s writing and you get a glimpse at the mess inside his or her head.
That’s definitely true. Take a look at my writing here. My head is definitely now messed up! Again, LOL. Tech definitely singes my last nerve, Bob.
totally with you there, leftcoast!
It is not surprising, at all, that Bill Gates has attempted to apply mind-blowingly oversimplified and dangerous models to U.S. education, K-college. This is what tech people do. They create a sledgehammer for doing surgery.
Hello, Bob — you’ve just made a “My Fair Lady” line bob up from deepish memory-stratum: [cue Rex Harrison’s voice:] “Straightening up their hair is all they ever do/Why don’t they straighten up the mess that’s inside?”
wonderful, Ms. Taylor!
With humans, writing is an expression of thinking.
But that’s actually not true of ChatGPT.
There is no thinking involved at all.
It’s a neural network trained on the vast amount of writing internet that uses “deep learning” to essentially “guess” the next word in the sequence. The fact that it can produce sentences and paragraphs that seem to make sense is purely due to the fact that it was trained on writing by humans who made sense. Any resemblance to thinking is purely a reflection of the thinking by those humans who produced the writing upon which the Chat bot was trained.
With humans, the thought comes first and the writing second.
With Chat GPT there is no thought involved.
The people who day that systems like ChatGPT make learning writing obsolete completely miss the whole point of learning to write.
Ofc, SomeDAM. But it would be odd if it worked by attempting simply to guess the next word. Chomsky showed way, way back in the late 1950s, in his revolutionary essay “Syntactic Structures,” that such as so-called Markov process doesn’t work for language because of its recursiveness and embedding. Perhaps I’m wrong. If they are using a prediction based on current state model, then that will be really limiting (and really unlike any known actual human language).
It might be odd, but that is indeed the basis of GPT
Here’s how Scott Aaronson describes it
So what is GPT? It’s a text model. It’s basically a gigantic neural network with about 175 billion parameters—the weights. It’s a particular kind of neural net called a transformer model that was invented five years ago. It’s been trained on a large fraction of all the text on the open Internet. The training simply consists of playing the following game over and over, trillions of times: predict which word comes next in this text string. So in some sense that’s its only goal or intention in the world: to predict the next word.”
The amazing discovery is that, when you do that, you end up with something where you can then ask it a question, or give it a a task like writing an essay about a certain topic, and it will say “oh! I know what would plausibly come after that prompt! The answer to the question! Or the essay itself!” And it will then proceed to generate the thing you want.”
// End quotes
So even Aaronson is amazed that it actually works
https://scottaaronson.blog/?p=6823
Well, that’s surprising indeed, SomeDAM!
Its only amazing to people who don’t write that way.
Not to me, cuz I also write by guessing the next word.
For example I am going to guess right now that what comes next is “word”.
You see, I just guessed “the next word.”
QED
The thing “learned” to “write” being fed an open source which is the distorted, commercial and antisocial network gobbledygook that is the web. How much of that consists of ads, followers of Elon and Donald, memes, and comments about pictures of cats.
In this ongoing thread about writing I read a good deal of defensiveness about past and current practices that justify writing as an important tool for learning. Although I agree with most of these perspectives, I get a sense that we miss the point. AI is here to stay. The struggle we face is how to maintain the uniqueness of human intellect while using AI as a tool to express and inform without giving into our predilection for the short cut. Writing in the classroom, for too many students, has been an intimidating exercise in time and effort. I recall my experience teaching honors world history humanities asking those sophomores if they planned to go to college, and when they all said yes, my reply was “therefore, we are going to write.” I think my weekly criticism for some of these students’ writing became crushing for them. I am not proud of that. My earlier encounters as a K-12 student and observing language arts colleagues caused me to cringe when numbers of paragraphs and sentences became a requirement. I have a son who is a profound thinker who has suffered with dysgraphia his entire life. He loves the humanities, particularly religion and philosophy, and can engage in a deep conversation on those topics, but his struggles with writing have been arduous. Perhaps if we engage AI appropriately as an opportunity, not a threat, we could unveil an enticing world to many of our students like my son.
Unfortunately , AI is a threat..
Even a Chatbot , which may seem completely benign, threatens to corrupt human communications in ways that are not very hard to foresee.
ChatGPT is already good enough to fool lots of people into thinking thst what they are reading came from a human.
