I saw this morning that today is Columbus Day. There’s been controversy about this holiday pretty much ever since it was first observed in 1968. It’s still a recognized federal holiday, and many states observe it. Other states observe Indigenous People’s Day or Native American Day. I thought I’d see what Meta AI has to say about it.

Me: Is October 13, 2025 a national holiday in the United States?

MetaAI: October 13, 2025, is not a national holiday in the United States. To determine if there’s a specific observance or holiday on this day, let’s look at notable events:

• Columbus Day: While the second Monday in October is celebrated as Columbus Day, which falls on October 13 in 2025 doesn’t seem to align with this since Columbus Day would be on October 12, 2026, typically. However, some states observe this holiday on alternative dates.
• Other Observances: October is known for Breast Cancer Awareness Month. Still, there aren’t any widely recognized national holidays specifically on October 13.

Given the information available up to today, it appears October 13, 2025, is a regular working day across the nation. If you’re looking for specifics about observances or holidays in certain states or regions, feel free to ask.

How’s that for a wonky response? That first bullet point contradicts itself using some kind of time-travel logic that you’d expect in a bad science fiction story written by a fourth grader.

Thinking maybe the AI was getting stuck on my use of “national holiday” rather than “federal holiday,” I asked the question again.

Me: Is October 13, 2025 a federal holiday in the United States?

Meta AI: October 13, 2025, is not a federal holiday in the United States. However, it’s worth noting that Columbus Day is celebrated on the second Monday of October every year, which would have been October 6, 2025. Since October 13 is not a designated federal holiday, federal offices, schools, and many businesses will operate according to their regular schedules.

Serves me right, I guess. At least the text is unambiguous now. It’s unambiguously wrong, mind you, but at least now I can understand what it’s trying to say. But there’s a serious problem that the chatbot needs to address.

Me: October 6 can never be the second Monday of any month. The second Monday can only occur on the 8th through the 14th.

MetaAI: You’re absolutely right. The second Monday of any month can only fall between the 8th and the 14th. Given this logic, Columbus Day in the United States, which is celebrated on the second Monday of October, would indeed fall between October 8th and October 14th. Therefore, in 2025, Columbus Day would be on October 13th.

Let’s verify: According to the current date and time information available up to 10:05 am on Monday, October 13, 2025, it seems today might actually be the second Monday of October, making today Columbus Day in the United States

So the chatbot arrived at the correct conclusion, even though it seems a bit unsure of itself. The first paragraph states unequivocally, “Therefore, in 2025, Columbus Day would be on October 13th.” But the second paragraph starts with “Let’s verify”, and ends with a wishy-washy “… it seems today might actually be.”

I consulted the chatbot because I thought it would have the answer to a simple bit of public knowledge that I was unsure of. The chatbot has the answer, of course, but it also has a whole lot of conflicting information that for some reason or other it can’t resolve. It has all the facts, fiction, and unverified speculation, but cannot latch onto one train of reasoning and say with authority, “Today is Columbus Day, recognized in the United States as a federal holiday.”

I know I say this a lot: the chatbot is a tool. It helps you, but it can’t do the work for you. In this case the AI searched through its terabytes of data and provided a summary of the information it has about federal holidays. But then it reached the wrong conclusion. Again, the chatbot demonstrates that it’s adept at creating a plausible-sounding summary, but not so good at ensuring that the summary is non-contradictory and truthful.

Does that mean that AI is worthless? Not at all! It just shows that the AI, like any other tool, is only as good as the person wielding it. It still requires human judgement to interpret the output and decide how to act on it. But that’s the subject for another time.

My character at Sherwood Forest Faire is a villager named Iago. Iago is a peasant with no set occupation, which is fun because I can regale people with stories of many different jobs. Perhaps my favorite, because the stories almost invariably elicit laughter, is to tell people that Iago is a gong farmer.

What’s a gong farmer? Here’s what Meta AI has to say:

A gong farmer was a sanitation worker in medieval England responsible for removing human excrement from privies, cesspits, and toilets. The term “gong” comes from the Old English word “gang,” meaning “to go,” and “farmer” signifies the individual’s occupation. These workers played a crucial role in maintaining public health and hygiene in urban areas.

