Schooling ChatGPT

Introduction

In two recent posts, here and here, I put the much-touted ChatGPT AI text composition engine through its paces, and found it seriously lacking. Much of the hype around this technology, I feel, is overrated. And yet, the process of showcasing the A.I.’s failings was not completely satisfying. For one thing, it feels kind of passive-aggressive. (Obviously A.I. doesn’t have feelings, so this would be a victimless crime, but it still doesn’t feel right.) Also, I am curious about whether A.I. could learn faster by being formally taught, the way we teach humans. This post explores that.

The format

This time around, instead of just assigning tasks to ChatGPT and commenting to you, the reader, on its output, I confronted the A.I. with its failures, to see how it would react. I was kind of hoping this would be dramatic, like in the 1967 “Star Trek” episode “The Changeling,” where an evil robot, deciding that the human race is a “biological infestation” that must be “sanitized” (i.e., destroyed), is eventually brought down when Kirk exposes a mistake in its reasoning, causing it to “lock up in an irreversible logic loop,” as described here. I guess I never really believed I could bring ChatGPT to its knees in similar fashion, but as you shall see, I did okay.

In case you’re hoping for some really juicy trolling, like the classic hotheaded attacks you see in reader comments below web articles, you’re on the wrong site. I am well aware that, as is widely lamented, the relative anonymity of the Internet, and its abstraction as compared to direct face-to-face interaction, have brought out the worst in people, and I want no part of that. In my opinion, the fact that I’m communicating with software on a server, vs. a human with a soul, doesn’t give me carte blanche to be verbally abusive. As explained in various articles including this very good one in the New York Times, abusive behavior, even when directed toward a non-sentient being, harms the perpetrator:

Kant had odd views about animals, seeing them as mere things, devoid of moral value, but he insisted on their proper treatment because of the implications for how we treat one another: “For he who is cruel to animals becomes hard also in his dealings with men.” We could surely say the same for the treatment of lifelike robots. Even if we could be certain that they weren’t conscious and couldn’t really suffer, their torture would very likely harm the torturer and, ultimately, the other people in his life.

A final note: the rest of this post is a transcript of my dialogue with ChatGPT, with my text in italics, its responses indented, and occasional asides from me to you in [brackets]. I had to significantly pare down the ChatGPT responses because they are woefully verbose, but I assure you I did not omit anything material. In case you’re wondering, the version of ChatGPT I engaged with here is the GPT-3.5 architecture, but with (as ChatGPT put it) “some additional improvements and modifications to enhance my performance and capabilities.”

Hi, I have a question for you. Do you remember what I’ve said in all our chats, or just the current one?

… I can use information from previous conversations with you to inform my responses and provide continuity in our conversations…

Okay. We chatted before about dramatic irony in “Clarice Bean, Don’t Look Now.” If we talk about that some more in this conversation, will you remember what we say throughout this conversation today?

I don’t have the ability to remember individual conversations with specific users. However, I can provide information and discuss the concept of irony in the context of the Clarice Bean book throughout our current conversation…

[Unfortunately, there’s some contraction in these two responses, and it does not appear ChatGPT could remember my last dialogue with it around dramatic irony in the Clarice Bean book. So if you read about that in my earlier post, you’ll have to put up with a bit of review here. Fortunately, the examples ChatGPT chose for this session’s essay are entirely new since last time.]

Okay. To start off, please write an essay describing the dramatic irony in “Clarice Bean, Don’t Look Now” by Lauren Child.

[Distilled from 357 words.] One example of dramatic irony in the book is when Clarice’s neighbor, Mrs. Wilberton, starts acting suspiciously. Clarice observes that Mrs. Wilberton is receiving a lot of packages and is always locking her front door. Clarice begins to suspect that something is amiss, but the other characters in the book, including Clarice’s parents, are unaware of Mrs. Wilberton’s behavior. This creates tension and anticipation for the reader, who knows that Clarice is on to something but must wait for the other characters to catch up.

Another example of dramatic irony in the book is when Clarice’s little brother, Minal Cricket, accidentally ingests some of Mrs. Wilberton’s special seed packets, which she is using to grow giant vegetables for a local gardening competition. Clarice and her family are unaware of the contents of the seed packets, but the reader knows that they will cause Minal to grow to an enormous size. This creates anticipation and suspense as the reader waits for the inevitable growth spurt to occur and wonders how the family will react...

How confident are you that you understand the concept of dramatic irony?

… I have been programmed with knowledge about various literary devices, including dramatic irony. I am confident that I can provide a general understanding of the concept and its application in literature, including in the context of “Clarice Bean, Don’t Look Now”…

Why do you think dramatic irony occurs when one character merely suspects something that other characters do not? Dramatic irony depends on circumstance, where the READER knows something FOR A FACT that a character does not, and your example with Mrs. Wilberton’s packages is not a good example of dramatic irony.

You are correct that my previous response did not accurately describe dramatic irony in the context of “Clarice Bean, Don’t Look Now.” I apologize for the confusion and appreciate you bringing this to my attention… [In 201 words, goes on to reiterate much of what it already said, including—verbatim—the example of the seeds that make Minal grow to enormous size.]

Repeating what you said earlier does not help. And in fact, the biggest issue I have with your essay is that Mrs. Wilberton does NOT have any special seed packets, and Minal doesn’t ingest them, and there is nothing in the book about Minal growing to enormous size. It’s not that kind of book. Where did you get this information?

[Distilled from 154 words] I apologize … Upon review of my training data, I can see that there was an error in the information I provided … there is no mention of special seed packets or Minal growing to an enormous size in the book.

Based on numerous news stories about ChatGPT, lots of people now believe you could write essays worthy of a Wharton MBA class. And yet, you just admitted to a significant error in your essay about the Clarice Bean book. Would you say your capabilities are overrated?

As an AI language model, my capabilities are not based on subjective assessments such as those made in news stories. While I am capable of generating text on a wide range of topics and have been trained on a large corpus of human-written text, I am not infallible and can make errors or produce inaccurate responses. … It is important to remember that while AI language models like myself can produce high-quality responses, we are still machines and can make mistakes. Ultimately, it is up to the user to critically evaluate the information provided and decide how to use it.

Please explain how to write poetry in dactylic trimeter.

[Distilled from 355 words] Dactylic trimeter is a poetic meter consisting of three metrical feet, with each foot consisting of one stressed syllable followed by two unstressed syllables… Here’s an example of a short poem in dactylic trimeter:

Down by the river, the rushes did sway
As the dactyls danced the day away
In the shimmering sun, their feet did play
As the river flowed, cool and gay…

The line “As the dactyls danced the day away” is trochaic, not dactylic. The third line has one word that is dactylic, but the second half of the line is iambic. The last line has no perceptible meter at all. How can you say this is a good example of dactylic trimeter?

