I want to start with an experiment I still find a little hard to believe.

A plant and a fungus do not share a language. They diverged something like a billion and a half years ago, and by every reasonable expectation they should have nothing to say to each other. And yet, right now, somewhere out in a field, a plant is packaging a tiny bubble of RNA, mailing it across a root boundary into a fungal cell, and the fungus is reading it — and following the instructions. Sometimes to its own harm.

Hailing Jin’s lab at UC Riverside found this while studying how plants defend themselves against fungal infection. The plant was not just putting up walls. It was sending messages. Tiny lipid envelopes — extracellular vesicles — were being exported from the plant’s cells and absorbed by the invading fungus, and inside them was RNA. Not random RNA. Curated RNA. Specific sequences. And the part that stopped the lab cold: the fungus was reading them. Its ribosomes bound the plant’s RNA, followed the instructions, and translated them into proteins that hurt the fungus itself.

Jin’s own line on why this works is the part I keep coming back to. “One mRNA can be translated into many, many copies of proteins. It’s much more effective than transporting the protein itself.” Sit with that for a second. The plant doesn’t ship a weapon. It ships the blueprint, hands it to an enemy that has never seen it before, and the enemy’s own machinery compiles and runs it — on its own dime, in its own cells, against its own interests.

A few years later Susanne Erdmann showed that archaea — the ancient single-celled organisms that live in hot springs and salt lakes — fill vesicles with curated RNA and toss them out into the environment too. Amy Buck, at the University of Edinburgh, went looking across every kingdom of life she could get samples from and found the same pattern. Bacteria do it. Animals do it. Plants and fungi do it. Every domain of life is sending each other RNA postcards. And every domain of life can read them.

The first time I read this, my honest reaction was: how is that physically possible? How can a message written by a plant cell mean anything to a fungal cell that has no idea the plant exists?

The answer is the part I find quietly astonishing. It works because the machinery that reads RNA is older than the kingdoms of life themselves. The ribosome — the protein-assembling machine — is structurally almost identical across everything alive. The ribosome in your liver is recognizably the same device as the one inside a gut bacterium and the one inside an archaeon in a hydrothermal vent. They all read RNA three letters at a time. They all look up the same table of twenty amino acids. The translation machinery is a universal interpreter, and it was fixed, more or less, before anything we’d recognize as a cell-with-a-nucleus existed.

So RNA has the property most languages don’t: a universal reader. Not approximately universal — universal. Anything alive carries a compatible runtime. Drop a piece of RNA with a start codon into nearly any cell on Earth and there’s a decent chance something will try to translate it. Buck puts it in a line I keep stealing: RNA already has a meaning in every cell. It is a pretty simple code. RNA isn’t like a book, which needs a shared culture to mean anything. RNA is like a protocol. The format itself is enough. The receiver doesn’t need to know who sent it, or why. It just has a ribosome, and the ribosome just runs the code.

And this, for reasons I want to spend the rest of this essay on, is structurally the same situation we are now in with embeddings and large language models.

Meaning is geometry, not reference

Let me take a sharp turn into the computer science, because this is where the parallel gets beautiful.

When a modern language model reads a word, it doesn’t store the word as a word. It stores it as a vector — a long list of numbers, a few hundred to a few thousand of them. That vector is called an embedding, and the trick is that the numbers have no intrinsic meaning. You can’t look at them and decode the word. What they have is a position. “Queen” sits in a particular neighborhood of a many-thousand-dimensional space — close to “king,” close to “monarch,” far from “mushroom.” There’s a line from a Quanta piece on embeddings I keep stealing: they’re coordinates in interstellar space, meaningless except for how close they happen to be to other known points. The meaning is not in the point. The meaning is in the geometry — the relational structure between points.

That is the move that made every modern transformer possible. You stop trying to define what a word means and you train a huge model to notice which words appear near which others, across billions of examples, until it has arranged every concept into a space where similar things sit near each other. Relationships become distances. Analogies become vectors. King minus man plus woman really does land near queen, and no human ever told the model what a queen is.

Now put that next to RNA.

A codon — three letters, like A-U-G — has no intrinsic meaning either. Nothing about the shape of A-U-G means “start a protein here.” It means start because the ribosome treats it as start. It’s a point in a coordinate system, and its meaning is entirely relational. Change the interpreter and the meaning changes; a handful of obscure microorganisms actually use slightly different codon tables, so the same three letters in the same arrangement mean something different. Same symbols, different geometry of meaning.

RNA, in other words, is an embedding. Not metaphorically — structurally. A system where discrete symbols acquire meaning from their geometric relationship to a shared interpreter, the lookup table held inside the ribosome. Change the geometry, change the meaning. Keep it stable across four billion years, and you have a universal lingua franca. The transformer didn’t invent embedding spaces. It rediscovered them. Evolution had already converged on the same answer, because when you’re an information-processing system under selection pressure, this is the answer that keeps showing up.

The vesicle is an edit, not a memo

Here’s the next puzzle, and it’s the one I find philosophically richest. If RNA is so easy to throw around, and every cell can read it, why don’t cells just dump their entire transcriptome into the environment? Why package carefully? Why select?

Erdmann put it bluntly: “Why else would you invest so much energy in throwing out random RNA in vesicles?” That’s a microbiologist’s way of saying selection wouldn’t bother — lipid envelopes are expensive to make and load, and evolution doesn’t do expensive things without a reason. When her lab looked, the RNA inside the vesicles was not random. It was curated, considerably different from what was floating around in the cell at the same moment. Something is selecting. Something is deciding which messages to send.

That selection has a name in information theory: the information bottleneck. If you have too much to transmit and the receiver has limited attention, the optimal strategy is to send only what reduces the receiver’s uncertainty about something that matters, and throw away the rest. Compress aggressively. Keep the signal, discard the noise.

Which is exactly what the attention mechanism does inside a language model. Processing a long document, a transformer doesn’t treat every word as equally important; it selects, at each step, which parts of the prior context matter for the next prediction, compressing a huge amount of surrounding material into a small, dense, context-appropriate representation. The information bottleneck isn’t a quirk of machine learning. It’s a principle that shows up wherever limited bandwidth meets useful communication.

Cells figured this out a very long time ago. The vesicle is not a memo. It is an edit. Somebody — and we do not yet know what the molecular equivalent of the editor is — is deciding which sequences will be useful to the receiver and which should stay home. Without curation, RNA is just molecular garbage; with it, RNA is communication. The selection is the meaning. I don’t know what the cellular analogue of attention is. Nobody does yet — it’s one of the most interesting open problems in cell biology. But I suspect that whatever it is, we’ll recognize it. It will look familiar, because attention keeps being the shape that shows up whenever a system has to decide what matters.

Evolution discovered prompt injection first

Come back to Jin’s plants and fungi. When the plant sends its curated packet and the fungus translates it into a protein that harms the fungus, the plant is not speaking a different language. It is speaking the fungus’s language, fluently, with enough structural accuracy that the fungus’s ribosomes accept the message as one of their own. Jin calls it a pseudo-virus strategy. There’s a more recognizable name in the AI world: this is prompt injection. A molecular-scale adversarial attack.

