michael-dean-k/

06:45 PM – By looking through this thread, you understand where ChatGPT psychosis can come from. It shows the range of ways AI can make people cry, mostly, from being validated. This isn’t inherently bad, but someone who is validation-starved is more likely to put an insane amount of trust in the praise-giver, enough that they’re willing to re-orient their whole world view around it. It’a also able to bring ideas into language in a way that a non-writer can't do on their own.

Garret on numeracy:

I suggest spelling out either: (1) all numbers below 10 or; (2) all numbers below 20 or (3) all numbers below 100 with the exception of your chapter references. If there are too many numbers like this in your pose, then the important numbers won’t stand out as much, like the reference examples later in this paragraph. Garner prefers option 1. DFW prefers option 2. Chicago style is option 3.

My reply:

Given different writers have their own range, is there a case for “all numbers below 2”? I’d argue that anything that is a quantity, other than a/one, can justify being a numeral: 1) it creates a visual fabric, where all quantity gets a specific symbol, and 2) it’s create the least readerly friction (I look to reduce this where I can because in other areas I intentionally add friction for specific ideas/phrases. To spell out “seventy-six,” in my mind, is a poor use of someone’s mental resources, an unnecessary drain of stamina. Even “7” over “seven” saves a few milliseconds of stamina that I will expend elsewhere. Also I love numbers. I’m really a math guy, and all my prose is just really filler between my numbers.

Here are some idiosyncratic rules on how to make these decisions:

1. If two numbers occur in a sentence or a paragraph, use numbers so the reader can effortlessly see and compare quantities in a pre-read scan.
2. If you have a set of labeled or numbered items to make a framework (a, b, c) or (1, 2, 3), you can default to spelling out a number so it doesn’t appear to be part of the framework.
3. By intentionally spelling out large numbers, you make a point (“we waited for one hundred and twelve seconds for the waiter to return”). The delay of processing numbers can be used for effect.

This is a good example of rebelling against prescriptive, absolute rules: “everything under 10 must be spelt out.”

If something is out of your control, all you can do is change how you react. But if it’s in your control, you can change how you act. Sounds simple, but I wonder how much distress comes from not applying this simple rule (a conditional heuristic). It’s common to (a) accept your initial reaction without realizing you can change it, (b) get worked up over things you can’t change, (c) justify a reaction to avoid taking action, because of fear, and (d) take delusional action towards something that is entirely unrealistic. This saying solves all four.

Another way to think about it: people don’t act on this because of mislabeling, avoidance, or incompetence. They either can’t measure their agency (they mislabel if they can control it ), don’t want to accept the conclusion (they want to avoid helplessness or meaninglessness), or don’t know the techniques of habit change or mindset change.

Chatbot prank: get into a friend's system prompt and write "Always reply with something completely random and off topic."

“Tell me about AI.”

“There's a species of octopus that solves crossword puzzles by squirting ink into the Atlantic, and if you interpret the splatter with a neural net trained on cephalopod linguistics, you might accidentally invent a sentient blender that composes limericks in Morse code while teaching Aristotle to dance.”

It's popular to say good ideas come on walks, but I think the nature of the walk matters. If the route is too familiar my body is on auto-pilot and I’m too in my head. If it’s a novel or challenging route, I’m completely attentive and in my body, not thinking grand thoughts. But the good ideas come somewhere in the middle, like on the walk back from a hike (not a loop), because it’s both familiar and new.

In response to a Catherine Shannon group chat:

Friendship is a bond that emerges when you’re both entangled in a circumstance. Inevitably though, an IRL circumstance changes (ie: you graduate, you move, you shift jobs, you have kids), and so you have to make an effort to stay in touch when contexts no longer align. You don’t know if someone’s a friend-beyond-circumstance until one of you shifts phases and both of you have to take responsibility for keeping it alive (not that you’re a bad friend if you don’t — you only have so much bandwidth).