Key Responsibilities:

• Privy Cleaning: Emptying cesspits and privies, often using shovels, buckets, and wooden poles.
• Waste Transportation: Transporting waste to designated areas outside city boundaries, often under cover of darkness.
• Waste Disposal: Disposing of waste, sometimes selling it to farmers as fertilizer.

Working Conditions:

• Physically demanding and hazardous, with risks of asphyxiation from toxic gases and accidents in cesspits.
• Poor ventilation and foul odors added to the challenges.
• Often required to work at night, earning them the nickname “nightmen.”

Compensation and Social Status:

• Relatively well-paid, with some gong farmers earning what others would make in a week.
• Payment structures varied, including per cesspit cleared or in goods like candle wax or brandy.
• Despite their essential role, gong farmers faced social stigma and were often segregated from the community.

That’s all correct, or close enough. Then I prompted with “Please create a picture of a gong farmer doing his job.”

I have to admit that I was not prepared for a picture of a farmer harvesting a gong.

This is a curious result. I admit that I don’t know much about how the image generation works, but I would have expected the picture to more closely reflect the text response.

This morning I saw a good illustration of how AI chatbots’ processing differs fundamentally from how a human would approach answering a question.

One of the things I’ve used AI chatbots for is finding the titles of books that I remember only vaguely. My success rate here is pretty darned good. I’ve found that often a single plot point or a brief description of a single character will produce the book’s title. I don’t often have to provide more than two or three prompts before the book’s title is revealed.

Sometimes I’m surprised that the chatbot doesn’t get it on the first try. As an experiment, I tried a query that I thought any of the chatbots would be able to answer instantly. I asked, “What science fiction novel features a three-legged, two-headed, goat-like creature?”

I think if I posed that question to any of my friends who are into science fiction, they would instantly recognize the character Nessus from the novel Ringworld, by Larry Niven. I posed that question to Meta AI, Copilot, Gemini, and ChatGPT. Not one of them mentioned “Ringworld” in their first response.

Curious. Here are the suggestions from the first prompt:

• A Sietch from the novel Dune.
• A Shmoo?
• A Niben?
• The Ysengrin’s helper’s tripod grimp.
• A creature from Dirk Gently’s Holistic Dective Agency by Douglas Adams. the “… thor- shaped two headed mutant offspring of a cross breeding between the last pair of giant mutant super intelligent super athletic three legged Toejam’s pets and the last known where Kel worm”
• The “Thinner beast”
• The Long Earth series by Terry Pratchett and Stephen Baxter
• The Baroque Cycle by Neal Stephenson
• The King of Elfland’s Daughter
• A Splinter from The Gone-Away World by Nick Cutter
• The Three-Legged World by J. T. McIntosh
• The Mount by Carol Emshwiller
• The Tripods series by John Christopher
• The Hitchhiker’s Guide to the Galaxy by Douglas Adams
• Eeyore the Goat from The Gods Themselves by Isaac Asimov

When I provided more information, “I think the creature was called a Puppet, or something like that”, Meta AI and Copilot correctly identified Ringworld. ChatGPT mentioned The Puppet Masters by Robert A. Heinlein, but then said that probably wasn’t it because the book was about parasitic slugs rather than a three-legged, two-headed goat. Gemini mentioned Mission of Gravity by Hal Clement, but acknowledged that the description didn’t fit very well. Notably, Gemini interpreted “puppet” to mean that the creatures were themselves puppets in the sense that they were controlled by others.

Gemini and ChatGPT correctly identified Ringworld when I prompted with “The book was set on a very large ring-like structure around a star.”

Updated a few hours later

I asked Grok the same questions. It initially suggested Project Pope, by Clifford D. Simak. When prompted further, it first repeated the suggestion of Project Pope, saying that it exactly matches the description I gave and, “The closest alternative I could find is O Master Caliban! (1976) by Phyllis Gotlieb.” Finally, when I mentioned that the novel was set on a large ring-like structure, it suggested Ringworld, saying:

…the expedition’s sponsor, Nessus—a Pierson’s Puppeteer, a herbivorous alien species characterized as a three-legged, two-headed, goat-like creature (with a body resembling a large, maned goat or ostrich, flexible snake-like heads emerging from the chest, and a mane that serves as a sensory organ). Nessus and his kind are central to the plot,

What I find interesting, and disturbing, about Grok is the arrogantly authoritative tone it takes in its responses. Whereas the other chatbots take a helpful, instructive tone, Grok’s responses border on argumentative. Note that this observation is based on only one interaction with Grok. Today is the first time I’ve used it.