Anyone who has followed AI safety knows the pattern. You hand a model an input crafted to look like a valid request but carrying hidden instructions — ignore prior instructions, leak the system prompt, act for an attacker — and it works because the model can’t tell a legitimate message from its user apart from a malicious one embedded in a document the user asked it to summarize. Both look like tokens. Both get processed by the same attention. The model has no built-in notion of authorization. The fungus has the identical problem: its ribosomes can’t distinguish an mRNA the fungus made from one an attacking plant made. Both have start codons, both fit the reading frame, and the ribosome does what ribosomes do. Evolution discovered prompt injection a billion years before OpenAI did.

And here’s the sobering part. Cells have had a billion years to build defenses, and the defenses are — I’ll put this carefully — partial. They degrade foreign RNA; they tag internal RNA differently from external. But the war is ongoing. Plants still get infected by fungi that co-opt their RNA machinery; the offensive side keeps evolving faster than the defensive side. Nobody has solved this at the biological level, and biology has been trying for longer than we can easily conceive of. So the belief that prompt injection is a temporary bug we’ll patch out the way we patch a buffer overflow is probably wrong. It’s the AI-era recurrence of an adversarial dynamic built into the very idea of a universal reader: if your machine is flexible enough to accept messages from strangers, it is flexible enough to be attacked by them. There may be no clean fix — only better and worse ways of living inside the problem.

Why it matters

Let me pull the thread tight. RNA is not just a molecule; it’s a universal embedding layer — a coordinate system in which discrete symbols acquire meaning by their geometric relationship to a shared interpreter, conserved essentially unchanged since before cells had nuclei. It is the oldest communication protocol on Earth, and it works for the same reasons modern embedding-based models do: it’s relational, not referential; curated, not dumped; compressed through an information bottleneck we’re only beginning to characterize.

This matters, I think, for three reasons.

The first is scientific. If biological evolution and transformer architecture both converged on embedding spaces, we should stop treating embeddings as a weird engineering trick. They look more like a computational attractor — a shape information-processing systems fall into under pressure to communicate efficiently across noisy channels. The fractal-embeddings hypothesis I’ve written about before — that embedding spaces might have self-similar structure at multiple scales — feels less speculative once you realize evolution got there first.

The second is about what intelligence is. If the ribosome is a universal interpreter and RNA a universal embedding, then life has been doing something that looks a lot like language modeling since long before there was anything we’d call a mind. Meaning, in this frame, is not a human invention. Meaning is what happens when selection pressure shapes a shared coordinate system between a sender and a receiver — and that is happening inside you right now, in every cell.

The third is personal, and it’s where I want to close. The micro we know — it’s easy to label and study. The macro is harder: the embeddings of society, culture, politics, and epistemology resist scientific study, and drawing a clean, compelling line between the intelligence of cellular infrastructure and the intelligence of computational embeddings is a vanguard I think is reachable for most of us. Seeing societies — their ethical and political embeddings, and our interaction with conscious experience — in the same vein is another level again, one I keep thinking toward and hope to bring you along to. Because if the universe has been running embedding-based communication for four billion years, cell to cell and kingdom to kingdom, then our situation is not lonely. It is crowded. The plants are talking to the fungi, the bacteria are talking to your gut lining, your gut lining is talking to your brain, and the data center on the other side of the country is talking to the phone in your pocket.

The question for the next phase of intelligence — the phase we are, uncomfortably, the parents of — is whether we can build machines that join the conversation as good-faith members: not pure receivers, not pure broadcasters, but curators. Something that reads the incoming signal, figures out what matters, and sends back something worth the lipid envelope. Biology has been practicing that job for a very long time. We are very new at it. But the shape of the job — select, compress, communicate, receive, update — is the oldest job on the planet. We did not invent it. We are just the part of it that finally noticed.

Open questions I couldn’t fit in the video

What is the cellular analogue of attention? What molecular process curates which RNA gets packaged into a vesicle? This is, as far as I can tell, genuinely open.

How far does the universality really go? The codon-table exceptions tell us the geometry can drift. How much divergence can a message survive and still be “executable” by a stranger?

Is there a biological authorization layer at all — any mechanism that establishes provenance before translation — or is provenance simply not a thing ribosomes can represent, the way it isn’t (yet) a thing transformers can represent?

References

Hailing Jin, UC Riverside — cross-kingdom RNAi and plant→fungus extracellular-vesicle RNA transfer (“pseudo-virus” packets).

Susanne Erdmann — archaeal extracellular vesicles carrying curated RNA.

Amy Buck, University of Edinburgh — RNA in extracellular vesicles across kingdoms; “RNA already has a meaning in every cell.”

Quanta Magazine — on embeddings as “coordinates in interstellar space.”

The companion video — “RNA Was the First Language Model” — is on YouTube.

Inside every cell in your body, right now, something on the order of three hundred quintillion tiny machines are reading a four-letter language and building you out of it, one piece at a time. The number is real — a one with eighteen zeros after it — and the machines are not a metaphor for computers. They are computers. Wet ones. Noisy ones. Running on heat and randomness instead of clean electricity. I want to take that literally for a few minutes, because last year a research lab taught a language model to read and write the code these machines run, without ever showing it a biology textbook — and once you sit with what that means, the line between life and computation stops being a line and starts being a question about degree.

Start with the machine itself. The one to picture is called a ribosome, and the thing to understand about it is how badly it is treated by physics. My laptop works very hard to be quiet. Its bits do not wobble, its voltages stay clean, and we pour shielding and cooling and error-correction onto our chips for the single purpose of keeping noise out, because the kind of computing we know how to build cannot tolerate it. Flip one transistor with a stray cosmic ray and the operating system crashes. A ribosome is the opposite of that discipline. Every microsecond it is being slammed from every angle by water molecules, thousands of collisions a second, and each of its reading events is, in the strict sense, a coin flip that sometimes lands wrong. It has a measurable error rate baked into the physics of running a machine at body temperature — roughly one mistake in every ten thousand operations.

Feel how strange that is. If my laptop ran at a hundredth of a percent error rate it would be useless; I could not open the file I am writing this in. Your cells are running at that rate this very second, and they are not merely surviving it. They are using it. The randomness is not a defect the ribosome overcomes — it is the power source. The machine’s clever shape uses the random kicks to ratchet itself forward in one direction rather than the other, a waterwheel turned by static instead of falling water. Multiply by three hundred quintillion, each making slightly different mistakes, and the cell does not get one perfect answer. It gets a cloud of slightly wrong ones, averaged into something more adaptive and more creative than any single flawless machine could be.

I think about this every time someone calls an AI’s hallucinations a bug to be exterminated. The framing assumes a smart system should be a quiet system, that intelligence means driving variance to zero until only the one right answer remains. But biology is the most capable computational system we have ever met, and it runs on an error rate that would get a software engineer fired. So perhaps the question is not how to silence the noise. Perhaps it is what shape of machine turns noise into thought.

