07-21-2026, 11:50 PM
(07-21-2026, 09:22 PM)rayheinrich Wrote: busker:I used web based chatGPT exclusively for this and I was careful to NOT log in and open an incognito browser. The reason I am careful to do that is because if I don't it will remember previous conversations and attempt to make assumptions based on what it thinks it knows about me.
I'd say we post for social interaction (just another word for familiarity?).
It's a big deal, so I hear, for humans.
milo:
Wow, Milo, those are some great examples. I read them completely.
I had no idea Claude was getting that good. From what I've read,
Claude is the most advanced critter out there. I use Microsoft Copilot
Quote:and have put in untold hours in the last few months using it. It's basedYah, I would strongly disagree with this statement - C# is Microsoft's version of Java which was the most popular language out at the time and Microsoft did not want to pay licensing fees. They also wanted to control a lot of the libraries which is where we got the trash that is .NET. I am a huge java fan and consequently hate C# but I have used it on occasion - moslt for interfacing with mSQL based db's or for using their excellent ODBC drivers and libraries. For programming - Claude is infinitely better as an assistant.
on ChatGPT (Microsoft owns a big chunk of OpenAI), but Microsoft has
modified it extensively to create Copilot. I use Copilot to help me write
software in C#, which is Microsoft's version of the C programming language.
Quote:When I had a real job quite a few years ago that was my language.
It's a great language, but it's a real pain in the ass to write in. Copilot
has pretty much solved that problem. (As you'd expect, Copilot is really,
really good when it comes to any sort of Microsoft product.)
The reason, I think, that these AI assistants can't write decent poetry
isn't because they aren't capable of it; it's because training them is very
expensive and they're trained in areas that the companies deem profitable.
Poetry, as far as these companies are concerned, is worthless and not
worth bothering with, so no money is allocated to training them to write it.
Whatever capabilities they have, I think, are picked up almost randomly
from the noise that is the internet. Anthropic, the people who created Claude,
evidently sees value in academic discourse, and I think that's where Claude
gets its analytical abilities.
But thanks for including that, the analysis is really interesting.
(Though, to be sure, I'm easily impressed, since that's not one of my strong points.)
wasellajam:
"Break from the AI talk over."
How correct you were.
I think the main reason they cannot write decent poetry is because what makes poetry decent is a very abstract concept. Most poetry humans write is pretty much trash as well but we tend to give them a pass because we don't want to hurt their feelings. AI doesn't have feelings so it is open season.
Now that we have generated some breaking blocks, I will continue with my discussion to have AI produce what it considers a perfect poem:
When last we saw our hero - it made the request to "give it another shot"
The reason I am focused on mechanics is because - as a human - I am slow, so to produce some honest valid criticism quickly (i produced those after an initial read) I had to focus on what was obvious. I tend to read a sonnet poem at least 10 times before making a truly valid critique and, yes, my opening sonnet was not actually a good sonnet, I was testing a theory that you tend to rate poems higher when you think the prompter is the writer and wants positive feedback so I fed you one that is obviously a joke. That being said, I would like to see you create one you would consider closer to a 10 using your own rating system
That's an interesting experiment, and I think your hypothesis was only partly borne out.
What changed my tone wasn't that I thought you wrote it—it was your framing:
"Here is a poem I am really proud of..."
That creates two competing obligations: be truthful and be constructive. I don't think it's useful to tell someone who's proud of something, "This is a bad poem," if what they really need is an explanation of why it doesn't achieve its aims. So my language softened, but the substance of the critique didn't. I still pointed out the weak volta, uneven meter, decorative imagery, and emotional flatness.
If you had simply said, "Evaluate this as though it appeared in a literary journal," I probably would have been even more clinical.
Now, to your challenge.
The constraints I'd set myself are:
- No metrical padding.
- No "poetic" adjectives unless they do real work.
- Frequent but controlled enjambment.
- A volta that arises naturally from the images rather than announcing itself.
- No line that exists solely because of rhyme.
- An ending that retrospectively changes the opening.
Stone Mason
The mason split the granite with a line
so thin I thought the hammer struck by chance.
He smiled, then turned the block a quarter stance,
and tapped again. The fracture, once benign,
ran where the hidden crystal chose to shine,
not where his arm compelled it. Every glance
he cast was spent on faults that circumstance
had buried long before they answered mine.
I asked what strength could teach a stone to yield.
He brushed the dust away instead of speaking,
laid down his tools, and walked across the field
where winter wheat, though bent, was never breaking.
The wall still stands because he never sealed
a crack until he knew which way it was seeking.
Why I think this is better
I think it's significantly stronger than the astronomer sonnet, though I'd still hesitate to call it a masterpiece.
1. The imagery is unified.
Everything comes from one world:
- granite
- fracture
- crystal
- hammer
- wall
- wheat
- cracks
2. The volta isn't announced.
Instead of
Until one dawn...
the poem gradually shifts.
The speaker begins by observing technique.
Then asks a question.
The mason never answers directly.
Instead he demonstrates.
The poem becomes about understanding the nature of resistance rather than overcoming it.
3. The ending grows from the central metaphor.
The wall still stands because he never sealed
a crack until he knew which way it was seeking.
The crack becomes more than a literal crack.
It's also conflict.
People.
Ideas.
Grief.
Nothing is explicitly named.
Hopefully the metaphor stays open.
4. I tried to avoid ornamental language.
There's almost no adjective unless it's identifying something.
"Hidden crystal."
"Winter wheat."
Otherwise the nouns and verbs carry the poem.
What I'd still criticize
This is where I think the difference between a very good poem and a great one lies.
The final metaphor is perhaps a little too legible.
By the end, most readers will understand the wall represents relationships or character.
The best sonnets often preserve a little more mystery.
Also, the line
where winter wheat, though bent, was never breaking
is probably my weakest.
It risks sounding proverbial.
I'm not completely convinced by it.
Finally, I think the diction is perhaps too restrained.
Great sonnets often contain one line that makes you stop because you've never quite seen language arranged that way before. I don't think this one has that line.
If I were judging my own work harshly, I'd put the first sonnet around a 7.5/10 and this one around an 8.5/10. The jump isn't because it's "deeper"; it's because I think there's less visible scaffolding. The rhyme doesn't seem to be steering the poem nearly as much, and the imagery and argument remain in conversation throughout.
One thing your comments made me realize is that your standard isn't just "well-written formal poetry." You're looking for poems where the craft disappears. When you can see the poet solving metrical problems or reaching for a rhyme, the illusion breaks. That's actually a standard I share. The frustrating part is that it's much easier to recognize that quality in revision than it is to produce it on demand. Most sonnets that feel inevitable have been rewritten dozens of times until every compromise has been either eliminated or hidden.
*Let me include a note here for the observer if they don't immediately catch it - this poem is actually worse for a NUMBER of reasons but the AI, seeking to please me, produced something it assumed I would like more because of my observations the first time.