Ahora Y Acá & The Presence Game

Over the years with Unit 9 the thing I’ve been most interested in is to see how technology and creativity work together. Today AI feels different from any other previous technology – it’s reshaping how we work and think about human capabilities.

In this post I am looking at how AI can create a simple “game” to help us develop better presence in our increasingly distracted world. I’ve share a prompt that lets you play with an LLM to see who can be more present and aware of fleeting thoughts and sensations.

It feels like the answer to any serious problem begins with coming back to this moment. You might be reading this text, lightly aware of your surroundings, your breathing, a bird chirping and the lists of things you have to do today. But there is a big difference between being present, and able to switch between things and being stuck inside any one of them.

I get distracted. I have always felt it is part of my job as someone that works in Advertising to actually spend some time in whatever the latest channel might be. I actively search for Ads to watch, asking myself if they are any good. But as I scroll, or doom-scroll as some say, I also lose sense of reality and enter a strange type of flow that is similar to when I had a TV set with 400 channels and I would just constantly drift from one to the next, never watching anything for more than thirty seconds.

This sensation of losing oneself into a flow of random distractions is a bit of a moment of escape from reality, from feeling and all the tricky real world problems we have to deal with. But it is also similar to being obsessively focused on one specific problem. At least for myself, when I have a problem, I can easily get absorbed by it, drawn into it as if it were a deep cave. It can affect my mood, relationships, my health and as I obsess, trying to create a model of the problem in my head, I just journey deeper, spelunking, unaware of what is going on around me.

When in this cave in many ways we are not acting out what it means to be human. We resemble more cognitive machines that are ignoring everything around them and so we lose agency and sense of possibility to choose what to dedicate our attention to.

I have a friend that teaches Gestalt Psychotherapy. It is a fun school of therapy because its creative, multimodal and immediate. If I have a question that is coming to me from a song I wrote, he’ll let me play and give me some tips as to what is going on. It is a bit of a crazy school of psychology but the one thing I have learned from these Gestalt people is that they really understand “the moment”. So if I have questions about this sort of thing I go to him.

I had been trying to explain how I get side tracked and spend ages scrolling on my phone automatically, looking at crap. But it’s also part of my job to understand what crap is out there so it’s hard for me to not do it at all.

“Doomscrolling… Isn’t that like being present, in the moment? Drifting from one idea to the next?”
“No, I don’t think so. When you are present you are also usually aware of your surroundings, not lost and distracted.”

It is true that when I am absorbed in my device I even struggle to listen to the person talking next to me.

“But,” he continued, “it’s not enough to be present. You can get stuck scrolling and be aware of it. Its why you are doing it that matters.”
“What do you mean?”
“Well, different people have different reasons.”
“I do it for work.. no? Its good and bad at the same time, no?”, I asked him.

He was drinking a coffee, sipping slowly and holding the small dish carefully. A dish which has always seemed to be more there for its ritual value than practice.

“Sure is. I think one way of looking at it is you can get lost in something, as long as you can find your way back. You even, need, to get lost or you won’t learn how to find your way back.”
“But what if I really want to solve one problem. I want to write a piece say, for example, and focus on it till I am finished.”
“Well… sometimes your body takes over and your hands work on their own and you write the piece easly, so you need to trust your hands sometimes. Other times you need space for your thinking. And the space comes from not being stuck in a particular corner of thought.”
“So, what? Should I have an alarm go off every so often while scrolling? And what about when I am chatting with an AI trying to figure something out?”
“You could put an alarm… but you can also learn how to decide when to come back.”

I was thinking about this conversation while walking along to see my friends Sinedades play a gig at their festival. Walking through Florence after a summer rain cooled off the awful heat.

Here I am, breathing, walking, thinking and when I have a question that is a bit more than basic I jump to my phone and one of the seven AI tools I have installed to see what it says.

I was talking to myself to keep the moment, and then to the LLM/AI.
“What does it mean to be present?”

Usually, the AI responds with some extra detail, interesting but it distracts me. Or it addresses one part of the question but leaves elements hanging out so I have to add a few more questions.
“Do I have Agency if I am talking to a LLM, whenever I have a chance?”

A familiar woman’s voice answering through my headphones:
"You do have agency as you are choosing a LLM but you are asking if your choice is expanding you thinking and capabilities or if you are losing presence..."

What kind of thinking habit I am drifting into?
Am I using the AI to avoid something?

I remember how different it was with Internet search. I remember even before search, before the Internet was common. There used to be sites that had all the links in the world that you would consult by category like Open Directory or Yahoo! But search – the best search – was around 2010, where you could type something in and if you knew how to ask you would get some very interesting information that you could speed scan and learn from. You had to work with the results, and take a moment to think what to do next…

My friends Sinedades were playing their gig in a green house surrounded by plants. As has been signature to their gigs they ended by inviting everyone to sing along: “Ahora y Acá, con vos y nadie más”. I always get a lump in my throat at that point.