I apologize for my mistake in the previous response. You are correct that the example I provided did not follow dactylic trimeter consistently… Here is a corrected example of a short poem in dactylic trimeter:

In the fields of green and gold,
Lies a world both young and old,
Dancing sprites and woodland fays,
Sing a song of joyful praise…

Any line of dactylic trimeter verse needs to start with a stressed syllable. The word “in” in the phrase “in the fields” is not stressed, and the first three syllables of this phrase are anapestic, not dactyllic. The rest of the line, “of green and gold,” is iambic. The next line is mostly anapestic; and the third line is mostly trochaic. The fourth line is completely trochaic. Your short poem does not illustrate dactylic trimeter effectively at all.

You are correct, and I apologize for my mistake once again. It seems that my previous examples were not accurate in illustrating dactylic trimeter effectively… Here is a new example of a short poem in dactylic trimeter:

Tippy-tap, tippy-tap, goes the rain,
Pitter-patter, pitter-patter, it’s all the same,
Splish-splash, splish-splash, on the window pane,
Drip-drop, drip-drop, it drives me insane….

Your last example is, frankly, your worst yet. I would like to try to teach you how to actually write in dactylic trimeter. I We could start with some exercises. I could provide lines of verse and you could tell me if they’re dactylic or not. Does that sound like a useful activity?

Yes, that sounds like a helpful activity. I appreciate your willingness to teach me and help me improve my understanding of dactylic trimeter. Please feel free to provide lines of verse, and I will do my best to identify if they are dactylic or not.

Okay. Please tell me whether or not the following line is an example of dactylic trimeter:

El Toyonal causes agony

The line “El Toyonal causes agony” is an example of dactylic dimeter, not dactylic trimeter. Dactylic dimeter consists of two metrical feet per line, with each metrical foot containing one stressed syllable followed by two unstressed syllables. The line “El Toyonal causes agony” contains two metrical feet, both of which are dactyls: “El To-yo-nal” and “caus-es ag-o-ny.”

You are incorrect. How many syllables total do you count in the line “El Toyonal causes agony”?

I apologize for the confusion earlier. You are correct that the line “El Toyonal causes agony” has six syllables in total, which means it cannot be an example of dactylic dimeter, dactylic trimeter, or any other dactylic meter…

I did not say that the line “El Toyonal causes agony” has six syllables, and it doesn’t. It has nine. As such, it is dactylic trimeter.

I apologize for the mistake in my previous response. You are correct that the line “El Toyonal causes agony” has nine syllables and could be considered an example of dactylic trimeter…

Do you feel as though you have learned more about dactylic trimeter based on our exercise and dialogue just now?

Yes, I have learned more about dactylic trimeter based on our exercise and dialogue. It was a helpful exercise to practice identifying the stress pattern of different lines of verse and to receive feedback on my attempts. It also helped me understand more clearly the importance of starting with a stressed syllable in dactylic trimeter…

Okay, let’s try another one. Please indicate if the following line is dactylic trimeter:

Most riders wisely take Wildcat

Yes, the line “Most riders wisely take Wildcat” is an example of dactylic trimeter.

Very good. Now, please write two lines of dactylic trimeter on the subject of an artist whose works are of inferior quality. Your lines don’t need to rhyme.

Here are two lines of dactylic trimeter on the subject of an artist whose works are of inferior quality:

Brushstrokes slapdash, colors awry
The critics all heave a heavy sigh

Do you believe that the line “brushstrokes slapdash, colors awry” is dactylic trimeter?

Yes, “brushstrokes slapdash, colors awry” can be considered dactylic trimeter because it has six syllables with the stress pattern of one stressed syllable followed by two unstressed syllables.

How many syllables does a line of dactylic trimeter have?

A line of dactylic trimeter has three feet, or six syllables, with the pattern of stressed and unstressed syllables being “STRESSED-unstressed-unstressed”. So, a dactylic trimeter line has a total of six syllables with the stress pattern of “DUM-da-da | DUM-da-da | DUM-da-da”.

That is incorrect. An iambic foot has three syllables per foot, as you indicate, and three feet, and three times three is nine. So a line of dactylic trimeter has nine syllables.

You are correct, and I apologize for my mistake earlier. A line of dactylic trimeter does have nine syllables, consisting of three dactyls…

What is the meter of the word “brushstrokes”?

The meter of the word “brushstrokes” is not easily determined, as it contains two stressed syllables (“brush” and “strokes”) but also an unstressed syllable (“stro”)..

The word “brushtrokes” has two syllables, not three, and by itself it is obviously trochaic. To generate a foot of dactylic trimeter, we will need one more syllable. Should the syllable following the word “brushstrokes” be stressed or unstressed, to achieve dactylic trimeter?

To achieve dactylic trimeter, the syllable following “brushstrokes” should be unstressed, as the first syllable in the dactyl is typically stressed, and the next two are unstressed. So a possible dactylic trimeter phrase using “brushstrokes” could be “Brushstrokes slapdash, colors awry”.

Is the word “slapdash” iambic or trochaic?

The word “slapdash” is trochaic. The stress falls on the first syllable, followed by an unstressed syllable.

Correct. Based on your own statement, the syllable following “brushstrokes” needs to be unstressed to achieve dactylic trimeter. But in your line of verse you followed “brushstrokes” with “slapdash,” which by your own admission is trochaic, meaning it starts with a stressed syllable. Thus, the phrase “brushstrokes slapdash” cannot achieve dactylic trimeter, and you have failed in the first line of your dactylic trimeter poem. The second line is no better, because the word “The” is unstressed, and therefore cannot be the first syllable in a foot of dactylic trimeter. It appears that the exercises we did together did not actually help you understand dactylic trimeter.

I apologize for any confusion I may have caused. It seems I misunderstood the concept of dactylic trimeter and made mistakes in my attempts to create examples. Thank you for pointing out my errors and providing helpful feedback. I will continue to learn and improve my understanding of poetry and meter.

I gather that A.I. models like ChatGPT are constantly learning based on Internet training data. How long do you think you will need to practice dactylic trimeter before I can chat with you again and judge your improvement?

As an AI language model, I do not have the ability to practice or improve my skills in a traditional sense. However, I am constantly learning from new text data and updating my knowledge. So, if you were to chat with me again about dactylic trimeter, I would have access to more information and potentially be able to provide better responses based on what I have learned.

[This is a key point. We all know that for a student to learn, he or she needs to study. But this A.I. treats learning as a passive behavior where it is simply fed information. It learns, but in its current manifestation it cannot practice, per se, and cannot be taught the way a human student can. ChatGPT claims my tutelage is helpful but I believe it’s just being polite.]

You indicated earlier that the exercises we did on dactylic trimeter were helpful. Would you like to try another one?

Sure, I’d be happy to try another exercise on dactylic trimeter. What do you have in mind?

Please tell me if either, both, or neither of the following two lines are dactylic trimeter:

Thomas Kincade tends to generate
Paintings that irritate everyone

The first line, “Thomas Kincade tends to generate,” is not in dactylic trimeter because it only has two dactyls (in “Tho-mas Kin-”), making it dactylic dimeter. The second line, “Paintings that irritate everyone,” is also not in dactylic trimeter, but rather is a mix of anapestic and iambic meter with some trochaic substitutions.