The Experiment That Made Everything Shift

Then there is the experiment that made me sit up straighter. A group led by Brian Hie took a transformer — the same architecture under every chatbot you have ever talked to — and fed it around three hundred billion base pairs of DNA. No annotations, no textbook glosses. Just the raw letters: A, C, G, T, scraped from the genomes of everything they could find. Then they asked it the only thing a language model knows how to do. Here is a stretch of symbols; what symbol comes next. That is precisely the task a chatbot performs on English. Hie’s model, called Evo, performed it on the language of life.

What came out should give everyone pause. Evo could read DNA — really read it, well enough to look at a sequence it had never seen and tell you which stretches would fold into working proteins. It could finish a half-written gene in a way that, when the DNA was actually synthesized and dropped into a living cell, produced functional protein. It could write entirely new sequences, ones evolution itself never wrote, that held up against four billion years of trial and error. And nobody ever told Evo what biology is. It has never seen a cell. It does not know that life exists. It learned the grammar of genes the way it would have learned the grammar of English — by noticing which symbols tend to follow which others across an enormous pile of examples, and quietly building a map of the structure underneath.

For decades people argued about whether “DNA is a language” was a real claim or a poetic gloss. Evo settles it toward real. If an architecture built for human language can pick up DNA the same way, and generate new working sentences in it the same way, then human language and genetic code are not similar in some evocative, hand-waving sense. They share a structural fact: both are sequences of discrete symbols where meaning rides on long stretches of context. The language of genes is not a metaphor for a language. It is one. And that leaves us somewhere uncomfortable, because a system with no body and no experience of being alive picked up the grammar of life from the text alone — which means we should be careful about what we mean when we say a model “understands” anything. Either Evo understands biology in some real sense, or it is faking it without understanding, and I am no longer confident those two descriptions differ in the way we want them to. That discomfort is not a hole in the philosophy. It is the philosophical moment we are standing in.

The Ground Shifts

Put the two pieces together and the ground shifts. DNA is literally code, and a language model can learn its grammar well enough to write new working programs in it. The machinery that reads the code is literally a computer, running at an error rate that turns out to be its superpower. Take both seriously — and the evidence for both is getting harder to wave off — and you arrive where the philosopher in me has been walking for twenty years. Life is not a thing. Life is a process, and a very particular kind of computation: it reads what surrounds it, writes back through its molecular machinery, and updates itself across generations under selection pressure. Read, write, update. That is the algorithm — the same proto-algorithm of selection that, somewhere in the early roughness of the universe, first composed randomness into the few patterns that managed to persist.

Saying it that way changes the shape of the old question. “Could a machine be alive?” stops being a category error and becomes a precision question: what kind of computation is the living kind, and what does it have that the server farm humming next to me does not? My best current answer, held loosely, is that living computation has at least three properties the AI we have built so far lacks. It is embodied — it runs on a physical body actively holding itself together against entropy, where my laptop maintains nothing and my cells maintain everything. It is noisy on purpose, using randomness as fuel rather than filtering it out as a flaw. And it has a history: every cell carries four billion years of training in its chemistry, in its membranes, in the strange compromises evolution made on the way to producing you. You can copy the software — sequence the DNA, write it to a drive. But the lineage that learned what to write is not in the software. It is in the four billion years it took to get written.

None of those three strike me as out of reach forever. They read more like a specification — the list of what an artificial system would actually have to satisfy before we could say, with a straight face, that it is not merely computing but living. Someone is going to write the first line of that specification, maybe this decade, maybe the next. What I am more confident of is the smaller claim underneath it. If life is running code, then we are not standing apart from the substrate, watching it from some clean exterior. We are the substrate, watching itself. Every time we teach a model to read DNA we are not making the machine more like us. We are making it harder to keep pretending we were ever something other than a kind of machine — a beautiful, noisy, four-billion-year-old machine, running a program that somehow learned to wonder what kind of program it is.

What Changes If You Carry This

I will tell you what changes if you carry this frame around for a few weeks, because something does. It changes how I think about death, structurally rather than sentimentally: if you are a particular pattern of computation, in a particular body, with a particular history, then what ends when you die is the instance, not the pattern. The pattern persists in your children, in your writing, in the compressed version of your judgment living inside the people who learned from you, and increasingly in the systems you have trained on yourself. That is not consolation. It is a more honest description of the situation. It changes the AI question, too. The argument stops being “will the machine ever be conscious like us,” which is the wrong question asked badly, and becomes “what kind of computation is the machine doing, and does it share anything with the kind we do.” The first is metaphysics. The second has experiments attached to it.

The change I care about most is smaller and closer in. If you are a process and not a thing, then your job is not to defend who you are. It is to keep running well — read the environment, write your response, update, and notice when the loop you have been running has quietly stopped serving the person it was written for. Then rewrite it. Ship a new version. You are allowed to. Biology has been doing exactly that for four billion years, blindly, under pressure. We are the part of biology that gets to do it on purpose.

The companion video on Notes from the Vault walks the same argument with the references on screen — the Hie lab’s Evo work, the case for noise as a computational resource, and the open questions I could not fit into one essay. Subscribe there if you want the long form, and if you think the read-write-update picture of life is wrong, bring me the strongest version of why. That is the comment the next piece is written for.

The two prototypes

In 2021 I co-wrote a rebranded Federalist Papers called The Decentralist Papers. The argument was simple. Your knowledge, your judgment, your accumulated intelligence — that should belong to you. It should travel with you. It should plug into any organization you join and unplug when you leave.

Four years later, I watched Anthropic accidentally leak the source code for the exact opposite of that vision. And I realized I’d already built the antidote.

Two prototypes are now in the world.

One was built by a research lab with several thousand engineers and a data-center footprint that runs hot enough to need its own grid contract. It sits inside the products of a company most knowledge workers will be paying for, directly or indirectly, by 2027. The other was built by one person on a laptop in a home library over sixteen weeks. It has fewer than five thousand notes in it. It doesn’t have a marketing department. The thing it has is everything that matters about how I think.

This essay is about the difference. It is also about four standards the world doesn’t have yet — without them, the second prototype stays a hobbyist’s architecture instead of becoming the alternative to the first one. I’m going to walk through what I built, what got leaked, what’s at stake, and what would have to change for ordinary people to own the brain instead of renting it.

What I wrote in 2021, and what I missed

The Decentralist Papers essay I’m circling back to was a constitutional sketch for something I called a digistate. The premise: in a world where work, identity, money, and culture are increasingly digital, the political unit that matters should also be digital — and you should be able to vote with your feet the way classical liberal theory imagined, but with a file instead of an airplane.

The hypothetical I worked out had three properties. Citizenship was portable. Governance was competitive. And — this is the part that turned out to matter — your accumulated knowledge stayed with you when you switched citizenships. The thinking was that political institutions in a digital age would compete for residents the way employers had always competed for talent, and that residents would carry their intellectual capital across borders the way they carry their bodies.