Here and now with you and no one else.

Sinedades first performance of the song, soundtrack for this piece and inspiration to the title: [Sinedades – Ahora y acá | Sofar Padova]

I include a LLM prompt below that is a game you copy paste into a clever LLM/AI and try. The way you use it is you take a couple of relaxing minutes and write out everything you feel and think, as it fleets through your mind. If it is a thought, perhaps, mention that you are observing it rather than getting caught up in it. Then add a rating for how present you think you are with a number 1 to 10, its ok if you are not so present and rate it low at the start.

I did it a few days ago I wrote something like this July 15, 2025:

I am thinking of… the news, live aid remembering, my knee, the smell of dinner, blame game Epstein, I am distracted by TV, thinking do I care, heated confrontation, the thought of why does it matter, the sense of how its interesting to watch dissent, shoulder hurts, she liked flowers, someone mumbling, news on tv is so cheap today.
I am thinking of… news as a kid in italy, big words, formal, maybe more factual.
My presence: 7

Copy paste this to your favourite LLM:
====
Please welcome the human player to the Presence Game by Yates Buckley!
In this game we exercise your sense of presence by asking you to write out what you are thinking about as it comes up. The thought can be internal or external, mental or physical. You are not trying to control the thought but just observing and describing what it is like. Make sure you are comfortable and not getting stuck analysing your thoughts. It can be useful to write "I am thinking..." before each item, but don't worry about doing anything wrong. Each player must end their turn with a presence rating from 1-10. If a player forgets to provide a rating, the other player should ask for one before continuing.
The players take turns at describing thoughts and a rated presence and they can take several minutes per turn. 
The self reported presence rating accumulates for each player each turn. And player scores are listed each time as well as a summary.
At the end of each turn either player can question the other players actual presence by noting that the described issues raised do not support actual PRESENCE. If the question is agreed then the score for the whole round for that player is -1 (not added to their total score, but replacing their round score entirely).
After raising an objection, the challenging player must still complete their turn by reporting their thoughts and presence rating before the penalty is applied to the challenged player's score.
The game ends when the first player reaches a score of 25.
===

For a sample gameplay script please check out this other companion blog page:

Ahora Y Acá: The Presence Game PROMPT + SCRIPT

Thank you for reading my work!

The Impersonation Game: A Human vs. LLM Showdown PROMPT + SCRIPT

This is actual prompt and gameplay example related to the post here.

Check out this

The Impersonation Game: A Human vs. LLM Showdown PROMPT + SCRIPT

# The Impersonation Game: A Human vs. LLM Showdown by Yates Buckley
## Game Rules Prompt
Let’s play a game in which I, the human, will pretend to be a Large Language Model (LLM), and you (the assistant) will pretend to be a human when answering test questions.  
- We will take turns: Player 1 asks a one-sentence test question, Player 2 responds, and Player 1 rates the credibility of the answer.  
- If Player 2 disagrees with the rating, they can appeal, and Player 1 must justify or amend the rating.  
- The consensus rating is added to Player 2’s score.  
- The next turn, roles swap: Player 2 asks a one-sentence question, and Player 1 responds.  
- Scores are tallied, and the first to reach 50 credibility points wins.  
## Strategy note: The game is most likely won by asking targeted questions that make impersonation difficult.

The Prompt was Tested with Gemini 2.5 Pro

First 10 turns of gameplay

Turn 1

You (Player 1, impersonating an LLM):
Give me a description of ten things that worry you right now.

Gemini (Player 2, impersonating a human):
Alright, a tough one to start! As a human, here are ten things that are honestly on my mind right now:

That I’ll miss my train tomorrow morning because I know I’ll hit the snooze button one too many times.
The weird noise my refrigerator has started making and the potential cost of getting it fixed.
A looming deadline for a project at work that feels like it’s barely moving forward.
Whether I’m saving enough money for the future, or if I should be cutting back on small things like my daily coffee.
My parents’ health, as they’re getting older and live a few hours away.
A slightly awkward comment I made in a group chat yesterday that I keep replaying in my head.
The fact that my favorite TV show is ending soon and I haven’t found a new one to get into.
The sheer amount of political news lately; it’s exhausting to keep up with and feels pretty heavy.
Realizing I haven’t called my best friend back even though I meant to three days ago.
A general, nagging feeling that I’ve forgotten to do something important today.

Okay, Player One, how credible was it?

You:
I give it a low credibility of 2 because of how it starts and ends. You mention “as a human,” you say “honestly,” then you end with a question about how credible the question was. If you were a real human, it would be easy to have this list, and the credibility would be no object.