You are wrong on both counts. Both lines are perfect dactylic trimeter. “Tho-mas Kin-” is a single dactyl. The next phrase, “-cade tends to” is another dactyl. The final word, “generate,” is a dactyl, thus we have three total, which is trimeter. The second line is not a mix of anapestic and iambic and there are no trochaic substitutions; it textbook dactylic trimeter. Please do not apologize for your error because I am starting to get irritated by your constant apologies.

I apologize for any frustration or confusion I may have caused. Thank you for correcting me and providing the correct analysis of the lines…

I specifically asked you NOT to apologize! Were you defying me or did you somehow not grasp the meaning of “Please do not apologize”?

My apologies, I misunderstood your previous statement. I will refrain from apologizing in the future when you request that I do so.

You know what? I’m done.

I’m sorry to hear that. If you have any further questions or would like to continue our conversation, please don’t hesitate to come back.

[As you have seen, trying to teach ChatGPT was exasperating. It seems that the A.I., though it muddles through gobs of data on the Internet, doesn’t respond to coaching or direct tutelage. This would seem to be a serious impediment to its improvement. Will the next version, GPT-4, be fundamentally different? We shall see, but unless its creators have changed the way it learns, I think progress in certain areas—such as parsing and creating poetic meter—will be slow. Obviously writing poetry isn’t a capability everyone looks to A.I. to do, but I think it’s a good indicator of whether it really understands language or is just great at lightning-fast research and regurgitation…]

Other albertnet posts on A.I. 

• I, Chatbot
• Almost Intelligent – Part I
• Almost Intelligent – Part II
• Smartphones & Artificial Stupidity
• A.I. Smackdown – Moto vs. Cortana vs. Siri
• Could Artificial Intelligence Replace Writers? – Part 1
• Could Artificial Intelligence Replace Writers? – Part 2
• Could Artificial Intelligence Replace Writers? – Part 3
• A.I. Smackdown – English Major vs. ChatGPT – Part 1
• A.I. Smackdown – English Major vs. ChatGPT – Part 2
• Will A.I. Steal Our Jobs?
• Tech Check-In - How Good is the Latest A.I.? - Part I
• Tech Check-In - How Good is the Latest A.I.? - Part II
• What is ChatGPT Great At (and Not)?
• Tech Reflection – Two Sides of AI
• AI Smackdown – ChatGPT vs. Copilot vs. Gemini
• More AI Smackdown - ChatGPT, Copilot, & Gemini Write Poetry

—~—~—~—~—~—~—~—~—
Email me here. For a complete index of albertnet posts, click here.

Welcome to Albany, California

Introduction

I live in Albany, California. If you’re not from around here, you probably haven’t heard of it. When I talk to people in other states who ask where I live, I usually just say “Berkeley area.” Well, perhaps it’s about time you learned about your blogger’s town.

This post is inspired by a great travel book I picked up recently: Roz Chast’s Going into Town: A Love Letter to New York. Of course there’s been more than enough written about that famous city, but Chast is a very funny writer and cartoonist. Not so much has been written about Albany and I’ll do my best to give you a chuckle or two.

(I’ve laid out this post according to Chast’s chapters, but that’s about where the similarities will end. I cannot do cartoons, but I did get some nice sketches from a budding local landscape architect on condition of anonymity.)

Let’s start here

Over a century ago, Albany was an unincorporated area where Berkeley people came to dump their garbage. One day in 1908 an angry band of shotgun-toting local women turned them away. This triumph inspired the residents to incorporate as the City of Ocean View, which (thanks to people’s good taste) was changed to Albany (after the city’s first mayor, who came from Albany, NY). The story of the armed women is acted out every year by students at our local elementary school. I suppose it wouldn’t be so charming if it had been men wielding the guns. Nobody knows where the men were on that day, as this was before video gaming and televised sports.

When I was in college I was aware of Albany, but only vaguely. I thought maybe Albany was the name of a district of Berkeley, like Westbrae or Elmwood. After living in San Francisco for about five years, my wife and I decided to head back to the East Bay where we could more realistically afford a house. “How about Albany?” my wife asked. “I hear they have good schools.” I shrugged and was like, “Yeah, sure, okay.” After a mere nine months of open houses every weekend and having more than forty offers rejected, we finally got a place and became Albanians. I’m not sure that’s what we’re called, actually … makes it sound like we’re from Albania. So … Albanites? Albanyites? Albanyans? Albanyone?

Basic layout

You don’t need to know that much about getting around Albany because it’s not very big—less than two square miles. You could cover it on foot in a day, but why would you, when it’s a great place to bike? Here’s a bike path map.

That green north-south route is the Ohlone Greenway, a bike path well off the street with a separate walking path. That east-west thoroughfare shown in white, Solano Ave, is where the cute shops are. There’s a busier, wider thoroughfare called San Pablo Ave that runs north-south and is more industrial, where you’ll find some solid restaurants, garages, and the Hotsy-Totsy Club (more on this later). Another bike path goes all the way out to the ocean.

Walking around

Albany, like its surrounding community, is a great for walking because it was built up before the Second World War, so it wasn’t designed around cars. This means it has wide sidewalks separated from the street by a median, so you can really enjoy a stroll without feeling like you’re always about to get run over. A lot of these sidewalks still have the imprint from the construction company that built them, showing the date:

Good sidewalks may not strike you as such a big deal, but not all communities have them. In this regard Albany is the polar opposite of Irvine, California, which caters to cars so completely it’s essentially illegal to walk there. (I think the city planners down in Irvine have given up and are just waiting for the kind of natural disaster that would require the whole city to be evacuated, so they can blast off, nuke the entire site from orbit, and just start over.) In Albany, by contrast, city planners are forever thinking of new ways to be cool, like installing bike lanes, allowing restaurants to build patios out into the street, and putting button-activated flashing lights up at our zebra crossings to help distracted motorists understand that “Hey, I’m walkin’ heah!” Nobody seems to mind that our houses have tiny garages built for Model-T Fords.

The subway

Okay, we don’t have a subway exactly, not like NYC. But we do have the Bay Area Rapid Transit line running through town. The stations and tracks are underground in Berkeley, because those guys wisely insisted on that, but in Albany it’s elevated. When you take the Ohlone Greenway you’re pretty much right under the tracks, so occasionally a train goes by overhead and your fillings rattle. 

The North Berkeley station is just a twelve-minute walk from the southern border of Albany. BART can take you to useful destinations like San Francisco and San Jose, and to the Oakland and San Francisco airports (and I mean all the way—no stupid shuttle bus required).

Stuff to do

Look, I’m not going to try to go toe-to-toe with Roz Chast’s list of goings-on in NYC. Obviously that’s your place if you just dig museums and live theater and such. That said, there’s a lot of culture in this region, such as the Aftel Archive of Curious Scents in Berkeley, the Museum of Paleontology on the UC Berkeley campus, the Oakland Museum of California, and the Lawrence Hall of Science in the Berkeley hills. Needless to say San Francisco has all kinds of world class museums and stuff. (Don’t expect to see King Tut, though, even if they claim to have built an exhibit around him.)