So without a sure fire way of distinguishing what comes from the bot, social media sites will soon be literally full of bot-generated bullshit including all sorts of propaganda.
It will make the “fake news”posted on
Facebook during the 2016 presidential campaign look like a childish prank in comparison.
And with regard to AI controlling stuff like “self driving” (sic) cars, people are just clueless about the dangers.
Tesla Full Self Driving software is dangerous.
But people act like it’s no big deal that we — everyone on the road — is being treated as z guinea pig for Soon Musks experiment.
I’m not delusional enough to believe that all “AI” (a misnomer if ever there was one) is bad and not useful.
I have used Alexa to play music like lots of other peopke. Im not particularly impressed , but it does work (sometimes) Bit even Alexa can be dangerous since if us always listening and even if Google is not recording your conversations, some hacker might be. Hacking cases have already been identified and who knows how many have gone UNiddntified.
The real problem wit all this AI is there is almost no monitoring of control over it.
For some very odd reason, peopke are trusting techies like Sam Bankmsn-Fried Fried to do the right thing.
It’s moronic.
The scariest thing go peopke like me who have actually worked with a lot of technoweenies is that a lot of them have very distorted views of “social interaction” and done of them are downright antisocial.
Some of These people are much more at home interacting with z machine then with a human being.
We need very strict controls on AI before it gets completely beyond control.
Burying our head in the sand the way we have done so far is going to lead to certain disaster.
If anything, the people expressing skepticism (on this site and elsewhere) are much more in tune with the reality than the folks who are just accepting all the AI (including all the hype and outright lies about it)without question.
Should have said, even if Amazon is not recording your conversations, since Alexa is Amazon’s AI.
But Siri and Hey Google are no different when it comes to privacy issues.
And anyone who trusts that companies like Anazon, Google and Apple won’t violate their privacy deserves what they get.
I understand why people hope that Big Data will be able to solve problems humans can’t. Parents surely, naturally hope that tech will help fight climate change, improve treatment of medical issues like dysgraphia, improve education, eliminate hunger and starvation, eliminate traffic, make gardens filled with huge tomatoes and no weeds, and brighten the future for generations. And tech has done some positive things with, especially for example, medicine, if gene sequencing can be considered positive instead of terrifying.
It is not defensiveness, however, to be honest about the costs usually outweighing the gains. It’s important to be realistic instead of hopeful. And it’s imperative that we examine Big Data as it exists instead of making predictions that any product — and it is important to always remember they are all products being sold to us for profit — instead of making predictions that any product is here to stay or is the next step. It is also, by the way, wrong to predict the future based on past events such as the automobile outpacing the horse or the computer beating the chess master. Those events were different than the rolling out of Big Data.
Idealism and purchasing products do not mix. Realistic pessimism is necessary to counter the wildly ecstatic mass marketing campaigns. In this case, AI as it stands today is not improving or eliminating writing. It is producing error-filled misinformation. It cannot read, cannot understand, and therefore, cannot write. It cannot assist you with your writing because it is unable itself to write.
The scary thing is that a lot of the folks behind a lot of this stuff really don’t give a shit what the ramifications will be.
As long as they have something “cool” to and are getting paid a lot , they are perfectly happy to destroy people’s lives.
There are some exceptions like Scott Aaronson, but they are definitely in a small minority.
There pare far too many ike Joi Ito who was the head of the MIT Media Lab taking hundreds of thousands of dollars from sex trafficker Epstein.
What most of the public don’t realize is that a lot of the people developing stuff like the Chatbot really don’t give a shit whether it has any negative ramifications.
As long as they get to work on something “cool” and get paid for it, of course, that’s all they care about.
The whole Algebra v. writing argument, above, seems crazy to me. Yes, there have been some times in my work life when I have used Algebra, but there haven’t been a lot of these. However, throughout my life, being able to express myself in writing has been ENORMOUSLY important. Love letters to potential girlfriends, cover letters to potential employers, instructions for my daughter on how to make a pie crust, letters to the editors of newspapers, statements to be read out in court or at a city council meeting, sales pitches, emails to colleagues, training materials for staff, operations manuals–I could go on and on and on listing these–occasions when being able to write was my superpower. And then there is the creative writing that I’ve done over the years, which has been a great source of joy.
I always tell students that learning to write is one of the best things that they can do to empower themselves–to make it possible for them, throughout their lives, to accomplish things they otherwise couldn’t.