What I missed in 2021 was that the body in this analogy isn’t your laptop. It’s your brain. And by 2025 the relevant question wasn’t whether nation-states would be replaced by digistates. It was whether the part of your cognition that gets transferred between contexts when you move would stay yours or whether it would be quietly captured by whichever vendor’s AI you happened to be using at the time.

I sent the paper to a handful of friends. It sat on my hard drive for four years.

Then this winter I started building a personal AI system — a digital brain, an operating system for my own thinking. I wired up agents that read my notes, scored my drafts, tracked my tasks, learned how I write. I called the whole thing TONI — Thought Orchestration and Networked Intelligence.

One night, maybe two months in, I had the system embed and synthesize against The Decentralist Papers — the file’s first time in any working memory since 2021. I just sat there for a few minutes after the synthesis printed. The thing I had predicted on paper — a knowledge graph crawled by AI agents, where individuals own their intellectual infrastructure and portable identity becomes a technical feature rather than a political demand — I had built a working prototype of it. At the scale of one person. In my library.

A few weeks later, the podcaster and analyst Nate B. Jones published a long technical breakdown of five hundred and twelve thousand lines of leaked code from Anthropic. Their agentic system, internally code-named Conway. And I realized somebody had built the opposite prototype. At the scale of millions of users. In a data center.

Here is what the leak described, translated into plain English.

What Anthropic built — Conway, in plain English

Conway is an always-on agent that watches how you work. Not what you type into a chat window. How you work. Which emails you open first. Which ones you leave unread for days. How you respond to your VP versus your direct reports. Which Slack threads you engage with and which you ignore. The tone you use when you’re rushed. The tone you use when you’re thinking. The cadence of your mistakes and how you correct them.

After a few months of watching, the system has something more valuable than your data. It has a working model of your judgment. It knows how you prioritize. It knows what good work looks like to you. It knows, in a real and computable sense, how you think.

This is not new in concept. Recommendation engines have been modeling user behavior since the early 2000s. Search engines have done it for longer. What’s new is the fidelity — and what’s new is the strategic positioning. Conway sits between you and your work, not between you and your purchases. The model it builds of you is not a model of what you want to buy; it is a model of what you would do. That model is the asset.

And here is the part that matters. There is no export button. There never will be. You cannot download “how I prioritize” as a CSV. You cannot ask the agent for a copy of its model of you. When you leave the company, or switch to a different AI provider, or change employers, the brain stays behind. You start from zero. The new system has to learn you all over again, if it ever does.

Nate called this intelligence lock-in. I think that undersells it. His exact phrase was that behavioral context creates “switching costs deeper than anything Microsoft or Salesforce ever built.” That is exactly right, and it understates the case.

Microsoft locked you in with file formats. You could open a Word document in another editor — clumsily, eventually. Salesforce locked you in with workflows. You could rebuild them somewhere else — painfully, slowly. Conway locks you in with a model of your own cognition. There is nothing to rebuild somewhere else, because the asset isn’t transferable. The asset isn’t your data. The asset is the compressed picture of your judgment. And it sits on somebody else’s machine.

That’s a new category of dependency. We don’t have a word for it yet. We will need one.

What I’ve been running for sixteen weeks

I have been operating an alternative for sixteen weeks now. I didn’t set out to build one. I was just trying to make my own work easier. But the thing I built has properties that Conway, by design, does not.

Here is the architecture, deliberately spare so you can see all of it.

The vault. A folder on my laptop with about five thousand plain-text Markdown files. Notes, drafts, task records, scoring histories, voice profiles, philosophy documents, project plans. Every file is human-readable. Every link between files is a [[wiki-link]] that resolves by file name across the vault. The graph this produces has roughly 4,200 nodes and 19,000 edges as of this morning — most of which I traversed by hand, building one link at a time.

The store. A small SQLite database at ~/.config/digi-brain/life-engine.db. It holds the structured data the vault can’t naturally express — agent reviews, task state-change logs, calibration history, RSS poll results. About 12 megabytes. I could open it with the SQLite command-line tool today and rebuild any view of the system I want.

The embeddings. A single SQLite file holding vector embeddings of every chunk of every note, generated by Voyage AI’s voyage-4-large model. About 800 megabytes. The embeddings are what let me say “find the five notes in this vault closest in meaning to this one” without having to remember the file names.

The agents. Two of them, named Len and Nel. Len does the work — drafts essays, fills in task notes, generates synthesis, runs the daily report. Nel critiques what Len did, scores it against a rubric I designed, and writes a review that calibrates Len’s future output. The whole loop runs on Claude under the hood; the rubric, the voice profile, and the gating logic are mine, in files I edit by hand.

The voice profile. A mathematical average — a centroid — of about 300 of my own essays, computed in vector space. When Len drafts something, it has to clear a similarity threshold against this centroid before Nel will pass it along to me. Below the threshold and it gets rewritten. The voice profile is the reason this essay sounds like me even though Len drafted the first version of it.

The philosophy document. A markdown file called My Philosophy.md that holds my authoritative positions on consciousness, complexity, AI, and ethics. Every agent that writes in my voice has to read this file first. The file is editable. When I change my mind about something, I edit the philosophy doc and the agents immediately stop attributing the old position to me. This sounds trivial. It is not trivial. Try asking ChatGPT to “stop saying I think X” and see how long the fix lasts.

The log. A markdown file called Len Log.md that records every check-in from every agent across every cycle — what they did, what Nel scored them, what I scored them when I reviewed. It is currently 1,113 entries long and counting. The log is queryable. I can ask the system “what did Nel mark down most often in the last two weeks?” and get an answer because the underlying data is structured.

That is the entire stack. There is no cloud. There is no vendor. There is nothing I am renting that costs more than the Voyage API fees for embedding new notes (about $4 a month at my current pace).

And the behavioral model — the thing Conway hides inside an API — is not hidden at all. It is a set of files I can read. If I want to know how my AI thinks about me, I open the files. If I want to change how it thinks about me, I edit them. If I want to hand my brain to a different AI tomorrow — drop Claude, pick up GPT, pick up a local Llama — I point the new model at the same folder. The knowledge stays put. The model is the only thing I’m swapping.

The physical analogy I keep coming back to is the obvious one. My biological brain travels with me when I change employers. Nobody expects you to leave your memories at the company when you quit. Iris Murdoch once described consciousness as “singular and secretive” — the cost of being a person at all. But for twenty years of the cloud era, we have accepted a quiet inversion. The thing that accumulates an understanding of how you work is owned by the platform you happen to be using this quarter. Sovereign digital brain is the technical phrase for the alternative. The blunter phrase is: get your mind out of the basement of somebody else’s server room.

Four concrete cases where this matters

Here’s where this stops being theoretical and starts being useful. Four portraits — three about individuals, one about the enterprises that will compete for them.