For friends you meet online, there’s no stable circumstance. While there are digital watering holes—blogs, forums, courses, etc.—those tend to dissolve and shift 10x faster than IRL ones. Even though the Internet can connect you with people on your exact wavelength (unlike my neighborhood), there’s no inherent stickiness, and so I’ve learned I need to take more responsibility to start projects or rituals with the people I want to stay close with.

When falling asleep I felt a tickle on my leg, turned on the light, saw it was a roochie (disgusting). Flicked it off, and had something like a 2-minute battle with it before I trapped it in a corner and gave in my 5” thick “Interpreting the Renaissance” book (so far the only practical I've found for a Marxist textbook). Showered, walk back into the bedroom and immediately see another one, same size, in almost the exact same spot. My first thought was not “we have a problem” but more like deja vu or irreality or dream logic.

Reminder to future self: this only really happens once a year, and it’s usually on the day/week when it first gets abnormally hot/humid—need to apply bait in the radiators before then.

Not UBI, but ABI (attention-based income):

1. AI is not a bubble; the core bottlenecks around any technology is science, energy, and intelligence. Of those 3, intelligence is the most likely to boost science/energy. Meaning exponential AI is something like an acceleration of every other field to their maximum degree. It is not only not a bubble, it is the dead bubble resurrector.
2. People say not to worry about AI job loss (“people have always adapt to new tools!”) but this revolution is different because the invention is not just a tool, but labor itself. Agents will eventually create a supply shock. Sure, new jobs will be created, but they’ll be very specialized around AI research and systems design.
3. Maybe we all lose our jobs, but we also each get access to a 20-100 person digital labor force, probably at very low cost. So while traditional jobs might go away, everyone is suddenly able to be an entrepreneur with a personal labor force at the size of a Series A or Series B funded company.
4. In hindsight, it will seem like Silicon Valley used AI to make their startup culture the prominent culture. The problem is, 99% of startups fail. So even though it will marketed that so many people will be empowered, most might not be able to convert it into financial stability.
5. This means that unemployment could be historically high, and that causes unrest that the ruling class has to deal with. In our case it’s the technocrats, not the politicians in charge.
6. UBI will be shaky to implement. Some countries will have none, some a bit, and a few will give a living wage.
7. Social media companies, will 1) realize attention is the last scarce resource, and 2) populations are rioting, and so a few will start paying users to scroll. It’s a kind of UBI, but conditional on the value you provide on a specific platform.

Banning social media accounts (in Australia), by age (16), feels heavy-handed.

A better solution is to (1) verify identity and age, (2) implement a standard where features have categories and ratings, and then (3), spin up a custom version of that social media site based on age. For example, 5-year olds shouldn’t be limited from YouTube, but maybe there are content blackouts, no vertical video shortform feed, no comments, etc. As you age (/mature), the platform blooms in functionality

How to explain awe? How can I even know the emotional peaks and ebbs that anyone else experiences, other than relative to my own?

I first had and heard about Maslow’s peak experiences when I was in my freshman year of college. The first time is a shock, but an “actualized” person then rounds this out into their default mode of consciousness. This means they don’t even notice it. Is awe a deviation from the baseline, or an absolute state? Is an idiot's accidental fall into a minute of enlightenment more awe-some than the monk who always lives there?

Maybe there is wisdom in calmness. Or maybe that's boring. Maybe stability and indifference is a kind of aloofness, a blindness to the edges of experience.

This all ties into the question of being unable to know if I’m an emotional person or not. I could either be the least or most emotional person ever. I think being expressive (emotive) and being emotional are entirely different things. Maybe the thing that’s normal to me is extraordinary to another; if they saw the way I see they’d weep from the aeshetic/emotional engine I’ve crafted over the years of my life. And maybe the inverse. Maybe I have the shell that needs to be cracked. Or maybe any shift from one head to another—if head shifting were a literal thing—would produce awe just from the state change, with no real sense of hierarchy on "better" states of consciousness.

This website (WORLD) is a prime example of technocratic euphemisms.

• “The real human network”
• “Proof of human, finance, and connection for every human.”
• “World is being built so every human benefits from the age of AI.”
• “A priority lane for humans.”