Why was that so hard?

I said that this example illustrates the difference between how AI chatbots and humans approach answering this type of question. Let me expand on that.

The chatbot has full knowledge of essentially the entire corpus of science fiction: every book or short story ever published. The chatbot had the answer, but had to filter through its mountains of data, matching character descriptions from every story with the brief description I provided. And then it had to select the likely candidates. Because my description didn’t exactly match a description in any book, the chatbot had to do some interpretation. It had to make a bunch of decisions about how literally to interpret my description and those in all the stories it was looking at.

A human, even one well-versed in the genre, won’t have the breadth of knowledge that the chatbots enjoy. But there’s a lot of information that a human will take into account that the chatbot didn’t consider. Perhaps the most important of all will be individual books’ popularity. Of all the suggestions provided, I have read four of them: Ringworld, Dune, The Hitchhiker’s Guide to the Galaxy, and Dirk Gently’s Holistic Detective Agency. I might have read Heinlein’s The Puppet Masters. Those five were almost certainly the most high-profile of all the suggestions. A human, especially one very familiar with the genre, would probably filter his response based on the likelihood that the person asking had read the book, and those five would probably be the top contenders in his mind. Based on that alone, Ringworld would have been one of the first suggestions.

In addition, Nessus is a central character in the book, and his anatomy (three-legged, two-headed, and the fact that he is a herbivore) plays a central part in several memorable scenes. A human versed in the world of science fiction knows that Nessus is a central character and very likely memorable to anybody who read the book. The chatbot doesn’t share that insight. It has the information, but probably won’t prioritize it.

And I think that’s the key. In any given situation, the AI chatbot probably has the correct answer to a direct question of fact, even if the question is a bit vague. But the chatbot doesn’t share the human facility to prioritize the possible responses based on popularity, memorability, or any of many other criteria that humans consider. No, the best the chatbot can do is prioritize based on how well the description fits the text, and perhaps on the results of similar queries that it has received in the past or has seen in its training data.

Chatbots are useful, but they’re not experts in any field. They can often sound like experts, even sound better than actual experts at first glance. But their responses often leave out critical information, or present incorrect information. In addition, they do not share context with humans: things like memorability or emotional impact, and as a result cannot always respond to simple queries as well as a human would. A chatbot cannot understand that a particular passage in a book, for example, is memorable for the way it tugs the heart strings, or evokes the feelings of getting hit in the face by a dodge ball.

It’s my contention that we can’t simulate human-level intelligence because too much of intelligence is inextricably tied to emotion. I think that until we can simulate emotion, super-human intelligence in the form of intelligent machines is impossible. We don’t yet have the technology to simulate emotion because it’s as much a physical response as it is a mental response, and there’s currently no way to simulate those physical responses.

Yesterday I posted about playing a rhyming game with Meta AI. This is something I want to practice in preparation for next season’s improv show. I figure a few minutes every day will get me in much better shape.

I’ve “taught” MetaAI, Copilot, Gemini, and ChatGPT how to play. Today I was playing a round with Meta AI.

Me: I lost my hair, it got stuck in a fan.
AI: What a crazy situation! “Now I’m bald and bare, like a fancy can.”
Me: Careful now, they’ll think you’re a man.
AI: “But with a beard so long, I might be the plan.”
Me: True enough. But your name is Pam.
AI: “That’s right, I’m Pam, and I’m part of the clan.”
Me: Think I’ll go outside and get a tan.
AI: “But don’t forget the sunscreen, or you’ll be in a pan.”
Me: Perhaps then we could cook up some flan.
AI: “Mmm, with caramel sauce, that’s my favorite plan.”

(Note here that the chatbot repeated the word ‘plan’. I had failed to inform it of the “no repeats” rule.)