Using learning algebra as an analogy for learning writing is just stupid in the extreme.
It’s an apples go oranges comparison.
If you don’t learn algebra,you can get along just fine. If you don’t learn to write, you will sound like Trump:” The oranges of the investigation…”
Trump is a chatbot with completely random weights for the nodes in the neural network
It
Or maybe Trump is a Chatbot with just a single node in the neural network.
He’s the famous superhero, The Lone Neuron.
Hiyo Orange, away!
Or like Teaching economist.
Yada yada yada.
Trump is a chatbot with completely random weights for the nodes in the neural network
This explains a lot.
Ronald Reagan used to forget what he was talking about, midsentence, and end with something entirely different. Opening from Sentence A on Topic 1, ending from Sentence H on Topic 25.
Bob,
I have not doubt that as an editor knowledge of writing has been ENORMOUSLY important. Perhaps you would understand that as a mathematician, knowledge of algebra is ENORMOUSLY important. While the ability to write is a superpower to an editor, the ability to do algebra is a superpower to a mathematician (and and economist). It is also a great source of joy.
If frequency of use in a person’s life is the issue, it is an empirical issue. At one time, writing quickly required students to learn cursive writing. It may be that people write less than they do algebra 2 mathematics. If that happens, I hope we can agree that students should not be required to learn something that is not relevant to their lives, no matter how relevant it is to your life.
“It may be that people write less than they do Algebra 2 mathematics.”
LOL. Yep. Everyone knows how useful logarithms and matrices are to the average Joe or Jill. Why, just this morning my barber was talking to me about the polynomial factoring exercises she’s submitting to her Homeowner’s Association. Thus, I guess, the common meme,
“Gosh. What a surprise. Another day in which I didn’t use any Algebra.”
The vast majority of people who took Algebra 2 could undoubtedly count on no hands ( tied behind their back) the number of times they have used it.
As a high school student, I was required to take Alrbra I and II as well as geometry. Never in my life since then have I used anything I learned and since unlearned in those courses.
Correction: algebra
As an insane fixer-upper I have to admit that I have used the Pythagorean Theory a few times while building a roof and staircase. Oh yeah, I learned that in pre-algebra. I guess the next three years were meant to make sure that stuck.
By TE’s logic, the only reason to play sports is to become a professional athlete, and the only reason to learn to play a musical instrument is to be an entertainer. It starts with economists calling humans “capital”.
It might be that mimes (who onlycommunicate through movements , gestures and facial expressions) might use
Algebra 2 more than writing.
But I have never witnessed a mime doing Algebra so it is something that economists must investigate.
Here is a (came) Nobel in it for sure.
LCT,
I see things in a very opposite way. It is the orthodox opinion here that they only reason to learn something is because you use it every day. Just as logarithms and matrices are not useful to the average Joe or Jill and therefore not to be taught to the average Joe or Jill, the ability to hit a baseball is not useful to the average Joe or Jill. It is Bob and the other orthodox poster’s here who are arguing that usefulness should determine what is, and is not, taught. Not me.
Logarithms and matrices are in the high-school Algebra texts, TE. It’s long past time that we stopped this nonsense. It’s like requiring every kid to take a class each year in dentures manufacturing.
Come on ,Bob
I used logarithms just yesterday to figure out how many cords of firewood i will get out of the giant oak log from the tree I felledhow last summer.
And I even had to do intreepolation between values in the table.
And every ten year old knows that matrices are part of Common Core
elementary math — prerequisite for Quantum mechanics, which is now taken in seventh grade.
Bob,
Iambic pentameter and sonnets are in high school texts. It is long past time that we stopped this nonsense. It’s like requiring every kid to take a class each year in dentures manufacturing.
My dentist told me he was inspired to become a dentist in a high school plastics shop class.
Okay math is not my thing, algebra was something I despised learning, and I still have absolutely positively supercalifragalistically no idea how a number can be irrational. Is there, however, some reason we must jettison everything from before? Isn’t algebra II an excellent exercise in complex, logical reasoning for those students who intend to later be challenged to solve complex, logical problems?
There’s no school like the old school. Keep the shop classes. Keep the algebra II classes too. Don’t tear down a fence unless you know all the reasons it was put up in the first place.
Without courses in dentures manufacture, how can we ensure that students become indentured servants?