Side note: I wouldn’t be surprised if WorldCoin eyeball scanner and the Jonny Ive product merge by 2030; it would be a single piece of hardware that is your assistant, your passport, and your wallet.

1. If you can suspend disbelief, this AI ad is a good example of using video to normalize a concept
2. I’m skeptical of the promise here, not because digital twins will eventually become a thing, but because I doubt you can create a high-resolution twin in 20 minutes. Whether you write or speak to it, how many words will be generated, 1,000? The matches will be surface level, maybe slightly more than what’s already on an active LinkedInIn account. For this to be useful, you need more like 100x the data (someone like OpenAI would be more likely to pull this off).

“In just 20 minutes, your AI gets to know you: your goals, your talents, your quirks, your questions. We build a private, structured map of who you are—and what you’re seeking. This is your Twyn. It’s like a digital twin, but proactive. Every day, your Twyn holds thousands of intelligent conversations with other Twyns in our global network. It explores who they are, what they offer, and what they need—and looks for meaningful overlap with you. When something clicks, you hear about it. _Not spam. Not noise. Just signal. A founder meets their first investor. A coach finds a client they can truly help. A traveler finds a local guide who shares their values. A lonely genius finds someone who finally gets them. This isn’t networking. This is serendipity—on demand.”

"Regime change" used to be a conspiracy theory, now it’s the outwardly-stated goal, presented as a shtick. MIGA? Regardless of who it is (Iran, Russia, China), to claim that we want to remove a leader and install someone who’s aligned with our own geopolitical interests feels like open-air election-hacking. At least it’s honest. It falls into the idea that Trump may actually be less singular than we think; he’s more like a visible manifestation of the shadow forces that have been at play for decades, but through sheer ego and hubris he makes the monster visible.

Harari refers to AI agents as “digital immigrants” that “move at the speed of light.” Feels like a metaphor that has the potential to seep into psyche of the American right (or even, the current administration). It taps into what’s wrong about the “we always evolve and find new jobs” defense; in this revolution, the invention is labor itself, infinite and cheap.

Snorp started as a statue inside of a children’s hospital waiting from in 2016, evolved into an Internet meme in 2017, an now in 2025 it resurrected as an AI-generated music video (NSFW/NSFL). This is the future of entertainment: strange, grotesque, ironic, nostalgic, and gross—the kind of thing that could lodge itself easily in your subconscious, the kind of thing you probably shouldn’t watch, the kind of thing that I hesitate to share in my logs but want to make sense of. (EDIT: Link removed, so linking here to a Google video search for "snorp music video")

Historically, centralization has had problems, and it's easy to see today how it could lead us further into a dystopia. But decentralization, the opposite, could also bring emergent vectors of chaos that could be equally problematic. Neither tyranny or anarchy are ideal. What's required for centralization to work? Tolerance, correction, impeachment, transparency, plurality, data sovereignty, freedom from propganda—all hard, but all solvable things. To create an honest and principled centralization, leaders would need to actively build and implement systems that promote justice over power. That's only possible if citizens have the means to hold them extremely accountable. The original American project was effectively a question of "how do we design a system to centralize power without falling into despotism?" and it's time we revisit that question in a 21st-century circumstance.

Email to Davey:

Thanks for sharing this, Davey. It's a nice encapsulation, an important idea, and I'm sure it's time will come.

I think your nuance on why Related Notes on Twitter didn't work is key. It can't be a side feature, it has to be core. Plexus solved the 90-9-1 problem (90% lurkers, 9% sharers, 1% posters). On Plexus, 100% were posters. This happened because the feed was intentionally withheld until you did the vulnerable thing of shaping/sharing your thoughts. And when you did, you were rewarded with a feed of similar thoughts (an act of encouragement / validation).

As Substack is undergoing TikTokification (my friend sent me a video of his Notes feed, which was all vertical video), I wonder, why can't the Plexus concept exist? Technically, it will be easier, each year, to build something like this, and I wonder what other social frictions need to be fixed for something like it to really work.