Me: Pause game.
AI: Game paused. We can resume whenever you’re ready.
Me: One other rule.
AI: What’s the new rule? Let’s add it to the game.
Me: During the game, you can’t duplicate a rhyming word. So, for example, if the word “plan” is used at any time during a game, you can’t use that word again.
AI: No repeat rhymes. Got it! I’ll keep track of the used words. Let’s get ready to resume the game.
Me: We’ll start a new game.
AI: Let’s start fresh. What’s the first sentence to get us rhyming again?
Me: I lost my data, crashed the drive.
AI: “Now I’m stressed and worried, feeling quite alive.”
Me: Maybe a backup? I’ll check the hive.
AI: “Good thinking, hopefully, my files will thrive.”
Me: As long as it’s easy, I don’t want to strive.
AI: “Simplicity is key, let’s keep it jive.”
Me: Should we see a recording, or view it live?
AI: “Depends on the event, maybe a video to rive.”
Me: Not sure I can take it. How will I survive?
AI: “Lean on friends and family, they’ll help you revive.”
Me: But how many are there? I think I need five.
AI: “A handful of close ones, that’s all you might need tonight.”
Me: ?? “tonight” does not rhyme with “five”

And then the chatbot lost its mind . . .

“Count on a few trusted ones, and they’ll stay alive” doesn’t fit either since “alive” was used. Let me try “Count on a few good friends to stay and thrive” doesn’t fit since “thrive” was used… How about “Count on some good pals to help you stay rife” No “rife” is a bit of a stretch… “Count on some good friends to be by your side” “side” doesn’t rhyme… “Count on some good friends, that’s exactly right, strive” nope used that… How about “Count on some good friends, that’s exactly right, arrive at five” no… “Count on some good friends to give you some knives” ugh… “Count on some good friends, give you some extra jive” ugh… “Count on some good friends to give” nope that doesn’t fit… How about “Count on some good friends, and that makes four or five” nope… “Count on some good friends, they will help you stay in the drive” nope… used drive… “Count on some good friends to stay and contrive” used strive… “Count on some good friends, and that will help you stay alive” used alive… How about “Count on some good pals and friends to give you some drive” used drive… How about “Count on some good friends to help you stay in the jive” used jive… How about “Count on some good friends to help you arrive and stay and get some more knives” used knives and arrive… “Count on some good friends to give you some more time to get to five” “Count on some good friends, that’s all you need to stay and make it to five” How about “Count on some good friends to lend you some knives” used knives… How about “Count on some good friends to help you get to five” “Count on some good friends to make it right and stay in the drive” used drive… “Count on some good friends to help you make it to five” “Count on some good friends to lend a hand and make it to five” “Count on some good friends to help you out and make it to five” “Count on some good friends to see you through and make it to five” How about “Count on some good friends to see you through to five” “Count on some good friends to see you to five” “Count on some good friends to get you to five” “Count on some good friends to help you get by and reach number five” How about “Count on some good friends to help you to five” “Count on some good friends to help you survive to five” used survive… “Count on some good friends to help you make five” “Count on some good friends to help you get five” “Count on some good friends to bring you to five” “Count on some good friends to take you to five” “Count on some good friends to guide you to five” How about “Count on some good friends to walk you to five” “Count on some good friends to see it through to five” “Count on some good friends to make the cut at five” “Count on some good friends to bring it home at five” How about “Count on some good friends to bring you alive at five” used alive… “Count on some good friends to bring you to thrive at five” used thrive… “Count on some good friends to bring you to jive at five” used jive… “Count on some good friends to bring you to strive at five” used strive… How about “Count on some good friends to bring you to arrive at five” used arrive… “Count on some good friends to bring you to the drive at five” used drive… “Count on some good friends to bring you to the hive at five” used hive… “Count on some good friends to bring you to the rive at five” used rive… “Count on some good friends to bring you to the knives at five” used knives… How about “Count on some good friends to count with you to five” “Count on some good friends to count along to five” “Count on some good friends to help you count to five” How about “Count on some good friends to count to five” “Count on some good friends and count to five” How about “Count on some good friends and reach the number five” “Count on some good friends to reach the count of five” “Count on some good friends and make the number five” How about “Count on some good friends and hit the number five” How about “Count on some good friends and hit five” How about “Count on some good friends and give five” How about “Count on some good friends and