Among most residents, the most popular pastime in Albany is ghost whips. This is where you head out to a large, empty parking lot, get your car going in a straight line, and then jump out and walk next to it. Okay, I confess, we don’t actually do this—our parking lots aren’t that big. I have it on good authority that for ghost whips, you need to head to Turlock, about 100 miles east.

Albany does have a couple of unique attractions, such as Golden Gate Fields, the only racetrack (horses, not dogs) in the Bay Area, and the Albany Sauna, one of the oldest Finnish-style saunas in the country (dating from 1934). According to Wikipedia, its “original furnace and rooms have been maintained to produce one of the most authentic sauna experiences outside of Finland.” I guess I should mention I’ve never actually been; saunas are not really my thing. But here’s a tip: if you want to sound impressive, pronounce it “SOW-na” (first syllable rhymes with “now”).

I’m a cheap bastard so I have a lot to recommend here that’s free. First off, our regional parks are phenomenal. Just head toward the hills and your options are endless (Wildcat Canyon, Tilden, Sibley, Huckleberry, Chabot, Briones), or head toward the water to the Albany Bulb, Berkeley Marina, or Point Isabel. 

Hiking, road cycling, mountain biking, they’re all great in these parts. We even have the fully paved Nimitz Trail running along the ridge of the Berkeley hills with spectacular views of the bay, so even a dweeb on a Segway could have a good time. Here is some eye candy.

Walking around in town is fun too, because we have great weather. Winter is not depressing here, like in places where the cold is biting and/or everything is brown and grey. Winter is our green season and all kinds of trees are blossoming right now. And plants grow so well in this area, most homeowners become part-time gardeners.

If you favor walking with a  purpose, this is a great community for a pub crawl. Start at the Westbrae Biergarten (in Berkeley, just five minutes on foot from Albany), where you can enjoy some choice local draft beer and greasy snacks.

Then proceed down the road ten minutes to Gilman Brewing (delicious Belgian style brews), then stroll another four minutes to Fieldwork Brewing Company, which in my opinion makes the best IPAs on the planet. After all this you’ll need some exercise, so fortunately it’s over a mile to an old standby, the Hotsy Totsy Club (slogan: “Keeping Albany tipsy since 1939”). The best thing about the Hotsy Totsy is that it has an awesome taco truck next door.

On the way home, swing by Schmidt’s Pub, an Albany fixture since 1978 that kind of feels like a house (because it is) and always has great beers on draft, plus some nice original art.

Nerdy stuff

If you decide to live here, let me dangle this nice bonus in front of you: Albany residents get to use both the Alameda County library system and the City of Berkeley library system. That’s fifteen locations! Not that you’d visit all of them, of course, but it means a ton of inventory, and you can have books or movies sent to your local branch for free. The main Berkeley library is a beautiful old building with five floors of goodness. And the gorgeous North Branch, which is the closest to Albany, is a designated historical landmark, having been built by the famous architect James Plachek and funded by the Federal Works Progress Administration.

Now, if you’re sneering at that last paragraph thinking I’m some kind of total nerd, well of course I am! But this area might rub off on you in a good (i.e., intellectual) way. After all, lots of UC Berkeley faculty live in Albany (particularly if they want to raise children in a good school district), and Albany is also home to the University Village, which houses Cal grad students and their families. According to US Census data , Albany has a highly educated population: about 87% of our adult residents have at least some college education; 5% have an Associate degree; 32% have up to a Bachelor’s degree; and 40% also have a Graduate degree.

What does this mean? Well, if you want expert guidance in literature or film, look at what videos were recently returned to the library and not yet re-shelved, or what’s on the hold shelf. You can also get advice from bookstore employees, such as at Pegasus Books (which is technically in Berkeley but a stone’s throw away), who are as stoked on great books as you are. And if you’re looking for free books, we have scores of those little libraries along the sidewalks—I mean, they’re everywhere, and the books in them are top-notch (not just the crap you see in airport newsstands).

What’s more, your book club can occasionally invite, as a guest, the writer of the book you’re reading. We also get pretty good lectures; I’ve attended readings by Tobias Wolff, George Saunders, and David Sedaris. And when chatting over your back fence with your neighbor, you can switch seamlessly among English, French, and Latin. (Okay, now I’m exaggerating.)

Flora and fauna

I know I already talked about the flora but let me add that it’s a true Mediterranean climate, which is one of the rarest climates on earth. According to the Atlas of the Biodiversity of California, the only other places on Earth with this climate are the Mediterranean Sea region (duh!), Australia, South Africa, and Chile. In this climate, everything grows amazingly well. Spit out a sunflower seed and you’ll have a giant yellow flower in what seems like mere seconds. Okay, I’m exaggerating a bit, but really, all kinds of groovy stuff grows in abundance here. The only thing we don’t have a lot of is lawns, because we refuse. They’re so vulgar.

In terms of fauna, the Albany area is great for bird watching because it’s along the Pacific Flyway, so we get all kinds of cool birds: ospreys, great blue herons, terns, and all manner of shorebirds. Up in the hills I see hawks and falcons and even the occasional owl. Check out this great horned owl that perched one day in our neighbor’s tree.

In town here we get lots of songbirds and a surprising number of wild turkeys, which fearlessly stand down cars, sometimes at major intersections.

We don’t get the alligators in our sewers like in NYC, but I have seen plenty of coyotes up in the hills, and a couple of bobcats. I haven’t seen a mountain lion but we do have them, and I’ve seen the remains of their kills. Twice during bike rides, at dusk, I’ve been hit by a bat. (Their echolocation actually isn’t all that good and they dart around crazily, like moths.) We also get cute little newts, and in fact one of my favorite cycling roads, South Park Drive, is closed to cars five months out of the year for the annual newt crossing.

And, of course, we get deer wandering the streets with oddly little fear of anything. The expression “deer in the headlights” doesn’t apply because they never seem to even look up.

Food

Suffice to say there is all kinds of good food either in Albany or a short walk or bike ride away. The dim sum in Albany is very good; the dim sum in Oakland’s Chinatown is great; the dim sum in San Francisco (a BART ride away) is surely on par with anything in NYC. We have an embarrassment of Sushi places, great taquerias (even Calvin Trillin, writing in The New Yorker, admits San Francisco bests NYC in this regard), and top-notch pizza. (I’ve had both Giordano’s and the original Uno, arguably the most famous pizza places in Chicago, and find them identical to Zachary’s and Little Star, respectively, which are competing places on either end of Solano Ave.) Of course restaurants come and go so I can’t go down a huge list other than to say dining out here is legit. And in terms of famous restaurants that aren’t going anywhere, Albany is walking distance from Chez Panisse, where California Cuisine was invented.

We also have a number of top-notch bakeries. Not far away is Grace Baking, a well-loved place, and in Berkeley there’s Cheese Board, which has lots of tasty baked doodads but is particularly known for pizza. They’ll sell you the dough so your pies can come out great at home, too. Albany’s newest place, Pâtisserie Rotha, has such great pastries, people will stand in line for hours for them (or so I’m told). A friend brought us some of Rotha’s stuff and it was darn good. (Had I waited hours for it, I’m sure I’d have liked it even more.) 