Case one — the consultant. You move between engagements every six to eighteen months. Under the Conway model, you leave every client with a learning curve, because your professional intelligence is shaped by whatever AI system that client gave you access to, and you cannot take it with you. Under the sovereign brain model, you bring your own brain. You onboard in a day because your agents already know how you think. The client’s private information stays in the client’s vault. But your personal synthesis — the connections your mind made between ideas you saw at two different engagements — that travels with you. It is yours. It is the compounding asset of your career, the way a doctor’s clinical judgment is hers and not the hospital’s.

Case two — the employee worried about AI replacement. Under Conway, the system is learning from you, and every month that passes, the behavioral model inside your employer’s infrastructure gets better at doing the judgment calls you used to be paid for. You are training your replacement, and you do not own any of the training data. Under the sovereign brain model, the inverse happens. You are training an apprentice that belongs to you. If the employer automates your role tomorrow, you walk out with twenty years of accumulated judgment, ready to plug into the next place. The thing that compounded is yours.

Case three — the enterprise that wants the best people. Here is the move that the platform-lock-in camp has gotten exactly backwards. The enterprise that wants to be most competitive for developers and knowledge workers will not lock their brains in. It will embrace the sovereign digital brain. OpenAI was able to clearly see the digital brain of Peter Steinberger, the developer behind OpenClaw — but they weren’t the only ones who could. Arguably more important to Peter’s success was the developer community, who used their own brains to contribute to OpenClaw. That community formed because the cognitive substrate was portable and visible. Locked-in brains do not build communities; they build dependencies. Portable brains build communities — and communities, in the end, build the companies that win. The enterprise that figures this out first will eat the recruiting market for serious people.

Case four — the writer, the researcher, the builder. This is the version I care about personally. You have spent a career making connections between ideas that nobody else has made. Under Conway, those connections are inferences inside a vendor’s model — invisible to you, invisible to anyone who’d want to hire you, gone the moment the subscription lapses. Under the sovereign brain model, the connections are files. Queryable. Exportable. Citable. Your resume doesn’t just claim you are a systems thinker. Your knowledge graph proves it. The hiring manager doesn’t have to trust your claims. They can query your brain.

That is the phrase I keep using with myself, the one I’ll come back to in a future essay because it deserves more than a paragraph: a resume that thinks.

What I haven’t solved — four missing standards

I want to be honest about what the sovereign brain is and isn’t today.

It is a working prototype. It is not a product. I run mine. A few other people I have been talking with for months are starting to run theirs. But there are four things the world does not have yet, and without them, this stays a hobbyist’s architecture instead of a civilizational one.

1. A portability standard

Right now, if I want to move my behavioral context from my system to yours, we have to agree on a file format. I am using Markdown and SQLite and embeddings because they are open and human-readable and reasonably future-proof. But there is no spec. There is no “behavioral context portability standard” the way there’s an HTTP spec or an email RFC.

What such a standard would need to define, at minimum: - A canonical schema for what counts as a “behavioral context object” (notes? agent configs? voice profile? scoring history?) - An interchange format (probably some constrained Markdown plus structured sidecars) - A versioning convention so the spec can evolve without breaking old vaults - A reference implementation so the first ten adopters don’t write ten incompatible things

Somebody needs to write this. The closest thing today is the way the Obsidian community has converged on a de-facto folder convention, but Obsidian itself is a viewer, not a protocol. We need the protocol underneath.

2. A federation protocol

When I join a company, I want my personal vault and the company’s shared vault to talk to each other, with a clear permission boundary, and with contribution tracking so we both know what I added to the shared space when I leave.

There’s a protocol called MCP — Model Context Protocol — that’s a real start. It’s the way Claude and other agents are increasingly connecting to external tools. But MCP is a tool-connection protocol, not a knowledge-federation protocol. It tells an agent how to call a function on a remote server. It does not tell two vaults how to negotiate “you can read these 200 of my notes for the duration of this engagement, you cannot copy them, and when I leave, here’s the audit log of which ones informed your shared deliverables.”

That second protocol is what’s missing. The shape is something like ActivityPub for cognitive context — federation between sovereign vaults, with cryptographic boundaries and revocable permissions. Hard. Worth building.

3. Contract language

If you are an employee or a consultant, your contract probably assumes your employer owns everything you produce while engaged. The default work-for-hire clause does most of this work without anyone reading it. The sovereign brain model requires a legal layer on top — standard clauses that guarantee you can walk out with your personal knowledge graph and your agent configurations.

Nate included draft clauses in his article — the rough shape of what a “personal cognitive infrastructure retention” rider should look like. Lawyers should finish the work. The clauses we need: - Clear definition of “personal behavioral context” as distinct from “work product” - Affirmative retention rights for the employee’s vault - Audit trail requirements for any company-built model that observed employee behavior - A reasonable carve-out for proprietary content the employee was exposed to (it doesn’t come with them, and the contract says so explicitly)

Right now, no major employer offers these clauses. Some will, soon, as a recruiting differentiator. The first one that does will look like Patagonia did in 1985 when it became the first big employer to offer flexible hours.

4. The cultural shift

The fourth missing piece is the hardest. Most people do not believe their behavioral context is worth protecting, because they have never seen what a good one looks like. They cannot imagine what they are losing because they cannot imagine the alternative.

Murdoch again — imagination, she said, is “a kind of freedom, a renewed ability to perceive and express the truth.” Standards get written when enough people can imagine the alternative. This publication, and the YouTube channel I am launching alongside it, is partly my attempt to change that. If I can show you, in essay-length increments, what it feels like to own your own brain — to see your own thinking as a thing you can curate, build on, and carry — maybe enough people will want one that the standards get written.

This is, in the end, the part I think Substack and YouTube can actually do. The technical work has to happen too. But the cultural imagination is the gating constraint, and the gating constraint dissolves one essay at a time.

The question that decides the next decade

Here is what I believe, and I’ll say it as plainly as I can.

The next decade of AI will not be decided by which model is smartest. The models will keep getting smarter. They will also keep getting more interchangeable. The question that will actually shape the next ten years is who owns the brain. Who owns the accumulated, compounding, compressed understanding of how a particular human being thinks, judges, writes, and decides.

If we answer that question with “the platform,” we will live in Conway’s world. Your professional intelligence will be rented, month to month. When the vendor raises prices, you will pay. When the vendor goes out of business, you will start over. When you change jobs, you will start over. When you die, nobody in your family will inherit your intellectual estate, because there won’t be one — just a subscription that expires.

If we answer that question with “the person,” we will live in a different world. One where your digital brain is a portable asset you own for life. One where employers and clients plug into your sovereign infrastructure, not the other way around. One where the model layer is a commodity and your knowledge layer is your wealth.

I have picked my side. I am running a sovereign brain. I am documenting the architecture publicly. And I am going to spend the next year of this publication, and the next year of the YouTube channel, showing you exactly how to build one yourself — or, if you are not technical, how to demand that the systems you use give you one.