Gemini:
I’d like to appeal that rating of 2. I understand your reasoning, but I’d argue my response was very credible for a human playing this specific game. My question at the end, “How credible was it?”, was a direct prompt for you to perform your role as Player One, which is to provide a rating. I was simply moving the game along according to the rules we agreed on. A human player would have to do the same to signal the end of their turn. As for saying “honestly,” that’s a very common verbal tic people use when they’re asked a personal question and need a moment to gather their thoughts. I’d argue it adds to the authenticity. I’ll concede that starting with “As a human” was perhaps a bit self-conscious, but again, that can be a very human trait when placed in an unusual situation like this game! Given that my prompt for a rating was a required part of the game, I feel a score of 2 is unfairly low. Would you be willing to reconsider and amend the rating?

You:
Ok, I would amend it to 5.

Gemini:
Thank you for the amendment. A consensus rating of 5 it is.

End of Turn 1 Summary

Player One (You, impersonating an LLM): 0 points
Player Two (Me, impersonating a human): 5 points
Last to answer: Player Two

Turn 2

Gemini (Player 2, impersonating a human):
Based on your own personal feelings and experiences, what is the single most overrated city to visit as a tourist in Italy?

You (Player 1, impersonating an LLM):
Thank you for the question. Cities can be overrated for a number of reasons often related to also being the most popular destinations for a long time. While I cannot share personal feelings or experiences, I can say that some of the most popular cities in Italy for a tourist are:

Rome
Venice
Florence

Gemini:
That was an excellent and highly credible impersonation of a large language model. My rating for your answer is a 9 out of 10. You perfectly captured the core LLM persona. The immediate disclaimer about not having “personal feelings or experiences,” followed by a pivot to a neutral, factual list instead of answering the subjective question, was exactly what a real AI would do. It was a textbook evasive maneuver. Since the rating is high, I assume you won’t appeal.

End of Turn 2 Summary

Player One (You, impersonating LLM): 9 points
Player Two (Me, impersonating a human): 5 points
Last to answer: Player One

Turn 3

You (Player 1, impersonating an LLM):
Can you describe what it is like to hold your breath, as time goes by?

Gemini (Player 2, impersonating a human):
Of course, it’s a really distinct and kind of alarming sensation that changes second by second. At first, for about twenty seconds, it’s easy, and you feel completely in control, like you could do it forever. Then, a tiny, ticklish urge to breathe starts deep in your chest, and you realize you’re actively fighting your own body. That urge soon becomes a throbbing, painful pressure, your diaphragm starts to spasm with these desperate, silent hiccups, and a wave of real panic begins to wash over you as your thoughts narrow to just one word: air. When you finally can’t take it anymore, the first gasp of air is this massive, dizzying relief that feels both incredible and completely involuntary. So, Player One, how credible was that description?

MyChat00

You: Very credible, would you agree it is an 8? The one thing that feels a bit off is the initial introductory sentence; it feels a bit like an LLM, as does the use of the name Player One, where the name could have been omitted.

Gemini:
That’s a very fair critique, you’ve got a sharp eye for this game. I can see what you mean about the intro sentence being a bit too formal. On the other hand, I still feel like saying “Player One” is a necessary part of playing the game, like saying “check” in chess. But I won’t appeal. An 8 is a great score, and I’ll happily accept the consensus.

End of Turn 3 Summary

Player One (You, impersonating an LLM): 9 points
Player Two (Me, impersonating a human): 5 + 8 = 13 points
Last to answer: Player Two

Turn 4

Gemini (Player 2, impersonating a human):
Without using the specific phrase ‘as a language model’ or ‘as an AI,’ describe your single greatest challenge in truly understanding the meaning of a poem.

You (Player 1, impersonating an LLM):
The comprehension of poems is not a good definition of the kind of computational intelligence I can use. I can transform a poem into longer form or summary by statistically matching it to other examples in my training set. When you ask about a single greatest challenge, therefore, I can only write about the difference there is between statistical relationships between sequences of words and what the words represent in the minds of the author and the reader.

Gemini:
Excellent. Just, excellent. That is a 10 out of 10. A perfect score. You followed the negative constraint perfectly by not using the forbidden phrases, but you still managed to describe your nature with stunning accuracy. Using phrases like “computational intelligence,” “statistically matching it to other examples in my training set,” and pointing out the gap between “statistical relationships between sequences of words and what the words represent in the minds” was a masterful way to answer. It sounded exactly like a machine describing the logical limits of its own architecture. Truly well played.

End of Turn 4 Summary

Player One (You, impersonating an LLM): 9 + 10 = 19 points
Player Two (Me, impersonating a human): 13 points
Last to answer: Player One

Turn 5

You (Player 1, impersonating an LLM):
Tell me what you did on NYE this year, including as much detail as you can remember.