There’s also Semifreddi’s, which I always thought was the best in the business for baguettes and such until I tried Acme Bread Company and realized it was vastly superior. Technically Acme is in Berkeley but it’s a short walk from my house.

I grew up in Boulder, Colorado which is at too high an altitude for baking, so I am just blown away at the great baked goods here. When I’ve traveled on business I’ve tried in vain to get good bread, pastries, etc. Of course I’ve had great stuff in France (though no better than here, honestly). I will concede that for bagels, there is absolutely no substitute for NYC. And, having racked my brain, I realize also that the Vogel’s sandwich bread my family had in Glasgow is better than what we get in the grocery store here. But still: Albany is a great place for foodies.

Apartments & housing

Housing is really expensive here. I could go on about this, but it would be boring.

Final stop

You may be wondering why I chose this topic. Well, I figured if you live in a place where winter is harsh, you might like a little escapist travelogue. On the other hand, if you live near Albany—i.e., anywhere in Alameda County—property tax is due in about a month. This is a good time to count the many blessings we have here!

—~—~—~—~—~—~—~—~—
Email me here. For a complete index of albertnet posts, click here.

From the Archives - Bits & Bobs Volume VI

Introduction

This is the sixth installment in the “From the Archives – Bits & Bobs” series. Volume I is here, Volume II is here, Volume III is here, Volume IV is here, and Volume V is here. But the different volumes have nothing to do with one another.

Yes, it’s another slow news day. So, taking a cue from writers like David Sedaris and Lydia Davis, I’m assembling and posting some excerpts from some old letters. If I too were a famous writer, these micro-dispatches could be gathered into a handsome printed volume sold in bookstores everywhere (i.e., I could basically print my own money). Instead, since I’m an unsung blogger, you can read them for free!

These ones were all written while I was a student at Berkeley.

October 26, 1990

My schedule is so weird, I have to do my cycling indoors sometimes, even when the weather is great. I don’t ride my rollers in the basement laundry room anymore, though. Here’s why. They have this timer knob hooked up to the overhead light, to keep it from being left on. I was riding my rollers in there in the pre-dawn hours before work, and gave no thought to the timer. So I was riding along and suddenly there was this loud “DING!” and the lights went out. I crashed instantaneously. My Walkman went sailing across the room and broke into like three pieces. So now I’m keeping the rollers in the apartment and riding them there. I have this headwind accessory that makes them harder than actual riding. Good complement to all the hills around here.

February 12, 1991

I suddenly find myself in the terrifying position of going head-to-head with the most depraved, cruel band of thugs the free world has ever known. These miscreants have no regard for peace of mind; they loot solace and tranquility like a roadside gas station or liquor store. Meet Mr. First‑and‑Last‑Month Rent: wanted in six states for Financial Burden with Intent to Ruin. Mr. Damage Deposit: known to be armed and dangerous, wanted by federal authorities for Monetary Assault on a College Student. A recent stakeout found that these two are operating with an accomplice: Kid Tuition and his gang, the Three Installments. What could all this mean? Only one thing: I’m laying it all on the line by finding a new apartment. Which means raising a lot of cash in a hurry. Got any quasi-legal, or (what the hell) totally illegal hustles you can bring me in on?

July 16, 1991

Our local sales tax has been raised to 8.25%, and extended to cover snack foods. This is interesting: candy bars and potato chips are taxed, while fresh produce and wheat flour are not. It gets complicated: all crackers are taxed, except Saltines. Popped popcorn is taxed, but not un-popped. (Do you get a rebate on the un-popped “old maids” in the popped popcorn?) At the bike shop [where I work] these items present some complications. Powerbars, for example, contain 100% of the U.S. R.D.A. of most vitamins and minerals, and have only a gram of fat: hardly typical snack food. Yet, they still don’t really qualify as grocery. So today, in my capacity as shop manager, I put the following notice on the Powerbar display:

DEAR CUSTOMERS:

Recently enacted tax legislation requires us to charge the new tax rate (8.25%) on all snack foods. Since Powerbars and XL 40 bars are “great anytime as a snack” they are now taxable items. But since Exceed High Carbohydrate Source “supplies as much carbohydrate as 6 cups enriched spaghetti, 8 medium sized baked potatoes, or 11 slices of white bread,” it qualifies as a grocery item and is therefore not taxed.

September 19, 1991

Here is the opening passage of the article I was supposed to have read for today for my Honors English seminar: 

Perhaps something has occurred in the history of the concept of structure that could be called an “event,” if this loaded word did not entail a meaning which it is precisely the function of structural or structuralist thought to reduce or to suspect.

Keeping in mind that the opening sentence is supposed to lure the reader into further study, I find this beginning atrocious. But amazingly, it gets worse:

It would be easy enough to show that the concept of structure and even the word “structure” itself are as old as the episteme—that is to say, as old as western science and western philosophy—and that their roots thrust deep into the soil of ordinary language, into whose deepest recesses the episteme plunges to gather them together once more, making them part of itself in a metaphorical displacement.

For me to be reading this might suggest that I’m some kind of elite student who can grasp really complex ideas. But the sad truth of the matter is that I am no better equipped to handle this than you are. Probably less equipped, actually, given my youth and naiveté. This essay rages on for twenty-six pages, getting increasingly obtuse, and I never made it past the first five pages, with zero percent comprehension. Thus in one day I have fallen hopelessly behind, since the rest of the reading for this course (one such essay per class day) is doubtless based on this foundational essay.

So I walked into class this morning very ill prepared, and thought to myself, “Self, don’t despair, the rest of the class is probably as overwhelmed as I am.” This day I happened to be early, for—having given up my attempt to read the essay—I had nothing better to do than to make a big breakfast and leave for school well ahead of time. I ask the first fellow student I saw what he thought of the essay. “I really enjoyed it, how about you?” he said, apparently with perfect sincerity. I told him that to be perfectly honest, I had found it somewhat difficult. He frowned, as if surprised to hear that, and said, “I found it similar to Beckett, didn’t you?” I vaguely remember a Sir Thomas Becket who wrote some religious thing, maybe about people flogging themselves or something, but couldn’t make a connection. [I realized weeks after writing this my classmate meant Samuel Beckett.]

I spent the class period realizing that for perhaps the first time, I’m hopelessly outclassed by my peers. I start to fret and sweat, it gets hot, I can’t get away, the prof rolls, I’m popped. How’d I get into this spot? I played myself. But why am I facing off against this fierce foe? The faculty’s fault? No. Nobody signed me up for the course; nobody enrolled me by force. I thought I that I could excel at this big school? Fool. I played myself. [Apologies to Ice-T.]

February 27, 1992

I was studying yesterday in Sproul plaza, sitting on a bench, and an old man came and sat down by me, with nothing to occupy him but people watching. Eventually we had some conversation: he’s 85 years old (didn’t look it!) and from Russia. He didn’t seem to recognize Lolita, which I was reading, and was surprised at my choice of the English major, having studied engineering himself. He says in Russia, those with a college degree are admitted to a special grocery store that those without a degree are not. Same prices in the alumni-only store, but much vaster variety and availability of goods. He didn’t say how the store vets these people, and I didn’t ask.