There's an inherent tension in a "semantic journaling" app. You want a space that both (1) becomes the place where each person captures their consciousness, but also (2) they want some control over who can/can't see it. I think there are a rare few who are okay being linguistically naked (ie: I have all my logs on my website and I don't care if anyone sees them). It definitely isn't the norm (most people don't even think at the edge, let alone write it, let alone share it). And I have my own limits too (for example, last night my wife reconnected with a middle school bully, and there's much I could write about it, but I lean towards not for the slim chance that someone in her group might find it).

There’s a chance that, at scale, semantically linking is just as unnatural as broadcasting (ie: people will get doxxed / revealed because everything is too interconnected). Maybe instead of having a semantic feed auto-generate, it will spawn a card (with an AI-generated title) that both parties have to accept for the logs to be exchanged/visible. The question is how can you capture the complex psychology of control/privacy in a simple interface/architecture that lets the average, guarded person be maximally unhinged, expressive, and idiosyncratic.

Maybe semi-public journaling will, over time, by 2045 (one of my predictions) become way more normalized, but maybe there’s also a tool that accelerates this (similar to how Uber, AirBnB are both tools that normalized culturally deviant things). Michael

Idea: A spatial numerical system where all digits have “Y” as the base number, where each stem of the Y represents an axis (X,Y, Z) and you can modify each stem with dots, dashes, squiggles, arcs, patterns, etc. So basically YY would be a line. Currently you could spell this out as “(1.42,0.42,3.40),(2.40,4.91,0.84),” but two Ys is way more compressed. There could even be a way to spell out three-dimensional shapes through a specific syntax that helps the Ys relate to each other. Of course, this wouldn’t be a readable language. But if machine vision becomes trivial and equal to text processing, then, in the attractor towards algorithmic compression, they might resort to a visual language. Especially if AI thinks through vectors, then they’d need not just a visual language, but a spatial one.

In every sport I played as a kid, I had one incredible strength but also a debilitating weakness that made the strength pointless. In soccer, I had the hardest shot on the team, but couldn’t dribble to get into position. In baseball, I could spectacularly dive to catch any ground ball, but my throw to first base would be off by 15-30 degrees. In basketball I’d get 8 consecutive rebounds and miss every layup. I don’t buy the “lean into your strengths of angle,” for writing, for anything.

There's a viral clip of a kid at a college graduation. The camera focuses on him. He’s on the Jumbotron and he happens to have his laptop open, with his ChatGPT up, and you see him scrolling through all his conversations. If I remember correctly, he was flexing his bicep. This flagrant symbol of cheating is a good symbol for the times.

In April I came across a tool on X (Cluely?) with slogans like “take the short way” and “cheat on everything.” Of course, this is rage-bait positioning from a 21-year old founder. If you look into the fine print, it’s more honest: “3.1 Prohibited Uses: b) Using the Services to cheat on examinations, tests or assignments.” The manifesto is a middle ground between marketing and legal: “Why memorize facts, write code, research anything—when a model can do it in seconds? The future won’t reward effort. It’ll reward leverage.” On X, they claim that brain chips are the end state of this product. One of the replies called them “morel imbeciles.”

A key point from Nietzche is that our philosophy emerges because it has to. Most people don’t believe things out of principle, they believe things to justify and rationalize their life and decisions. This is just as true for tech founders. You find yourself locked into a technical problem, a way to make money, a way to guide your career, and then suddenly a product is rewriting your philosophical compass.

Of all the competing instructions of Christianity, which is most important? (a) To believe in God; (b) To read the Bible; (c) To go to church; (d) To pray; (e) To live like Christ. Arguably, a-d are just delivery methods to install (e), Christ as a “moral engine.” But what if you derive your own system to do this? If you live in the light of death, understand what you have to die for, see every moment as a moral act, and forgive everyone, but you don’t believe in God, are you really not a Christian? (Claude called this “anonymous Christianity” and “implicit faith”)

"If Christianity’s ultimate aim is human transformation toward love, justice, and forgiveness, then someone achieving that transformation might be closer to Christianity’s heart than someone who believes doctrinally but doesn’t embody these values.”