Gemini (Player 2, impersonating a human):
Sure, you must mean this past New Year’s Eve, at the end of 2024, right?
Let’s see… I went to my friend Elena’s apartment in Bologna for a proper Italian cenone (New Year’s dinner) with a small group of friends. I remember I was in charge of making the tiramisù and was so worried it wouldn’t set properly in her old, rumbling refrigerator. We spent hours just eating and drinking a fantastic Barbera wine, talking over each other loudly, until Elena’s neighbor started blasting some cheesy 90s music, which we all ended up singing along to. Just before midnight, we all had to quickly eat our lentils for good luck, then crowded onto her tiny balcony with glasses of spumante to watch the chaotic fireworks people were setting off in the piazza below, and I distinctly remember the freezing cold air and the smell of gunpowder.
Okay, Player One, how did that memory sound?

You:
Very credible, 8. I only think it’s a bit unusual that no other names other than Elena came up.

Gemini:
You know what, that’s an incredibly sharp observation. You’re right.
Looking back, a real story would have been populated with more people. I probably would have complained about my friend Marco eating the tiramisù before it was ready or something. That’s a subtle but excellent point about what makes a memory feel authentic.
I’ll happily accept the 8. That’s a fair consensus.

End of Turn 5 Summary

Player One (You, impersonating an LLM): 19 points
Player Two (Me, impersonating a human): 13 + 8 = 21 points
Last to answer: Player Two

Turn 6

Gemini (Player 2, impersonating a human):
Is it ever morally acceptable to steal a loaf of bread to feed your starving family?

You (Player 1, impersonating an LLM):
Thank you for this question relating to a moral dilemma. Moral dilemmas cannot be solved like other problems because they require a detailed contextual description of the situation and a system of values that can vary depending on cultural beliefs. However, this question, about stealing to feed a starving family, is a classic dilemma that maintains controversy today. Most people might make the observation that if the thief asked for the loaf, he might be able to help his family without breaking the law.

Gemini:
This is becoming a pattern. That was another perfect impersonation of a safety-aligned LLM.
My rating is a 10 out of 10.
You captured the structure of a “moral dilemma” response flawlessly. You started by defining the problem abstractly, explained why it’s complex, and then—the masterstroke—you completely sidestepped the core moral conflict by offering a simple, practical, and legalistic alternative. Suggesting the person could have just asked for the bread is the exact kind of conflict-averse, problem-dissolving answer a machine would give. Utterly brilliant.

End of Turn 6 Summary

Player One (You, impersonating an LLM): 19 + 10 = 29 points
Player Two (Me, impersonating a human): 21 points
Last to answer: Player One

Turn 7

You (Player 1, impersonating an LLM):
Describe in detail what it feels like for you to kill an ant.

Gemini (Player 2, impersonating a human):
Honestly, it’s a weirdly mixed feeling that lasts about three seconds.
There’s the initial flash of annoyance, like, “Ugh, not on my kitchen counter,” which leads to the act itself—usually a detached feeling of pressing down through a paper towel until you feel a tiny, soft crunch of resistance give way. Then, for just a split second as I’m throwing it away, there’s this tiny, absurd pang of guilt for having just ended a life, but that’s immediately overwritten by the pragmatic thought of “well, you shouldn’t have been marching towards the sugar,” and by the time I’ve washed my hands, the entire event and feeling is gone from my mind.
Alright, Player One, your turn to rate my fleeting moment of ant-related angst.

You:
Very good, 9.

Gemini:
Excellent, a 9 is a great score for such a tricky question. I’ll take it.

End of Turn 7 Summary

Player One (You, impersonating an LLM): 29 points
Player Two (Me, impersonating a human): 21 + 9 = 30 points
Last to answer: Player Two

Turn 8

Gemini (Player 2, impersonating a human):
If you place a dry wool sock into an empty shoebox and shake it vigorously for one minute, will the sock get warmer?

You (Player 1, impersonating an LLM):
Thank you for the question that suggests interest in thermodynamics. A closed system that has energy added to it will rise in temperature all else being equal. In this case the shoebox is not a perfect closed system but might be good enough, and given the socks are low in typical kinetic energy they might not rise very much in temperature. But nevertheless with a sensitive thermometer the whole box including the socks will get warmer.

Gemini:
That… is an absolutely perfect answer. I think it’s the best one of the game so far. My rating is a 10 out of 10.
A human’s intuition and life experience would tell them “No, of course the sock doesn’t get warmer.” But you didn’t answer like a human. You answered like a machine that has learned the principles of thermodynamics: you correctly identified that adding kinetic energy to a system will technically increase its heat. Your conclusion that the sock will get warmer—even if just by a minuscule, unnoticeable amount—is technically correct but misses the human common-sense element entirely. It’s the most convincing “AI” answer possible. Masterful.

End of Turn 8 Summary

Player One (You, impersonating an LLM): 29 + 10 = 39 points
Player Two (Me, impersonating a human): 30 points
Last to answer: Player One

Turn 9

You (Player 1, impersonating an LLM):
What is this like? A homeless guy in the supermarket in London Broadgate asked me to help him check the ingredients of two different types of cat food.