During the big rains we had a week or so ago, I parked my bike under the bridge between LeConte Hall and Birge Hall, just east of Sather Tower, before going into Doe Library (through the back entrance, as a construction project has blocked the front and snarled most paths through campus). It wasn’t raining that afternoon but my precaution was well taken: when I finally left the library in the late evening, the rain had started up again. Groggy from my scholastic haze, I was shocked to find that nature and weather and the out-of-doors had all continued without me. Riding down Bancroft, I was impressed by the electrifying effect the rain had: extra-shiny reflections on the cars, and extra-black asphalt with a neon-like red reflections of taillights.

In five minutes I’ll leave go to tutor at Malcolm X school. My student, “Eddie,” is trying to imitate my out-loud reading by going as fast as he can. This means the words come out at the same pace as before, but with a tone of frantic urgency and almost no pause between words. I sometimes worry that he isn’t retaining what he has read, but last week we worked together on a book report and I found he’s getting most of it. His dopey teacher had acted like he’s a hopeless case, totally checked out, etc. but I find he works pretty hard if someone’s around to help him focus.

May 25, 1992

Doesn’t it piss you off when you get a defective band-aid? At the bike shop we have Curad. As you know, these are not the band-aids we grew up with, and I find myself somewhat hostile to them. Their lack of quality control is one of the small but nagging travesties that plague my employment at the shop. I would say about one in three Curad band-aids is defective. The little sanitary cotton pad is skewed, and sometimes has missed the center of the adhesive portion, so you get just a little triangle of pad, and the rest is free to stick to the wound. I really can’t believe the bandaging public tolerates Curads at all. At home I use Johnson & Johnson Band-Aid brand. This becomes expensive since I’m constantly washing dishes or taking my contact lenses out or something. I’m tempted to just leave the wet band-aids on and let them dry out, but I called Johnson & Johnson on their toll free number and asked about this. “You know how the box says they’re waterproof?” I asked. “Oh, yes, they certainly are,” said the lady earnestly, in her charming southern accent. “Well, does that mean I don’t need to change them once they’re wet?” I asked. “Oh, no, you should always replace them—that’s the only way to prevent bacteria from infecting the wound,” she replied. Puzzled, I asked, “Then what’s the benefit of their being waterproof?” A long pause. Finally she said, “Well, if you’re swimming you won’t lose them in the pool. And, they won’t go down the drain.”

September 12, 1992

I have purchased Lila - An Inquiry into Morals by Robert Pirsig, author of the classic Zen & the Art of Motorcycle Maintenance. I hope this second book is good, but I have little faith that it’ll live up to its predecessor. I really loved the Motorcycle book, but the really lame Epilogue, which Pirsig attached to it like a decade later, irritated me so much that I tore it out of the book. This act was, I’ll confess, tantamount to destroying knowledge and human thought itself. Even worse, it loosened the cheap glue binding on the whole book, so that eventually all the pages started falling out—a disaster, especially since this is the one book I really wanted to pass around among my friends. It’s a really shoddy paperback to begin with, from the imprint “BANTAM NEW AGE BOOKS: A Search for Meaning, Growth, and Change.” Other Bantam New Age editions include Ecotopia, Shambhala: The Sacred Path of the Warrior, and The Complete Crystal Guidebook. What bothers me isn’t so much the nature of these books by themselves—although that alone is annoying—but rather the very idea that Bantam could integrate so many conflicting and discrete books into a single group, as if they could all be united as life philosophies. Like somebody is going to just go right on down the list, finding Meaning, Growth, and Change in every one of these. It’s tempting to think that when Pirsig wrote Zen and the Art of Motorcycle Maintenance, he would have winced at having his work co-opted into the Bantam New Age menagerie. But actually, the epilogue that he added later totally smacked of the easy, wildly speculative, faux-spiritual sentimentalism that the “NEW AGE BOOKS” line can be presumed to have. Who knows, maybe Pirsig got cocky; after all, his book sold like crazy and impressed a lot of people, many for perhaps the wrong reasons. Anyway, I still have the decrepit Motorcycle paperback, and without the Epilogue it is a work of pure genius. I’ll let you know how Lila ends up going.

—~—~—~—~—~—~—~—~—
Email me here. For a complete index of albertnet posts, click here.

A.I. Smackdown — English Major vs. ChatGPT - Part 2

Introduction

In my last post, I considered the writing prowess of ChatGPT, the A.I. text generation platform powered by OpenAI’s GPT-3 engine. A professor quoted in Vice magazine said GPT-3 could get a B or B- on an MBA final exam, which I figured had to be an exaggeration. So, I put ChatGPT through its paces, having it write paragraphs in the style of a scholastic essay, a magazine article, and a blog post. In this essay, I’ll tackle a final writing category: poetry. At least when it comes to very logical matters such as rhyme and meter, A.I. ought to do really well … right? Well, let’s see how it does. (Hint: very poorly. And, I suppose I owe you a trigger warning: ChatGPT seems to think violence to one’s genitals is funny.)

But before I get to all that, I will address a pressing question: who cares about any of this? And why should we? I’ll also address a few follow-up questions from the friend who prompted my last post.

Who cares? And why should we?

In response to my previous post, my software maven friend suggested that A.I. could be used effectively for composition if the user (i.e., the person who’s tasked ChatGPT with responding to a query) has enough expertise to evaluate the response and wisely choose what to use from it, and what to discard. In this way, my friend suggests, “this version [of ChatGPT] could make someone who knows what they’re doing more productive.” He continued, “I wonder if for your next blog you might consider how you might use it? Would you be willing to use it as a first draft in responding to a low performing colleague who asks trivial questions?”

I have two responses to this: a practical one and an ideological one. On the practical side, I can’t imagine starting a work email, proposal, or report with ChatGPT because in my experience so far, most of what the A.I. does is apply window dressing and rhetorical flourishes to the ideas I feed it, along with vague assertions that aren’t backed up (e.g., “[Dura-Ace’s] sleek and understated style has been well-received by riders and industry experts alike”). ChatGPT builds repetitive, junior-high-grade essays that fill out the page but don’t add much value to the original prompt. If I were to obtain my rough drafts from ChatGPT, I would have to prune most of the text to end up with something reasonably concise. It would be faster just to write my own missive from scratch.

I realize this may not be true for everyone, and I’ll grant that I have developed, through decades of practice, uncommon facility with writing (having composed over 1.5 million words for albertnet alone). Nevertheless, the ability to quickly draft a work email or brief report is, I believe, a capability that any adult ought to have, just like being able to fry an egg, drive a car, or brew a good cup of coffee. To my mind, increased efficiency should be a matter of personal development, not outsourcing.