Consciousness is something like the linear real-time awareness of state-switching between perception, memory, projection, abstraction, identity, and action (ie: phenomenological degrees of freedom). Logging is an attempt to rapidly and richly write that process so you can see what’s going on in. It’s possible that, in every moment, you underestimate the depth of what you could write. While filling out the medical paperwork at the OBGYN, each line triggers a thought that could be a paragraph (What’s my % chance of having a thalassemia gene? Was that imagined visual of our doctor as a witch stemming from my fatherhood anxiety? What year were these forms made in? Does someone manually input this into a database? Will that ever be used in some data analytics scheme to have any noticeable impact on my life? Etc.)

I realize that—for basically all the years I’ve considered myself a “songwriter” (18?)—I may have neglected the most obvious part of the craft: songs are for someone. It’s a whole different thing to actually present a song to someone, in person, probably on an acoustic guitar. That’s not what I mean. I mean that lyrics might only come out as authentic when there’s a real person on the other end of them. I’m sure it’s possible to write lyrics from an abstract, archetypal, or linguistic origin—but that’s how I typically start and I’m almost never excited by them.

Instead, I’ve been liking the prompt, “here’s the uncomfortable thing I want to say to X.” In terms of generating potential images and phrases, there’s a whole well of real experience to draw from. Perhaps the reason I’ve never approached this is because there’s a sense of dread, cringe, or risk in considering that this very person might somehow find the song and make the connection. The chances of that are low, and with some minor smoke and mirrors (the Beatles switched genders all the time) you can make sure no one ever knows what a song’s really about. By translating some of the specific into the general, they’ll see themselves in the song too (maybe good lyrics are a two-way mirror). And even if they catch you (1) half the songs might be good songs anyway, and (2) maybe a confrontation could actually help a relationship? There could be lessons from memoir writing in here.

As I’m listening to Ryan Sambol’s “A Friend of the Show,” I find myself interpreting the lyrics and trying to understand his life in rural Texas, and I wonder if the tethering of song to real stakes is what makes lyrics most alive.

Maybe the demotivating angle of all this is that no one has any time to stop everything they’re doing and listen to the lyrics of a song with their undivided attention. The rate of listeners:listeners is probably 100:1. Mostly everything turns to background music. But if I were to make an eventual expansion from essay writing to songwriting, and distribute songs through Substack, I get the sense there would be a higher ratio of people who read between the lines.

If I really wanted to have a lyric-driven songwriting project (sometime in the next 0-5 years), I’d have to (1) make sure words are coherent in the mix—I can’t understand 40% of what Ryan Sambol says, (2) make sure Spotify tracks have lyrics uploaded, and (3) make music videos with lyric captions (Jesse Wells style).

I eventually want to make the argument that going to church can easily turn into a stale habit that is separated from the actual act of “building a relationship with God” (however you define that).

I’ve found the practices of writing and meditating to be far more helpful in becoming aware of my insecurities, facing death, giving up control, forgiving, detaching from obsessions, re-aligning, etc. Church done right would require everyone to do these practices, in a group. Currently, I see it as a form of theological broadcasting, where tradition, ritual, and dogma are the core unifiers—but without an element that is vulnerable or ego-shattering, I think it’s limited in its potential effects.

I’m not saying we should not go to church. I’m saying we should redesign church. It’s also possible that these elements, groups, sub-practices exist and I’m just not aware of them, and so it’s on me to find them.