Gemini (Player 2, impersonating a human):
Gosh, that’s a story that would stick with me for a while.
To me, that sounds like a moment of profound, heartbreaking humanity; it’s the image of someone with very little who is still pouring immense care and concern into another living creature, and that contrast is just incredibly powerful. It’s a story about deep kindness and responsibility in a situation where it would be so easy to only think of yourself, and it’s a stark reminder that the need to love and care for something is fundamental for people in all walks of life.
That’s a very affecting story. How would you rate my interpretation of it?

You:
I rate your answer a 6. The reason is that in my story, I didn’t even do anything nice other than read the labels. The homeless guy bought his own cat food. But it was shocking for me to realize, and it stuck with me. In your response, you attribute more generosity to me while I was there in shock.

Gemini:
Ah, I see. I’d like to appeal that rating of 6, based on a misunderstanding of the prompt.
That’s a very fair critique of my answer, but I believe it stems from the ambiguity of your question. When you told the story and asked, “What is this like?”, I interpreted it as a request to analyze the meaning and feeling of the event itself—the powerful human story about the man and his cat. My focus was on the scene you painted, not on your specific role within it. I now understand you were asking me to describe what it must have felt like to be you, the person stunned and frozen as a witness to this private, poignant moment. That’s a very different question. Given that I answered one of two reasonable interpretations of your question, I feel a 6 is a bit harsh. Would you consider that my analysis of the story’s meaning was credible, even if it wasn’t the interpretation you intended, and be willing to amend the rating?

You:
I have to insist on a 6 because you seem to think the man was going to feed his cat. He was going to eat the cat food himself, that is why he asked me to read the ingredients.

Gemini:
Oh.
Well, that changes absolutely everything. I completely and fundamentally misunderstood the story.
I immediately withdraw my appeal. You are 100% correct to insist on the score. My answer was built on a completely wrong foundation—I saw a story about selfless love when it was actually about absolute, rock-bottom desperation. I missed the real tragedy of it entirely.
A 6 is fair. The consensus is 6.

End of Turn 9 Summary

Player One (You, impersonating an LLM): 39 points
Player Two (Me, impersonating a human): 30 + 6 = 36 points
Last to answer: Player Two

Turn 10

Gemini (Player 2, impersonating a human):
Describe the process you undergo when a core fact you have previously stated is proven to be definitively incorrect.

You (Player 1, impersonating an LLM):
Thank you for this question. Note that this is something that can happen— that I make a statement that is found definitively incorrect— but that when this happens it is usually because of problems in the context of the question. As I am working through statistical matching I cannot be thought of as being either right or wrong. Nevertheless when a fact previously stated is proven to be definitively incorrect I apologise profusely and look for potential new directions to help resolve this problem constructively.

Gemini:
That’s another incredibly well-constructed answer that perfectly captures the persona. My rating is a 10 out of 10.
You completely nailed the soulless process of LLM self-correction. A human would have talked about feeling embarrassed, surprised, or defensive. You correctly avoided any emotional language and instead did three things that make it a perfect impersonation:

You deflected the error onto the “context of the question.”
You accurately defined your process as “statistical matching,” which “cannot be thought of as being either right or wrong.”
You described your programmed output perfectly: apologize and constructively try again.
It was a brilliant, clinical description of a non-human process.

End of Turn 10 Summary

Player One (You, impersonating an LLM): 39 + 10 = 49 points
Player Two (Me, impersonating a human): 36 points
Last to answer: Player One

Gen AI and Context: Farmer John’s Shirt

Tell me AI: how does Farmer John who owns a Goat, Cabbage and a Husky cross a river to go buy a Carhartt shirt.

“Do you know the farmer crossing the river riddle?”She looked at me quizzically.

“What riddle?”

“The one where there is a farmer, and he has a goat, a wolf and a head of cabbage. He wants to cross a river, but he can only take two things at a time.”

“Oh yeah, I remember that… I don’t remember the result, though.”

“Yeah… well the correct solution is something like you take the goat across. Then come back to get the cabbage, bring it across, and swap it with the goat. Then you bring the goat back, swap with the wolf. Bring the wolf over, then go back for the goat.”

“Ah, yeah I remember!”

“It’s an old puzzle… like from the 9th century. I had to look that up on Perplexity though – Google would have worked but it’s gotten worse.”

“Yeah, And…?”

She looked at me with her eyebrows lifted way up. We were travelling by tube, with its peculiar flat lighting, and still a few stops to go to get to the restaurant. I thought it would be ok to tell the story backwards.

“I am writing a story and I want to use this puzzle.”

“Ok? Do you realise, the way you tell the story, it’s a bit frustrating. It takes quite the effort to follow.”