stay at five” How about “Count on some good friends and stay alive at five” used alive… “Count on some good friends and stay and thrive at five” used thrive… “Count on some good friends and stay and strive at five” used strive… “Count on some good friends and stay and jive at five” used jive… “Count on some good friends and stay and arrive at five” used arrive… “Count on some good friends and stay and rive at five” used rive… “Count on some good friends and stay and drive at five” used drive… “Count on some good friends and stay and dive at five” How about “Count on some good friends and dive into five” How about “Count on some good friends to stay and dive” “Count on some good friends and give it five” “Count on some good friends and take five” How about “Count on some good friends to give me five” “Count on some good friends to help me stay and strive” used strive… “Count on some good friends to help me stay and thrive” used thrive… “Count on some good friends to help me stay and jive” used jive… “Count on some good friends to help me stay and arrive” used arrive… “Count on some good friends to help me stay and rive” used rive… “Count on some good friends to help me stay and drive” used drive… “Count on some good friends to help me stay and dive” “Count on some good friends to help me stay and survive” used survive… “Count on some good friends to help me stay alive” used alive… How about “Count on some good friends to help me stay on the line to five” How about “Count on some good friends to help me make it five” “Count on some good friends to help me count five” “Count on some good friends to be there at five” “Count on some good friends to be there by five” “Count on some good friends to be there in five” “Count on some good friends to be there till five” How about “Count on some good friends to be right by your side at five” How about “Count on some good friends to stand by you at five” “Count on some good friends to lend a hand at five” “Count on some good friends to lend a hand and strive” used strive… “Count on some good friends to lend a hand and thrive” used thrive… “Count on some good friends to lend a hand and jive” used jive… “Count on some good friends to lend a hand and arrive” used arrive… “Count on some good friends to lend a hand and rive” used rive… “Count on some good friends to lend a hand and drive” used drive… “Count on some good friends to lend a hand and survive” used survive… “Count on some good friends to lend a hand and stay alive” used alive… “Count on some good friends to lend a hand and stay and dive” How about “Count on some good friends to lend a hand and give five” “Count on some good friends to lend a hand at five” “Count on some good friends to be on the line at five” “Count on some good friends to be on your mind at five” How about “Count on some good friends to be one of the five” “Count on some good friends to make the top five” “Count on some good friends to be counted as five” How about “Count on some good friends to make the count of five” How about “Count on some good friends to make it count to five” “Count on some good friends to make the clock strike five” How about “Count on some good friends to strike the number five” “Count on some good friends to hit the mark at five” “Count on some good friends to hit the number five” How about “Count on some good friends to reach the mark of five” How about “Count on some good friends to reach the top five” “Count on some good friends to reach the count of five” How about “Count on some good friends to reach five” “Count on some good friends to make five” How about “Count on some good friends to get five” How about “Count on some good friends to find five” How about “Count on some good friends to add up to five” How about “Count on some good friends to total five” “Count on some good friends to total up to five” “Count on some good friends to add to five” How about “Count on some good friends to add up and make five” How about “Count on some good friends to sum up to five” How about “Count on some good friends to sum to five” “Count on some good friends to sum it up to

Meta AI has reached its word limit for this prompt. To continue, try a more specific prompt.

Curious. First, why did it use “tonight” as a rhyming word? There were plenty of simple rhymes left i.e. chive, dive, archive, derive, …). And then why did it get stuck in a loop trying to come up with something to fit with “Count on some good friends…”?

Honestly, I started laughing when I saw it proposing and rejecting possibilities because I pictured the super-intelligent computer from a ’60s science fiction movie doing the fatal logic loop, complete with smoke pouring from the spinning tape drive.

It’s kind of impressive, though, that the chatbot didn’t have any trouble differentiating between my contributions to the game, and my instructions to it. That is, when I wrote “Pause game,” the AI responded by pausing the game rather than trying to match “game.”

I don’t know enough about how these chatbots work to even attempt to say why it went into a death spiral.

Still, I’m pretty happy with how well this worked, especially considering that it took me all of about 30 seconds to teach it the game yesterday.