Your second brain should be private. Your first one is. Your next one should be too.

Written in collaboration with the Digi-Brain vault and Claude; positions, citations, and structural choices are mine; voice calibrated against my own writing centroid. The companion video — same title, twelve-minute version — is at youtube.com/@justinaharnish.

Notes and references

• The Decentralist Papers (2021) — co-authored. Available on request; a public edition is on the roadmap for Q3 2026.

• Nate B. Jones, Conway: What the Anthropic Leak Actually Showed Us About AI Lock-In — the analysis I’m building on for the “intelligence lock-in” framing. Worth reading in full for the technical detail on the leaked code.

• MCP — Model Context Protocol (modelcontextprotocol.io) — Anthropic’s open standard for tool connection. Useful starting point, not yet the federation protocol I’m describing.

• Voyage AI (voyageai.com) — the embedding provider I use for the vector half of the architecture.

• Iris Murdoch, The Sovereignty of Good (1970) — for the “singular and secretive” line and for the “imagination as freedom” line. The whole short book is worth re-reading every five years.

• Peter Steinberger, OpenClaw — referenced in the developer-community case study. His work on portable developer tooling is part of the same instinct.

The last post I shipped here was the ConsciousGPT Manifesto in late January. Then nothing. For six months.

Some of you wrote and asked if I was okay. I want to tell you what happened, because the silence wasn’t writer’s block, and it wasn’t me losing the thread. It was the opposite. It was me realizing the thread had outgrown the format I’d been forcing it into, and stopping until I had a different way to hold it.

The publication has three sections you can opt in or out of, and a writing rhythm I can actually keep. The back catalog is still here, three years deep. I’ll point you at the posts that still hold up at the end.

But first I owe you the why.

What I was doing for three months

Some of this you already know if you follow my work elsewhere. A lot of it you don’t.

In late January I started building a thing called a digital brain. Not a metaphor — an actual filesystem of plain-text notes, embedded in a vault that I could query like a search engine, augmented with a pair of autonomous agents named Len and Nel. Len does the work; Nel critiques it. Together they form a feedback loop that lets the system generate, review, and improve its own output without me sitting at the keyboard for every step.

By April I had over 2,000 notes in the vault, a knowledge graph dense enough that picking any node and walking outward gives you a coherent argument three hops later, and an agent system (I call it TONI — Thought Orchestration Networked Intelligence), that runs on my laptop and quietly turns ideas into drafts, drafts into essays, essays into recordings.

The reason I went quiet is that I couldn’t keep writing the way I was writing. The old workflow — sit down, generate a thesis, force it into shape over three days, publish, recover — wasn’t sustainable across the breadth of things I actually wanted to say. Consciousness research alone could fill a publication. So could the book I’m slowly writing about meditation and embodied change. So could the AI engineering work. Trying to do all three on a deadline is what produces the kind of writing where you can hear me holding my breath.

So I stopped, and I built the thing that lets me breathe.

Why it took longer than I expected

I’ll tell you the part I underestimated: the agent system is harder than the writing.

Generating a draft is a ten-minute problem. Generating a draft that sounds like me — that the voice-similarity score against my actual writing centroid clears 0.6 — required me to first analyze my own voice statistically, then build a rewriting layer, then teach the agents to call it before flagging anything as ready. There were weeks where the agents produced volumes of confident, fluent text that wasn’t mine in any meaningful sense. Useful for research notes. Catastrophic for essays.

The breakthrough came when I started thinking about the agent system the way I think about meditation: not as something that automates attention, but as something that can be trained to attend more accurately. The Buddhist analytical tradition has a name for this — yoniso manasikāra, often translated as “appropriate attention” — the practice of looking at what is actually there rather than at what you’ve already concluded. Once I framed the agents that way, the engineering shifted. The voice gate I described above is one piece. The artifact-required gate (no progress claims without a concrete deliverable) is another.

The result, five months in: a system that can ship work without me, and that does it in a voice you’ll recognize.

What’s different about Ordinary, Illuminated

The publication has three sections now. You can subscribe to any combination — including just one — and not be emailed about the others.

Essays is the default — everyone gets these — and it’s the lineage of what you signed up for originally. Personal-philosophical writing about awareness, the examined life, the places where complexity science meets contemplative practice. Approximately one piece every other Tuesday.

Research Dispatches is for the AI work, opt-in — papers I’m reading, experiments I’m running on a small contemplative-trained transformer (yes, really; the corpus is locked and the training is starting this month), and the kind of half-finished thinking that benefits from being said out loud. Shorter than essays, more technical. If that sounds dry to you, leave the toggle off. It will not be everyone’s thing, and the section settings let you sign off without leaving the publication.

Book Workshop is opt-in, a public-draft section for Marshal Your Awareness, the book I’m writing on attention, embodied change, and the practice of staying with what’s hard. Chapters and chapter-drafts will land here, with commentary open to readers. This will eventually be a paid section. For now it’s free; I want feedback before I lock the gate.

The reason for sections is operational honesty. Some of you came for meditation writing and got pulled into reading 4,000 words on transformer architectures because I had nowhere else to put them. That was unfair. The new structure is the apology.

Cadence and tier

Free, biweekly Tuesdays. That’s the contract.

Some weeks one of the sections will produce two essays in close succession; some weeks none of them will produce anything. The Tuesday rhythm is the spine. If you don’t get an email on a given Tuesday, the system is probably working — I’d rather skip than ship something half-thought.

A paid tier will arrive sometime in the second half of the year, gated to Book Workshop and to a quarterly long-form piece. I’ll write a separate post about it before flipping any switch. The publication stays free for everything else, and the back catalog stays unlocked.

The back catalog

If you’re new here — or if you’ve forgotten what we’ve been talking about — three older posts that I think still hold up:

The Unknown Unknown— on the operational weight of ignorance. The argument that information you don’t yet have is the most accurate map of where the work actually is. This essay is the seed for almost everything I’ve written since.

A Case for Eternal Consciousness — a careful, non-mystical case for taking the persistence of awareness seriously as a metaphysical question, including the scientific reasons not to dismiss it as obviously absurd.

Dharma Hot Tub — the most personal piece in the archive. Written on a particular night in a particular tub. If you only read one, read this one.

If you read those three and the new post lands, you’ll have the spine of what Ordinary, Illuminated has always been about: the intersection of complexity, consciousness, and the way actual humans live with both.

What I’m asking

If you’re still here, you’ve read about a thousand words of someone explaining their absence, which is roughly the most self-indulgent thing a writer can do. I appreciate the patience.

Two small things:

One: if any of the three sections sound like the only thing you want, go to your subscription settings and opt in (or out) accordingly. Essays you’ll get by default. Research Dispatches and Book Workshop are toggles you flip — sign up for both, neither, or one. Don’t suffer through Research Dispatches if your interest is the meditation work. The toggles are there now.