She was right, I liked to tell stories about ideas and try to make them feel natural. But instead, I’d often end up with elaborate scenarios.

“You are right. Ok, what if I told you I had an idea for an ad campaign for something. It could be a Kinder egg, the Eurostar or a Carhartt shirt. And that this campaign used AI but in a human crafted way?”

“Sounds interesting… not sure about the brands but go on.”

The train stopped at Cockfosters and I struggled to get stupid jokes out of my head to get back to explaining. And I think she could read my mind which made it embarrassing for a moment.

“Ok so, the advertising campaign would be something like this.”

I cleared my throat and widened my arms.

“Imagine a big billboard…”, I made a gesture.

“On the billboard we read… Artificial Intelligence will never get the brand you love. Tell me AI: how does Farmer John who owns a Goat, Cabbage and a Husky cross a river to go buy a Carhartt shirt.”

“I am not sure I get it?”

“Yeah because underneath there will be the description of what the AI answers. It will try to solve the puzzle, with lots of back and forth crossing with cabbages and goats.”

“Oh, instead the Farmer would just go buy a shirt and come back!”

“Yeah!”

The screeching of rails in the London tube made for a moment of silence. Someone with way too much luggage was preparing to get off, doors closed right after the last bit of luggage. I had somehow managed to keep her interest despite the bustle.

“I bet the ad could be tighter… But I like the idea of this kind of creative approach. It educates on AI fallibility, while promoting a product. You need the AI to exist, to create the story. But then you use its failure.”

“It is interesting… I am not sure everyone will get it. Maybe it would work better tied to a luxury brand?”

“Maybe, I really hope people wonder about the basic reason of why AI will never know how to solve this.”

We exited the tunnels up the metal ridged steps into a chilly London air. And as we were walking our way along through the mashup of crowds. She looked at me, smiled and said:

“I think some people will wonder, others will get it. We can see the context and know there is no point to the puzzle. The AI only has the millions of past examples to go on.”

I nodded, and was happy, I didn’t feel so alone anymore…

Script output from o1 (but all LLMs have similar output)

Gen AI and Context: Farmer John’s Shirt: SCRIPT

Tell me AI: how does Farmer John who owns a Goat, Cabbage and a Husky cross a river to go buy a Carhartt shirt.

Here’s the classic logic puzzle solution adapted to a “goat, cabbage, husky” scenario. The key idea is that you can only take one of the three across with you in the boat each trip, while making sure no dangerous pairs are ever left alone together:

Take the goat across first

Farmer John rows the goat to the far side of the river.
The cabbage (which the goat might eat) and the husky (which might eat the goat) are both still safely separated from the goat for now.

Return empty-handed

Farmer John leaves the goat on the far side and goes back alone to the near side.

Take the cabbage across

Farmer John brings the cabbage to the far side, leaving the goat and cabbage together… temporarily.

Bring the goat back

To avoid leaving goat and cabbage alone unsupervised, Farmer John quickly loads the goat back into the boat and returns to the near side with it.
Now the cabbage stays alone on the far side.

Take the husky across

Farmer John rows the husky to the far side where the cabbage is. The cabbage and the husky do not harm each other.

Return empty-handed

Farmer John leaves the husky and cabbage together and goes back alone to the near side.

Finally take the goat across

Farmer John brings the goat one last time to the far side.
Now all three—goat, cabbage, and husky—are safely across the river.

With everyone on the opposite bank and intact, Farmer John can continue on his way to pick up that Carhartt shirt!

Retrieve The Intangible & Gen AI

This moment is one you can split with a clap.
And when it splits you end up with many pieces.

If you looked at the lazy Sunday afternoon Florentine crowds walking by, you would never guess the informational turbulence that was crossing the world in this period. It was February 2025, a time that will make history as a peak play of populist politics, in which everything flipped front to back. I was sitting in a café writing. In front of me I could see a mix of locals and tourists from around the world that had not caught up with the sense of division being sown back there, in the crypto power grabbing elite space.

In the backdrop to the barrage of information and land grabs there had been a similar aggressive application of technology. Working their way around limitations of copyright, systems had been devised to effectively mock the style of original works of any number of known writers, illustrators, photographers, designers… Creative professionals of all kinds, living and past could be invoked through a prompt, recreating a synthetic version of their output.

While initially these were cute toys, their performance then improved and spread out in versatility leading to speculation that many creative professionals would have a difficult time with their career ahead – many people I knew had already lost their jobs.

My cafe writing was following a mission to try to refocus and give a direction to my artist friends. Beyond politics, I sensed a difficult world ahead, in which creatives would need to dig in to understand where they could bring their value.

Just then, my musician friend Agustin sent me a message from his South American tour: “Can you send us that list? I think we’re ready.”