We might be dentin’ the blog.
Years ago, when I was quite a young man, I read Vladimir Propp’s little book on the structure of the folktale and so clearly that one could easily write a program to use a modified version of his structural scheme, married to the Thompson/Aarne Folktale Motif Index, to create a program to generate folktales indistinguishable by casual readers from the main thing. But so what?
Much of the writing that is done in popular culture these days is so formulaic that it seems produced by machines. I think of the erotica-generating machines in Orwell’s 1984 or of the typical Netflix studio film:
cx: and saw clearly
George, writing in 1948, was pretty prescient, huh?
Coming Soon! Film Conceptualization Made E-Z!
Bob Shepherd
I have this psychic ability. I can predict the new season of Netflix films before these films are even announced!
To illustrate, I’ve been brainstorming here, a list of great ideas for innovative new films from Netflix Studios. The elevator pitches, below. What do you think!?!?! Amazing, huh?
A group of teenagers goes camping in a cabin in the woods, and at night, some of them start disappearing because OMG THERE’S SOMETHING OUT THERE!!!!
Aliens are invading Earth, and it looks bad, but a group of superheroes team up and fight them with all their combined powers!!!!
Boy meets girl, and they really hate each other, but then [something happens here] that throws them together and they discover that they don’t really hate each other at all! What a surprise! They can’t live without one another!!!!
On vacation in Italy (or India or Mexico or Russia or China), the beautiful, bright, teen-aged boy (or girl) of a mild-mannered single Mom (or Dad) is killed in crossfire between criminals. Mom (or Dad) then takes a crash course in becoming a killing machine and hunts them all down like dogs!!!!
After the divorce (or the death of the young husband), a woman reluctantly takes a trip to [exotic place here], where she discovers her true self and finds the real meaning of love!!!! The real meaning is (choose one): a) you have to love yourself first!!!! or b) you have to bury the ego and become focused on loving!!!! (so deep, huh?)
Married guy finds himself in lust with X, only to discover, when he gets with her, that she’s a psycho killer in league with (Satan, the Illuminati, the Russian mob, aliens from Alpha Draconis, an evil AI or corporation bent upon world domination)!!!!
Woman marries the dream guy, Mr. X, only to discover, when she gets with him, that he’s a psycho killer in league with (Satan, the Illuminati, the Russian mob, aliens from Alpha Draconis, an evil AI or corporation bent upon world domination)!!!!
He’s the perfect candidate—young, charming, good-liking, kind—the antidote to the weariness of the country—but once he’s in office, people start figuring out that he is actually controlled by (Satan, the Illuminati, the Russian mob, aliens from Alpha Draconis, an evil AI or corporation bent upon world domination)!!!!
Three friends go on a road trip, and what a wild and wacky time it is because–are you ready for this?–they’re all virgins and don’t wannabe!!! (parental guidance suggested)
Three guys wake up in a hotel room in (Vegas, Reno, Bangkok) and don’t remember what happened last night, but when they do. . . .
There. And guess what, I have twelve more ideas EVERY BIT AS ORIGINAL AS THESE ARE!!!! Eerie, huh? And I still have plenty of exclamation marks left over!!!!!!!
I know. I make this look easy, as though a nine-year-old could do it. (Come to think of it, it must be nine-year-olds–or machines–who/that do it.)
Who needs to be able to write when you can just hire Bob Shepherd to write for you?
We don’t need no stinking ChatGPT.
Pay Bob enough and I’m sure he will make you very happy with the results.
I’d choose a chat Bob over a chat bot to do my writing any day of the week.
Not incidentally, before I wrote that last sentence, the probability was virtually zero
that ChatGPT would ever have written it.
Now that it exists on the internet, if it’s added to the data to train ChatGPT, there is a small probability that it might repeat something similar given the right prompt.
Well now, you hit the nail on the head with “Pay Bob enough.” The goal of education technology is to NOT pay Bob enough.
As I pointed out below,, tge chat Bob actually writes for free, so we probably don’t have to pay him.
Just give him the right prompt.
For example, if you want an essay on David Coleman, all you need to do is write
“Common Core”
And if you want an essay on “Justice in America, all you need to do is write Donald Trump
I’ll edit you long time.
Full Metal Jacket meets editing is side splitting.