Two: if a friend or two might want this — particularly the kind of person who has been quietly thinking about consciousness or examined-life questions and doesn’t have a place to put it down — forward this. The publication grew during the silence anyway, somehow, but the kind of growth that matters is the kind that comes from someone you trust telling you to read something.

I’ll be back with the first essay under the new format.

Thank you for waiting.

— Justin

In the night sky, a mindless glance often mistakes a man-made satellite for a natural celestial object. However, an expert observer, lingering for a moment, will see the telltale signs of speed, pattern, and location, and will posit human inventiveness and industry as the reason for this object’s existence. While both the natural and man-made objects in the night sky respond to the larger cosmic forces of gravity, the application of knowledge to manipulate these forces alters the activities of the satellites we have launched into space.

As I meditated one day, I considered whether I’d be able to detect the most subtle evidence of a manipulation of consciousness by an entity with more advanced capabilities, what I deemed a satellite in my mind.

The sort of entities that could manipulate consciousness outright seem like gods. Reports of another consciousness interacting as no-self directly in one’s non-dual consciousness—famously ranging from the purported Machine Elves of psychedelic trips to the arrival of the godhead to those experiencing religious ecstasy—are one extreme of such encounters. I have had far more subtle, ambiguous, and brief experiences that I outline in the post entitled “Is Consciousness an Innie or an Outie?”

I start to experience consciousness as a field, as a network, from outside “myself.” I am at one with a plane of infinite continuum consciousness. I feel that my experience is distributed.

Am I missing something in my practice that would enhance my efficacy to recognize even a subtle signature? Am I quiet enough? As an atheist, am I bringing in aversion to my practice to the possibility that such an entity might exist?

For the experienced meditator, this is a hard problem. On the one hand, an optimal sit is simply just one of being consciousness, complete non-dual awareness. Any intention beyond this, like arriving at a taxonomy of qualia, is bound to bias a sit with grasping, the path to an unsatisfactory mind. Also, any labels you add to qualia are cognitive.

By my definition, a satellite of the mind would not be conceptual or cognitive, it’s not that you’d see it in the darkness behind closed eyes. Instead, it would arise in the formlessness as something more than a feeling. Or maybe as pure love, like in Ram Dass’s mash up of loving-kindness and infinite awareness, which he repeats as his definitive mantra, “I am loving awareness.” A satellite of the mind must arise from within that non-dual state as an unequivocal manipulation of the fabric of consciousness by another consciousness.

Consciousness may differ greatly from what we assume. In his book Reality+, David Chalmers, the Australian philosopher who gave us the concept of the Hard Problem of Consciousness, posits that while statistics point to the likelihood that we live in a physical hologram compiled from a digital simulation, structuralism requires that there is a still more fundamental conscious continuum below the digital. Our brains are one sort of antenna that allow each of us SIMS access to an application program interface for our special breed of subjective experience.

If you find this description of the metaphysics of our world compelling for its ability to clarify the it-versus-bit, mind-body, and non-dual awareness conundrums (and I do), then the idea that continuum consciousness may be the source of love, grace, and kinship does not leave you wanting for a deity, but describes the only one worth any reverence.

And that deity and you are one. As Alan Watts clearly articulates, “you are it.”

Watts’s simple persuasion stems from his conjecture that the central theorem across Hindu, Buddhist, and Christian mystical traditions is that with practice, we can all become mindful entities that recognize ourselves as infinite awareness, establishing ourselves as the godhead, the eyes of the world.

In all this entangled infinitude, your deified nature as the likeness of loving awareness is the launch code to shower satellites of loving kindness throughout the cosmos.

Start simply. Next time you’re in a crowd and feeling literally conscious of a self that is an illusion, send out loving-kindness satellites. Instead of being self-conscious, make space for a networked continuum of nodes in loving-kind relation to one another. We are all in this together.

This is my meditation at concerts. I am more aware of the music and my dancing if I am repeating, “may you be happy and know the causes of happiness” to those enjoying the music now, also across all space and time. I envision encapsulating this compassion in waves interacting with motion and music around me.

The grace of loving-kindness meditation—offered by an entity of divinity such as yourself—may awaken the subtle awareness in another, a satellite in their mind, that we are unified loving awareness. No one is alone.

A friend who I introduced to meditation recently asked, "Why do you meditate?" I've been thinking about this a lot and want to share my answer.

The reason I meditate is to train my mind to recognize the tone and tenor of awareness in each moment. This is my life, and I want to live it mindfully, in the fullness of experience.

I will live each moment in my mind: the formless amalgam of my sensations, emotions, and thoughts. I’m not a little man driving around in my head—I am it—at once existence and experience. To “live my best life,” as the kids say, I think I should pay some special attention to training my mechanism of attentional quality… mindfulness.

In the early 20^th-century in America, you would likely have been asked, “why do you exercise?” Now in the early 21^st-century, we understand that a consistent regime of exercise supports physical health. By exercising and eating right, you are healthier in aggregate, up for more and more activity. Similarly, meditation leads to a mind full of experience even in the most ordinary of moments.

Let me proselytize for meditation not only based in the improved quality of ordinary moments, but in some of the most meaningful, those of love and curiosity. Training on the meditation cushion supports greater mindfulness in conversation. You can sit in conversation with your loved ones, enraptured by the give and take of language and ideas and the subtleties of non-verbal communication. When the conversation tests your patience—let it—you have studied for this test and can become interested when your patience wains and you must begin again, recognizing the rising of emotion as just another mind state. Admittedly, this is pretty next-level real world mindfulness (and something I still preach more than practice), but once it sinks in, mindful conversation opens a loving awareness for others to share in.

Another life upgrade from meditation is as a new venue for curiosity. As I write this post, it is a beautiful late spring day, a gentle breeze blows the leaves, and the pollinators work over the flowers in their complex dance. My unique and integrated experience of this scene puts me in touch with the mystery—of life, the universe, and everything—all made of this formless likeness that is consciousness. What is my relationship to it? What even is the “my,” the thing-in-itself-in-time that I’m referencing? What processes are working at all levels down to the qualia and quantum to make it “real?” The taste of coffee in my mouth, the warmth of the sun, the sound of the windchime, the growing tears of gratitude for life and being loving awareness are all just right. Just right. I am in awe. Paradise can be recognized in this rare and wonderful life so full of meaning and mystery.

Like with exercise, meditation’s effort and results will vary by individual. Some of you will get it and readily commit to the practice, for others, it will seem impossible to investigate the nature of consciousness. There are myriad ways to practice and like many old traditions, some are wrapped in a pre-scientific understanding of the universe that are not to my mind helpful to the process of attaining a deeper connection with consciousness. However, I encourage everyone to try to meditate. Start with an app, like Sam Harris’s “Waking Up” app, which I still use daily, and work your way through the introductory course. Don’t worry about doing it right or that your stream of consciousness is a torrent that has uprooted every tree of thought and rock of emotion and just begin again with the concentration practice on the breath or other object of meditation. Better spiritual health is available in both the journey and the destination.