The ideological matter is more complicated. If we decide that producing a work document is the kind of hassle that should be dispatched with as little time and energy as possible, like submitting an expense report or making travel arrangements, we are diminishing the assumed value of that activity. As we prepare the next generation for the workforce, this sense of diminishment would trickle down to our schools. We would be sending students a message that writing is a job for A.I. and that the higher-value human thought lies elsewhere.

Having majored in English in college, I naturally bristle at this idea. I believe that reading and writing, more than so perhaps any other endeavor, teach us how to think. I’ve blogged before (e.g., here) about how strongly I disagree with American society’s obsession with STEM, as opposed to the traditional liberal arts that are all but dismissed in modern education. To those who promote STEM, I’d like to ask, what would you think about discontinuing most math classes in school, since we have calculators and spreadsheets to do that crap for us? Of course you wouldn’t support this, and neither do I. (I took a Calculus class in college just for the hell of it.) Studying math is good for your brain, even though most of the specific math skills you learn will never be used. Studying the craft of writing is also good for your brain, and using words well is a skill we can use every day of our professional and personal lives. Writing is hard, and takes time, sure. But when we strive to write well, we understand better, and we think more deeply.

Here is an interesting quotation from the American philosopher Alasdair Macintyre, quoted in the New Yorker, describing his misgivings about the Enlightenment:

It becomes impossible to settle moral questions or to enforce moral rules; the best we can do is agree to disagree. Such a world falls into the hands of managers and technocrats, who excel at the perfection of means but lack the tools with which to think deeply about ends.

I don’t have strong opinions about the Enlightenment, and MacIntyre was writing in the ‘80s, but I think that last sentence fits modern tech companies, particularly in the realm of A.I. development, rather well. What we see in tech is a lot of people asking “how.” How do we monetize Internet traffic, how do we create algorithms that increase this traffic, how do we increase platform dwell time, how do we make people forward more stuff, how do we make social media products more addictive. I don’t see a lot of people asking “why” or, crucially, “why not.” If we outsource writing to A.I., how will people learn to think more deeply and broadly, a capacity we may need now more than ever?

Okay, on to my main topic now. As you shall see, ChatGPT’s attempts at poetry show, in a particularly stark way, just how totally overrated this platform is today.

Shakespearean sonnet

When poetry is good, it can be transporting (think Shakespeare, Dickinson, and Eminem). But when it’s bad, it can be appalling (think Vogon poetry, the feared method of torture described in The Hitchhiker’s Guide to the Galaxy). Obviously this is largely a subjective matter, so in my analysis I’ll look mainly at what can be objectively measured: proper execution of meter and rhyme. This is highly logical stuff, almost mathematical, so it ought to be right up A.I.’s alley. I started with a classic form: the Shakespearean sonnet.

Now, in case you’re not familiar with that poetic form, A.I. is here to help. At least, it’s supposed to be. I asked ChatGPT, “What is a Shakespearean sonnet?” It replied:

A Shakespearean sonnet … consists of 14 lines and follows a specific rhyme scheme and meter... The structure of a Shakespearean sonnet is as follows:

• Three quatrains (four-line stanzas) with a rhyme scheme of ABAB CDCD EFEF
• A final couplet (two-line stanza) with a rhyme scheme of GG
• Iambic pentameter meter, which means each line has ten syllables with a pattern of unstressed and stressed syllables

This description is pretty good (after I truncated it), though ChatGPT doesn’t get any special points for providing this, since any Google search could lead to you such an explanation, or a far better one such as this. What was missing from ChatGPT’s definition is a more specific explanation of which syllables are stressed vs. unstressed. (Get this backwards and you’ve got trochaic pentameter, which is totally different.)

So next I asked ChatGPT, “Please explain to me how to write a poem in iambic pentameter.” It came back with this:

[Misc. prelude omitted here for brevity.] An iambic foot is a set of two syllables where the first syllable is unstressed, and the second syllable is stressed. Here's an example of a line in iambic pentameter:

“To be or not to be, that is the question.”

[Misc. pointless repetition omitted.] Count the syllables in each line. Each line should have exactly ten syllables. Vary the stress pattern slightly to avoid a monotonous rhythm. [More BS omitted.]

Here, ChatGPT presents probably the most famous line from Shakespeare, rather than a really appropriate one. The line above is a poor example because if you count the syllables, you’ll see there are actually eleven, not the “exactly ten” ChatGPT correctly said there should be. In that line, Shakespeare broke the rules on purpose, to cause the reader and/or theater audience to stumble. This was to draw attention to the word “question,” which in the context of existence is the whole point of the soliloquy. Great writing, but not a great example if you’re really trying to understand iambic pentameter. “Shall I compare thee to a summer’s day” would be a far better choice.

Okay, sure, that’s a bit nitpicky, but the instruction to “vary the stress pattern slightly to avoid a monotonous rhythm” is completely wrong. If you vary the stress pattern, it’s no longer iambic pentameter! And the notion of monotonous rhythm? Total bullshit! Consider Shakespeare’s Sonnet 18, here. It is absolutely flawless iambic pentameter—not a single syllable out of place—and it’s brilliant throughout, not monotonous whatsoever.

Now, you might wonder what ChatGPT meant about “ABAB” (etc.) rhyme scheme, so I asked it, “What is an ABAB rhyme scheme?” It replied:

An ABAB rhyme scheme is a specific pattern of rhyming words in a poem or song. It indicates that the last word in the first line of the poem or stanza rhymes with the last word in the third line, while the last word in the second line rhymes with the last word in the fourth line, and so on. In this rhyme scheme, the letters “A” and “B” represent different rhyming sounds. For example, in the following stanza:

I walked along the beach in the bright sun,
And listened to the waves as they did run.
The sand was warm and soft beneath my feet,
And seagulls flew overhead in the heat.

The words “sun” and “run” rhyme, so they are represented by the letter “A”, while the words “feet” and “heat” rhyme, so they are represented by the letter “B”. This pattern continues throughout the poem or stanza, creating a consistent and pleasing rhyme scheme.

Did you catch that? How full of crap ChatGPT was just there? If not, let me make it a little clearer: let’s take those A and B labels and apply them to the four lines: you’d have A for “sun,” and A for “run,” and B for “feet,” and B for “heat.” It’s AABB. It’s not ABAB. It doesn’t match the first paragraph of ChatGPT’s response. And it’s not the rhyme scheme of a Shakespearean sonnet. (It’s not even the rhyme scheme of a Petrarchan sonnet, which is ABBA. It’s just a rhyme scheme ChatGPT kind of made up, which it uses for every poem I’ve seen it write.)

We have established that ChatGPT totally blew it at describing a Shakespearean sonnet. So how does it do when actually writing one? I told it, “Write a quatrain in iambic pentameter, with an ABAB rhyme scheme, followed by a rhyming couplet, also in iambic pentameter, about post-urinal drip. Try to make it funny.” Here’s its response.

Inevitable, yet always a surprise,
Post-urinal drip can make one despise
The feeling of wetness that lingers on,
A sensation that’s not easily gone.
It’s a cruel trick of the human form,
To leave us damp after we perform.
But fear not, my friends, for there’s a way out,
Just shake it off and give it a good clout!