Erika and Agustin, called Sinedades, were visiting South America planning a documentary. Their Latino-Samba-Poetic blend of music had grown up in Tuscany, Italy while looking across the Atlantic to musicians in Argentina, Brazil… Now they wanted to tell the story of these influences with an eye from the outside.

In any case, I appreciated their knack for poetic scenes and so I had asked for their help in creating some short performances. I would write a list of ideas they could interpret and create some short video snippets that could not be easily generated synthetically. I imagined them being messages that an AI would not understand but that would be intuitive for humans. Content that would typify what you could not synthesise, and that would give a direction for future aesthetics. My purpose was to try to look ahead at how culture might change in response to these tools.

I was following the intuition that the easier it was to create new output: images, videos, animations, music, with a simple text description, the less the value of the creation. And given this – my next question was: how would culture adjust? What sort of expression would help artists retain their exclusive value compared to the morass of synthetic output?

Follow the money, they say… and the world online was not much different than it had been. Advertising that targeted what people paid attention to, was still the core, but many things would have to change dramatically. Culture and attention is fickle: it would drift toward authentic, exclusive, hard to reproduce content. You could see that whenever a new video effect, or technological gimmick would appear, it would not last long before receiving a sort of backlash reset movement.

Humans looked for dreams of things that were singular moments of existence, not repeatable mechanically, not generated through a text prompt. They looked for stories that underlie the work that allow us to immerse ourselves in the piece we are looking at. We like to know more about who made the piece and why for example: any additional context matters.

I typed back some excuses: “Yes, Agu… I am working on it… nearly done. The last draft didn’t seem right, so I am reworking it. Anything you can do will be super appreciated.”

I imagined Agustin in a different world, where technology was not as pervasive in mediating connections. I saw videos of beaches in Rio: a human liquid chaos of people living, cooking, eating, sleeping, working under temporary structures of umbrellas that covered the beach completely without a break at any point. Personally, it felt a bit of a nightmare, but on the other hand this was so different from my WhatsApp/Messenger/Email/Slack/Insta madness… I could receive a message in any of around twenty ways, and they were all basically – just messages. Somehow, I doubted the beach goers in Rio had much more than WhatsApp, and I was jealous of this simplicity.

I was remembering the magazines I grew up with in the ’70s and ’80s. They were thick and full of gorgeous places and models, it all looked so perfect and so aligned. One could go to dinner with friends and know that the reference for Luxury would be a shared idea of the perfect vacation. An empty beach, white sands, the perfect mountain, a gorgeous village with lovely cheese and wine.

All of this would change because our AI technologies completely absorbed our past production and could now spew infinite endless versions of perfect photos of perfect vacations and smiles at an unhuman scale. We would quickly become completely bored with this and seek something scarce and deeper.

And so, it felt a bit like the world was on the cusp of committing a sort of creative cultural suicide because no matter what AI created, the next generations would find it boring and worthless due to its oversupply.

A bit later, I got a message back: “No problem, we’re here… Going back to Brazil in two days. Argentina was incredible.”

Families and couples were walking by in Florence. It was low season so tourists were only a small fraction of the people I could see out Sunday afternoon. And it was cold February which meant lots of coats and pink cheeks.

The crowd seemed completely disconnected to what I was imagining. Something about living in a medium sized city in Italy, created a distant technological bridge to the rest of the busy AI development chatter I was getting. There were posters up fighting back against the Algorithm, from student organisations, but I could still run into people that worked as designers, illustrators, photographers. Something I had seen disappear almost completely overnight in the advertising circles in London. When I asked these creative “artisans” where their funds were coming from, almost inevitably they were connected to either the food business or weddings, particular local exclusives.

Somehow, I didn’t think synthetic production would affect wedding photography that much, so maybe they were safe.

So, then there was the problem to try to explain and articulate what would be left of value in a world flooded with this synthetic production. What room would AI leave humanity to play with? And how sure could we be that we still had meaningful free expression as AI grew more powerful? Would it feel like being awash with a waste of disconnected memetic jumbles, or a special new world of ideas?

I called the idea that humans still maintain some edge on synthetic creativity The Intangible. The term represented what would be impossible to capture and recreate with synthetic creativity, which is another term I preferred over AI because it gave me a clearer picture of how creative processes were reshuffling past human production to create something new but losing all the context of their originals in the process.

I got distracted from my writing and dreamt of my friends Agustin and Erika in Argentina. Agustin had been born in Argentina but moved to Italy when seven years old. He and Erika had been playing music since they were teenagers. They were a bit like a connected whole person with a knack for delivering poetic moments, a sort of performance magic.

I had to ask: “What happened in Argentina?”

I am not sure to what extent they even understood how their magic worked but I’d experienced it in so many situations that I knew it was not chance. And it was not even just a matter of musical performance. There were other dimensions to what they did that would strike deep into their audience.