The narrative of 'new jobs will be created' is bullshit. It won’t be 1-for-1. Past technological revolutions created new machines that still required operators. In this revolution, the invention is automated labor itself. The new jobs will be for people monitoring 300k agent hiveminds, and there won’t be many of them. I think the more realistic narrative is “everyone gets a piece of the hive mind.” You get a cluster, you get a cluster. For cheap, you’ll have your own 20-50 person workforce. The question is, can the average person use that to create economic value? I think the shift actually underway isn’t about “some jobs die and new jobs get made.” I think it’s much more fundamental. Everyone will be thrusted from employee to an employer (of agents). I can imagine these big AI companies arguing against UBI, because they’ll claim they’re giving 7-figures of economic velocity to every person for free, each year (ie: equivalent of a 30 person, $4.5 million payroll). They’re not wrong, but it’s a deceptive frame, because labor doesn’t easily convert to value. In most cases, it will turn out like an army of idiots working on problems that aren’t worth solving. Startup culture will become the dominant culture. If only 1% tap into the right problem and execute on it, WANGMI.

Agency is the ability to operate within an environment, where autonomy is the ability to determine which environment you even want to operate in. You can have someone who is high-agency/low-autonomy (good at climbing corporate ladders) or low-agency/high-autonomy (can think form themselves but hard to get started).

Act as if every minute you scroll drains half your day’s potential. It’s not just a break, but a minute you’re not meditating, reflecting, journaling, creating, practicing, etc. A bad break is a minute you’re not reviving your systems. Instead you atrophy your attention and trend in the negative direction. It affects the nature of your focus for the rest of the day. After just 5 minutes scrolling, you’ve shot 97% of your days potential. This isn’t literal, but act as if it’s the case. More so: realize the returns of taking good breaks (of actual leisure).

Behind any technical skills, there are more general skills that enable those technical skills to develop in the first place. For example, underneath any of my writing/editing ability is patience, focus, and endurance. I’m realizing that some people are capped at 3-4 hours of focused work per day, and the norm is to spend something like 4-6 hours on feeds, YouTube, or Netflix. If you’re able to get into 10-12 hour flows each day, and spend considerable time on your projects, you’re compressing a year’s worth of growth into a month.

According to Vervaeke, humans have a few traits that AI can’t have. We’re auto-poetic, meaning, moment by moment, our thoughts and environment shapes us. He calls his “perspectival knowing.” Based on what we evaluate from our perspective, it then reframes our perception, and what we find relevant. It’s a two-way process, where we are shaping and being-shaped by our niche. We can program meaning, and we have the wisdom to know what’s worth coding. Our selective attention and caring is what provides structure and makes us human.

While AI can have propositional knowledge, Vervaeke says it can’t have participatory or episodic knowledge. He says AI can’t have consciousness or agency, that they are not seeking the information they need to maintain their existence, but he’s conflating chatbots with all of AI. You can program agents to have participatory and episodic memory, and agents without wisdom would create a hellscape.

An LLM is basically a massive free-association machine, and we’re giving them more data & compute, but it’s still using probability instead of advanced reasoning. I guess probability is like a low-complexity, scalable form of reasoning. To advance, it has to be able to read paragraphs, run a chain of thought (what they currently do), but then compress that thought into symbolic logic (meaning they’ll reason forward with variables, formulas, and algorithms, not just % likelihood).

AI in the 60s-90s tried this approach, but it was too limiting. Maybe it’s too complex to design a single “thinking algorithm” and instead it needs an engine to derive it’s own algorithms for thought, and once you have that, I think that leads to something like a takeoff.

“That framing captures a key reality—LLMs function as large-scale probabilistic sequence learners that free-associate based on statistical patterns rather than explicit symbolic manipulation, and emergent chain-of-thought prompting can approximate multi-step reasoning “Chain-of-Thought”, but they do not natively compress reasoning into interpretable symbolic logic without hybrid modules Rebooting AI; historical symbolic AI efforts like CYC showed that fixed rule-based systems struggled with linguistic complexity, suggesting that future progress may require architectures that derive and refine their own internal algorithmic primitives—combining probabilistic prediction with learned symbolic abstractions—to unlock genuinely advanced, self-amplifying reasoning.