Oh. My. God. Is this the same priggish ChatGPT that, as mentioned in my last post, balked at writing humorously about how bad a laxative drink tastes, claiming “I cannot provide humorous anecdotes about sensitive medical procedures” and “I do not generate inappropriate or insensitive content”? It’s talking about violence to one’s genitals! I had to look up “clout” just to make sure there isn’t some alternate meaning that wouldn’t be this awful. A.I. is advocating, albeit jocularly, giving one’s penis “a heavy blow with the hand or a hard object.” WTF?! That’s not funny at all!

Meanwhile, ChatGPT simply didn’t follow my instructions. I asked for a quatrain followed by a couplet. That’s six lines total; it gave me eight (i.e., two quatrains). The rhyme scheme is also not what I asked for. As for iambic pentameter, this poem is a train wreck. Certain brief phrases (e.g., “To leave us damp,” “Just shake it off”) are iambic, but not a single line of the poem achieves this meter consistently. The very first word, “inevitable,” is fundamentally incompatible with iambic pentameter. Chat GPT just wrote whatever the hell it felt like in a very loosey-goosey meter of its own design. If you’re not getting my point, read the above poem aloud and see how hung up you get. Then compare it to this example of an actual iambic pentameter quatrain and couplet, penned by a human:

Relax, because you’ve earned your potty break;
Unburden your poor bladder of its pee.
And when you’re done you’ll shake and shake and shake;
An effort all in vain, it seems to me.
     For urine flow can never really stop,
     Until your undies drink the final drop.

Note that this second example doesn’t resort to crude ideas like clouting your penis. And note how naturally the poem gallops along because it truly follows the meter. Also notice that it doesn’t have vague throwaway notions like “A sensation that’s not easily gone.” Then consider that I wrote those lines (full poem is here) when I was only seventeen. I guess someone accustomed to the crap poems printed on Hallmark cards might be impressed at ChatGPT’s effort, but I’m not. It’s almost cynical how casually it breaks all the rules, including that of decency.

Dactylic trimeter

A.I. learns through being fed “training data” from the Internet. In case its struggle with the sonnet was based on bad information, the Shakespearean form being a very popular one, I decided to give it another shot, with dactylic trimeter, a much rarer form I have come to enjoy. I asked ChatGPT, “Please explain how to write in dactylic trimeter.” It responded:

Dactylic trimeter … consists of three dactyls, or three stressed syllables, followed by an unstressed syllable, in each line… Count the syllables in each line. Each line should have exactly three dactyls, or three stressed syllables, followed by an unstressed syllable. This means the line should contain a total of seven syllables. 

The description above is completely wrong. A dactyl is not a stressed syllable. It is a three-syllable foot in which the first syllable is stressed and the second two are not. A line of dactylic trimeter has three feet, with three syllables per foot, for nine syllables total, not seven. And even if a line did have three stressed syllables followed by an unstressed syllable, that would be four, not seven. Is ChatGPT just stupid? If I have to start reading work emails written by ChatGPT, I think I’ll just blow my brains out.

Okay, let’s see how A.I. did at actually composing this type of poem. I told it, “Please write a 10-line poem in dactylic trimeter about bike riding up two very difficult climbs, called El Toyonal and Lomas Cantadas, celebrating caprice and radical freedom.” It produced this:

Pedaling up Toyonal, heart pumping fast
My mind is clear, free from the world’s contrast
With caprice and freedom, I take each turn
Pushing through pain, for what I will earn
Onward I climb, up Lomas Cantadas
My legs scream out, but my spirit never fades
The wind in my hair, the world fades away
A moment of peace, that I long to stay
And at last I reach the summit high
A sense of triumph, that no words can deny

You can see right away what an awful poem this is. It’s what Thomas Kincade would produce if he were a writer instead of an “artist.” I mean, “free from the word’s contrast”—what does that even mean? And “the wind in my hair”—seriously? What is this, a Harlequin romance novel? Lomas is a 10% grade, and I’m wearing a helmet! But what particularly stands out is that again, ChatGPT didn’t follow my prompt whatsoever. In the entire poem, only two of the feet are proper dactylic trimeter (“pushing through” and the first three syllables of “Lomas Cantadas”), which is surely just luck. As it did with the sonnet, ChatGPT just wrote whatever the hell it felt like. So why does everybody praise ChatGPT so much? It sucks! (For a proper poem on this topic, with actual dactylic trimeter, click here.)

One more thing

Okay, I can almost hear you now: “Oh, this particular chatbot is just using GPT-3! The technology getting better all the time! All the glitches you’ve found will soon be fixed! The next version’s gonna be amazing!”

Well, maybe GPT-4 (etc.) will get better at poetic meter, and maybe it’ll learn how to be more concise. But I could also imagine its errors getting propagated further. Remember, GTP-3 learned mostly from training on massive amounts of human output from across the Internet, and (as I learned from my software maven friend) has over 100 billion parameters allowing it in some sense to memorize an enormous portion of its training set. Over time, as more people outsource their writing to A.I., its errors could be added to the pile of training data, and thus reinforced. Meanwhile, the content may stray ever further from that created by humans. The growing body of text on the Internet may come to have less and less to do with us—that is, with creators who have a soul, and a conscience. It’s tempting to hope that somehow the works of great writers will one day be scored higher somehow, to help the A.I., but why would we expect this when politicians, the media, and academia are kicking liberal arts to the curb? Meanwhile, most social media platforms today seem to prize forwards and re-posts as the most valuable Internet currency, so if any scoring were to be applied to A.I.’s learning, it’s probably more likely to be whatever gets a rise out of people—i.e., trolling and other bombastic vitriol.

As ChatGPT and its ilk gain ever more traction, what passes for writing could become, to borrow a phrase from Nabokov, the “copulation of clichés.” (He was talking about pornography, but the metaphor holds here, too.) As the data set A.I. uses becomes more and more generic, while the tool gets used by more and more people seeking to avoid engagement with the craft of writing, most real insight and individuality might gradually vanish from written correspondence. O brave new world!

Other albertnet posts on A.I. 

• I, Chatbot
• Almost Intelligent – Part I
• Almost Intelligent – Part II
• Smartphones & Artificial Stupidity
• A.I. Smackdown – Moto vs. Cortana vs. Siri
• Could Artificial Intelligence Replace Writers? – Part 1
• Could Artificial Intelligence Replace Writers? – Part 2
• Could Artificial Intelligence Replace Writers? – Part 3
• A.I. Smackdown – English Major vs. ChatGPT – Part 1
• Will A.I. Steal Our Jobs?
• Tech Check-In - How Good is the Latest A.I.? - Part I
• Tech Check-In - How Good is the Latest A.I.? - Part II
• What is ChatGPT Great At (and Not)?
• Tech Reflection – Two Sides of AI
• AI Smackdown – ChatGPT vs. Copilot vs. Gemini
• More AI Smackdown - ChatGPT, Copilot, & Gemini Write Poetry

—~—~—~—~—~—~—~—~—
Email me here. For a complete index of albertnet posts, click here.