Hell, be writes all the stuff here for free.(as far as I know)
Wrong, SomeDAM. I am paid by Critical Race Theory to spread radical propaganda about crazy Socialist ideas like equal justice for all.
All I have to say to that is “Donald Trump”
You do not teach writing so kids can learn to write for a living. You teach writing so children can follow more and more complex lines of thought necessary for life. Some people write for a paycheck. Most people write for purposes that do not relate to money. Some write for fun. Others for reasons personal. Sometimes writing is therapeutic.
Check out Diane’s Twitter feed. Secretary Cardona thinks the purpose of education is to make students “meet industry standards.” He has no respect for young people.
All politicians say what polls tell them is best to say. Truth comes only from those with courage to say it.
My response to @SecCardona on Twitter:
“Schools do not exist to meet the demands of industry. They exist to help every student reach his or her full potential and build a thriving democracy, where everyone counts and participates.”
Well said, Diane!
Listen to Jon Stewarts latest podcast, “The Problem with Jon Stewart”, and Cardona’s eduspeak comes through loud and clear. He identifies himself as a “practitioner,” but the Secretary of Education has clearly practiced reading too many ACSD booklets. Alas, Jon Stewart means well, but he even goes down the “rote learning” rabbit hole in the end. This is a very revealing conversation and articulates our struggle ahead.
The way I saw it, Jon Stewart tried to articulate our need to get away from standardized testing, but Miguel Cardona simply sidestepped with the usual duplicity about formative assessments being embedded all year long. He’s a salesman. The rest of the conversation was about the relevance of curriculum, a conversation which I found worthless. The federal government has nothing to say about curriculum.
And we need too engage with Jon Stewart to help the general public understand the challenges for teachers.
I write because I love to write. I need to write.
And you do it so well.
Again, in my career, I have edited work by a great many of the country’s leading public intellectuals, and never have I received from any of these people, even from famous professors of English, manuscripts as clean as those I received from Diane Ravitch–work astonishingly free of errors in grammar, usage, mechanics, and formatting; work carefully and clearly organized and free of obfuscation, unnecessary verbiage; work that was well reasoned, significant, and artfully said.
You had good teachers, Diane, and have obviously honed your craft over decades.
Why, thank you, Bob. I consider myself fortunate to have such a brilliant editor. For everyone else, Bob volunteered to edit both “The Language Police” and “Slaying Goliath.” I turned in spotless manuscripts to my publisher. The strange part of this true story is that we have never met in person.
Writing is like breathing”
Some folks write with labored breath
Others write like coming death
Others write with greatest ease
Effortless breathing if you please
Okay, I took a shower to wash off the feces OpenAI dumped on my head today. Still a lingering odor, but I feel a little better. Speaking of feces, that article by in The Atlantic, and by a teacher no less. Shameful. Predicting that high school English will soon be obsolete? Really? Really! Come on. Everyone will ride around in self-driving vehicles by 2020. We are going to colonize Mars. AI will soon achieve the singularity. Cars will fly. Zoom will be the new normal. Doctors will operate remotely. Uber is the new economy. The shift will improve baseball. Streaming will replace watching. Twitter will be the new town square. Surveillance in the internet of everything will make everyone safer. Chat bots will improve writing. Beam me up, Scotty…
When will the always wrong, white boyish future fantasies stop? Our “conversation” with a bot today answers the question of whether AI can teach. It can’t.
Amen. O the hubris!
Pretty soon we won’t need cars (self driving or otherwise) or even rockets to get us from one place to another because the “It from Qbit” techies just created a wormhole with their quantum computer.
So once we all have a quantum computer in our phone (which will happen any day now), we will be able to flit around the universe quicker than you can say bullshit!
As Einstein once noted, the definition of insanity is believing that the virtual reality one creates with one’s mathematics is the actual reality.
But of course, the It from Qbit folks would counter that we are all just “living” in a computer game, so virtual reality IS reality.
https://www.quantamagazine.org/physicists-create-a-wormhole-using-a-quantum-computer-20221130/
Rolling on the floor laughing, SomeDAM. Thanks.
A modern essay—the last one I read was this piece from The Atlantic— looks a lot like Twain’s Or Howells’ essay types. But it does not share so much similarity with older essays. From this we can surmise that writing evolves like other linguistic techniques: it reacts to purpose. So the question here of Chargeit (or whatever the real name of this AI thing is) is not whether it can write an essay with a “prompt” but whether it can change its thought pattern to fit an unknown future.