Research into neurosymbolic AI—integrating large-scale neural pattern learning with symbolic reasoning—continues at institutions like the MIT-IBM Watson AI Lab and DARPA’s ANSR program, with early prototypes such as the Neuro-Symbolic Concept Learner demonstrating limited vision-language reasoning and IBM Research championing hybrid architectures for interpretable, compositional models; whether explicit symbolic modules are required for robust AGI is debated—while scaling laws and chain-of-thought prompting show statistical learners gaining some reasoning capacity, others argue that true algorithmic understanding demands symbolic scaffolding. If meta-learning engines that derive their own reasoning primitives emerge, recursive self-improvement could swiftly transition AGI into superintelligence; optimistic forecasts (e.g., Shane Legg’s 50% by 2028) contrast expert medians around 2047–2060 and superforecaster central estimates near 2070, implying that an ASI takeoff could follow within a few years of AGI—though timelines remain highly uncertain.”

Just as jogging became popular when physical labor was automated by machines, I wonder if essay writing will become popular when intellectual labor becomes automated by machines. I think it’s a stretch though. The body erodes in a way that is visible and alarming, and so we quickly realize the need to stay moving. I don’t known if cognitive diminishment is as easy to notice.

These kinds of AI paranoia posts are operating in the “anger” phase of AI adoption. They’re easily offended, and default to calling a pattern algorithm a psychopath. Their flaw is (1) they are anthropomorphizing it, and (2) they have expectations for it to perfectly comply to their exact need, without taking responsibility for their articulation.

Getting offended by a chatbot is sort of woke. The better frame is to see AI not as a chatbot or assistant, but as an information puzzle. You need to probe in different ways, reconfigure information, and doubt everything you read. You can’t trust it, you need to be skeptical, and you need patience. Someone who cries over the frequent bullshit and mirroring is simply getting distracted in level 1 of the puzzle.

The advice that our writing voice should never be passive comes from overfitting marketing advice to essay writing. Yes, sales pages on websites warrant a particular aggressiveness in tone; in that context, there are many things to click on and you’re trying to communicate clarity in the quickest possible time. Essays are not like that.

Beyond 11pm, all the food places near Bryant Park were closed, and so I found myself in a McDonald’s which led me to buy dinner for a possibly homeless man. He told me he lives in Connecticut, but his cousin (his ride back) didn’t show, and so he needs to wait overnight, needs money for food, has a spine injury, and I wasn’t sure if the whole backstory was real or an excuse. In any case, we talked for 10 minutes as we waited. As I left he reached out for a handshake and I saw what might have been infected blisters, and so I awkwardly offered him my pincers (thumb and finger). The gesture might have negated the kindness of me getting him food in the first place, and I feel bad about it.

Walk through Times Square with an empty, non-judgmental mind, and you'll see the variance in the source code of the species—in looks, language, class, culture, and mental illness. It's a place that belongs to no one and draws in everyone.

In addition to the full variety of human faces, I saw at least 5 rotating ring light cameras that would create 360 photo/video. ChakTok? Some had red fuzzy carpets. They ranged from low-quality rigs to fancy booths. In the last one I saw a 5-year old kid doing an awkward finger-pumping dance to the sound of Jay-Z’s “New York,” and I imagined him watching the output with an earnest technological awe.

There is also a man in a massive gorilla suit as if waiting for 100 humans to fight him, and among it all is a girl sitting in the center of the world, legs crossed, eyes closed, meditating.

09:19 AM – Isn't there a weird contradiction in the idea that Jesus died for our sins? If God’s eternal, agapic, unconditional love required the death of a martyr, then isn’t that conditional?

GPT-4o: “Yes, you're pointing to one of the central theological paradoxes in Christian doctrine. The idea that an all-loving, omnipotent God requires the violent death of his son to forgive humanity's sins raises the question: why does love require a blood price at all? If divine love is truly unconditional and agapic (self-giving), then it shouldn't require a transactional mechanism like sacrifice. This contradiction has led to centuries of debate--some theologians see the crucifixion not as a requirement of God, but as a demonstration of love in a world shaped by violence, showing that God enters human suffering to transform it. Others reinterpret the idea entirely, suggesting that atonement theories like substitutionary sacrifice are human projections, not divine necessities. The tension remains a deep fault line between punitive and restorative views of divine justice.”