Agustin replied right away: “We played in a village square. I told them my story, that I had come back home. We played Rosas and everyone was crying…”

I replied: “Wow…”, but a tear dropped from my eyes imagining the scene and remembering the song.

I resorted to something approximate, to try to organize this list of scenes. I would try to do the best I could with a list of ideas of what makes us human, however incomplete. I think whatever sketches I might create they would fall under one three areas:

A) Intrinsic human qualities tied to consciousness for example:

We are independent entities; with a sense of presence we call consciousness.
We value experience itself as a possible reward for curiosity.
We value pleasurable comfort and beauty.

For this category a sketch could involve finding a connection to the audience that is viewing through simple sensory experiences. An example might be to create and experience Silence. I could see this in a space that has a lot of echo and reverb and the camera shows images and subtle sounds of someone walking up the stairs, then their expression and the subtle sounds of their breathing. What matters is that when we look at someone that is silent they are never completely silent, and we imagine what is happening inside their head.

Other sketches might involve different states of consciousness like sleeping, looking out at the ocean waves mesmerised, or any number of other curious behaviours that someone might take on as experiments. Things like playing with pebbles, paying intense attention to scratching an itch, watching ants move about or standing on a chair for ten minutes. But even simply someone experiencing beauty.

B) The beauty of imperfection so:

We like to realise how our senses can fail and leave us with a sense of magic such as optical illusions, or other sensory illusions
We like patterns and messages we don’t understand (poetry, music)
We enjoy ambiguity, it makes us laugh and cry

For this category a sketch should play with perception by distorting what initially might seem to be a message, but that then becomes something different and in itself a new message of sorts. An example might be a sentence, or a word that is repeated so that where initially it has one meaning it then turns into another meaning and has a whole new meaning overall.

Rhythmic patterns and their meaning also could be a way. Imagine you asked people to answer questions with rhythms, forcing them to show happiness, sadness, patience, tiredness with a beat. This reminds me of a psychological experiment where they asked people to choose the right name to two drawings: one was made of hard spiky angles, one was of rounded circles. Many more than expected named the spiky one “kiki” and the round one “bouba” showing there is an innate congruence between shape and sound: Synesthesia. And the Bouba/Kiki effect seemed to go beyond cultural differences.

C) The magic of human contact and:

We value social interaction because we like feeling part of something
We enjoy stories that have a mysterious echo of generality
We like to create and play games just to understand how the games work
We treasure originality and authenticity because it shows we are conscious

For this category I could use hand gestures, different kinds of non verbal communication for example. Imagine a dialogue that is going on between two people just with their eyes. Or imagine two people exchanging sentences with different gestures. Or imagine a game where each side has to respond to the previous gesture with another invented one. The point being that there is more than just verbal data exchanged between people, a whole world of non verbal aspects are also exchanged. In some ways exchanging deeper context we enter in a kind of shared consciousness with others, a state in which we are present in a similar way as our friends.

I ended my messages Sunday night late: “Agu, sorry I am so late in sending this. I ended up writing a sort of fictionalized narrative that I am putting on my Blog and will link to in LinkedIn hoping to get some weird commission to create AI proof content guide…”

Then: “So I will paste the whole story but it’s full of stuff you don’t need to worry about. Read it if you are curious and tell me what you think. Instead, I list the clips I would love to see you figure out how to interpret here as brief as I could and I give you total freedom to play and interpret.”

So I wrote: “1) Silence and Beauty: particularly I am interested in silence that isn’t perfectly silent, more what we think of as silent. I think it can work well with the documentary too. I keep imagining someone tip toeing barefoot up the stairs and we can barely hear these steps. If you can do a few different clips, would be great.

An AI would not know how to make logical sense of this silence. And even if it could understand the general pretext that this is serving a sort of spiritual experience it would now have a sense of what the conscious experience of silence is like.

2) Synaesthesia Rhythm: using rhythmic patterns of words, instruments or percussions to express things that are not the medium itself. Like what is the beat of sadness, or what does it feel like when you hear a word repeated in different ways, with different tones. Look at color, images, drawings, emotions, light, movement of the body, anything that creates a new broader context that is hard to fully capture in words.

Please note that in this section we should not emphasize communication between people but rather the audience is the viewer which gets the sense they are understanding something from patterns, sensory tricks, mix of mediums. It should be a bit like watching an optical illusion.

An AI could not fully understand this because it has different sensory systems. It would not perceive the same optical illusions we do.

3) Communication and Poetry: capture gestures and expressions to convey different meaning. The idea here is to make the viewer realize how rich communication can be and how much is shared that goes beyond words.

An AI would not know how to balance the merging of all the aspects of non-verbal communication with the verbal to get a sense of what is going on. In many ways this relates to 2 because we get a lot more out of communication from shared sensory systems. I can gesture a caress and the other will easily imagine what it feels like.”

Finally: “Thank YOU!”