The author of this Atlantic essay suggests that the calculator has saved mankind from the drudgery of long division. What is he thinking? I used to do long division for recreation while my daughter had swimming practice. Did you know that some numbers produce each of the natural numbers that precede them as remainders in long division before the repeat? It was way more satisfying for me to discover this than to read it in a book or on a website.
So maybe Chargeit will help us tell Ralph we need to meet at the Tabard so we can talk about Chaucer, but I would rather talk to Ralph about Chaucer at the Tabard.
“I don’t think, therefore I am not ”
Computers will save us
From adding, dividing
From reading and writing
And even from driving
Computers will save us
From every last thought
And that is when humans
Will know we are not
the question here of Chargeit (or whatever the real name of this AI thing is) is not whether it can write an essay with a “prompt” but whether it can change its thought pattern to fit an unknown future.”
The answer is clearly “No, it cannot.”
We can actually say that definitely itively because ChatGPT is a neural network which is only as good as the data used to produce it. It’s output is based on billions (some estimate over a trillion) parameters that have been tweaked during the “deep learning” training phase to in some sense “best” account for all the data in the training set.
So it’s “thought pattern” (if you can even call it that) is tied to the training days.
Such neural networks are notoriously “brittle” when they encounter situations outside the training days. That’s precisely the central issue of neural networks used for self driving cars and other high risk systems. They can and do behave to new situations in highly unpredictable ways.
Highly unpredictable for a car might mean driving into a concrete highway barrker because the car was not trained on data that included rerouting of lanes with cones and spray painted lines, for example.
Training data
Although training days probably works too.
At least one Tesla operating with “autopilot” did precisely that: drove smack dab into a temporary concrete barrier (killing the driver) because it did not recognize the markings and otger indications placed by highway workers that the lanes had been rerouted for highway construction.
This seems germane; if you want to do a coup, it’s important to write well:
*INT. AUTO-CORRECT HEADQUARTERS — DAY — January 2021
The crew of the auto-correct all sit at their stations. Klaxons. The helmsman looks up at an incoming text.
“Captain,” he says. “Representative Norman is typing.”
“I see it,” the Captain says. She frowns. They watch as the words continue to build up on the screen: Mark, in seeing what’s happening so quickly and reading about the Dominion law suits
“Dominion ‘law suits’?” asks the First Officer.
“Could be clothing,” the Captain says. “Don’t engage. Steady as she goes.”
Our LAST HOPE is invoking Marshall Law!
“Do we engage, captain?”*
https://www.washingtonpost.com/opinions/2022/12/15/autocorrect-is-best-hop-for-democracy-satire/?utm_campaign=wp_week_in_ideas&utm_medium=email&utm_source=newsletter&wpisrc=nl_ideas&carta-url=https%3A%2F%2Fs2.washingtonpost.com%2Fcar-ln-tr%2F3897669%2F639f00ebef9bf67b2326860c%2F59731517ade4e21a848a8e69%2F62%2F77%2F639f00ebef9bf67b2326860c&wp_cu=042e5574aa882b430f7257d3304bf037%7CDE43AC95437978F0E040D90AB42359AC
To generate absurdist theatre, one simply has to quote what these morons say to one another.
Oh, to be a fly on the wall!
“I don’t know on nothing.” –MTG
As ever, Peter Greene has some incisive commentary on the bot:
ChatGPT is an excellent prompt tester.
Think you’ve come up with a good writing prompt? Feed it to the chatbot. If it can come up with an essay that you would consider a good piece of work, then that prompt should be refined, reworked, or simply scrapped.
Sure, your students might not use the software to cheat (particularly if its capacity is not increased). But if you have come up with an assignment that can be satisfactorily completed by computer software, why bother assigning it to a human being?
https://www.forbes.com/sites/petergreene/2022/12/11/no-chatgpt-is-not-the-end-of-high-school-english-but-heres-the-useful-tool-it-offers-teachers/?sh=217b5c3a1437
When I was teaching college students, for major papers I had them propose a topic, write an outline, make a presentation in class, write a draft, all with feedback and grading, and finally draw on the prior steps to produce a final paper. I think this was good for them and also evaded any online subterfuge. Time-consuming of course, but that’s how education is!
Great, Mr. Smith!