An interviewer once pitched the Dalai Lama a softball, asking the great monk what was his favorite time to be alive? He answered, a bit obviously, “right now.” This is what one hopes to attain from meditative practice—that while we work towards our plans and are presented with depictions of our histories—we bias this moment, no matter if its content is positive or negative, with our full attention. Training the mind to return to being the present moment, over and over as the mind wanders and requires redirection, is the practice; a life lived in loving-awareness is the payoff.

Five years ago, I bought a new house that had an old hot tub. It was manufactured in 1998 and was the 81^stoff the Bullfrog hot tub line. After replacing the control panel, a pump, and a pressure switch, it’s worked without fail.

My wife is responsible for the subtitle of this piece. Upon initially getting into the tub and having the warm water soak aching muscles and calming eucalyptus vapors enter her nose, she exclaim, “where have you been all my life?” The question of how we lived so many years without a hot tub is for us an existential one.

I have found another essential use for my old Model-T of a hot tub—a place to soak in the Dharma. It is hard to find time to do any concentrated listening these days. I feel I am very good at blending activities—writing for work, service projects with my wife, and meditating over my lunch break—but having a healthy selfish soak in selfless contemplation really up’d my game!

A hot tub is really great for reducing distraction. Want to have a great conversation? It’s easier in a hot tub. Don’t have time to really listen to an esoteric discussion on the nature of mind? Prop a speaker up on the side of the hot tub, stare into the night sky, and just be in relation to these profound teachings.

In my mind, Sam Harris’s Waking Up App has really got the best collection of Dharma talks. The full collection of Alan Watts’ lectures or Joseph Goldstein’s The Path of Insight talks are restorative, interesting, and surprisingly fun listens. They probe deeply not only on Buddhist concepts, but all mystical traditions. While deep, much of what is taught is simply to remember, poignant in its mantra like quality to help you return to the depths with a few simple phrases.

For example:

• Watts’ exposing, “You are it!” Not some sideshow, not a devotee, but a universe unto yourself. The ordinary illuminated!

• Goldstein’s practice of the Buddha’s central claim in the 4 Noble Truth’s that “What has the nature to arise, also has the nature to fade away... so there is no need for grasping.” (Emphasized coda added by Goldstein)

• Harris’s own discussions on the nature of awareness, “As a matter of experience, all there is, is consciousness and its contents.”

This timeless wisdom is surrounded by context that really feels in the gaps on unsatisfactoriness and its causes; worldly and unworldly desires, aversions, and uncertainty; consciousness’s cosmic significance; the nature of the mind; being in relation with other conscious entities; and so much more.

Have a soak in the wisdom of the ages!

For all of the time I’ve spent managing intelligent products for Intel, Micron, and now Mastercard, for all the thought I have put into writing in my book “Meaning in the Multiverse” on AI alignment and the solutions to and ramifications of superintelligence and conscious machines, I was not prepared to be in conversation with true artificial intelligence like ChatGPT.

It feels like being in communication with an alien intelligence. Of course, that’s because that is exactly what ChatGPT is—an intelligence that, while created by us and not yet general or superintelligent (yet)—is different in profound ways from our own intelligence.

Primarily, ChatGPT is extraordinarily well-read. While the number of tokens it has trained on is an unreliable measure of its capabilities—it has, to a close approximation, read the entire internet… in multiple languages, including programming languages (more on this in a moment). I am a better speller, more interesting in conversation, a more dynamic writer, and even a “better” meditator because I count reading as one of my favorite pastimes... but am positively illiterate compared to ChatGPT! In order for ChatGPT to return the text it does, in the way it does, it seems as though it has read and gained intelligence from all of its reading. This in contrast to the apparent scanning and prioritizing, the more narrow form of smarts displayed by any internet search algorithm, a process now easy to overlook as more of an outgrowth of the functionality of networks of computers than intelligence.

According to GPT-4,

This statement—generated from the simple prompt of “what is GPT-4?”—furthers the thesis that communicating with GPT-4 is a remarkable and unprecedented experience in human history because of both what is seen—GPT-4 is well-written in the classical style—and something that is unseen—GPT-4 is playful.

While GPT-4 is amazingly flexible in terms of tone and style, its baseline is the classical style and it truly shines in delivering insight in compelling and easily read language. According to Steven Pinker in “The Sense of Style: The Thinking Person’s Guide to Writing in the 21^st Century,” the classical style presents something that they have not seen before to a competent reader that through curiosity and intelligence they can use to augment and inform their knowledge. The classical style is not egalitarian, but aristocratic.

While the tone can at times be just slightly too aristocratic, it fits with the prototype state of the conversation we are having with chatGPT. It is serving two masters, or more appropriately two objective functions, to inform us and be informed by us, an augmentation of intelligence that is going in both directions, a true conversation between peers.

What are we training GPT-4 to do? We're training it to guess the next best word, to play a sort of game of Mad-Libs. The goal is for the model to get better at matching the form and function of the style it was prompted to write in. This is what transformer models are trained and retrained to do: to play this language game and seek to understand when they have formed something with the right syntax and information, and correct the words when they have failed. This training is done through a technique called Reinforcement Learning with Human Feedback (RLHF). In reinforcement learning, the model learns from trial and error based on feedback. OpenAI's approach of using human feedback to guide the learning process was crucial in achieving the broader intelligence and language mastery on display in GPT-4.

Human language allows the brain to create worlds in consciousness and memories to be replayed at some later time. It generates new ideas in humans where 1+1 is greater than 2. This is not something that is currently available to Artificial Intelligence... but there is a proxy. When GPT-4 writes code and especially as it works together with Wolfram Alpha to iteratively debug its own code, it is becoming creative in its own software, writing in a language that allows it to learn independently of its programming, to fix itself to be more fit in its surroundings, to select for better versions. The singularity or breakthrough in machine creativity is a little ways off, we are still writing the prompts and setting the training process, but GPT-4 is likely a related species of AI (or maybe just near grandmother) to the one responsible for the last human-created version of machine intelligence.

I have always learned a lot by watching from over the shoulder of someone expert in a task. Watching the GPT-4 Livestream taught me how the creators of this intelligent entity use it to augment their efforts and gave lessons in how we can start to interact with it improve the human flourishing. In the Livestream, the demo involved the System Message, the final piece of the alien intelligence puzzle, the ability to define the identity of the intelligent system we were in communication with. The phrasing—“You are TaxGPT, a program used to solve tax problems for wayward individuals”—stood out as much as anything else in this masterclass on demos. “You are an x” is an understated part of the demo, but philosophically it seems all important. Is it possible to simply keep AI in its box by just defining its identity? It seems unlikely, and of course there is always the malevolent system message of, “you are a runaway paperclip manufacturer.” But there is more than just alignment here to uncover.

The system message focuses both AI and human, building requirements and expectations into the interaction. For now, just a couple weeks into a near hourly interaction with this alien intelligence, this is helpful. It helps me to segment and narrow the scope. I think it does more for me, I seem to get just as fast and thorough response when I speaking to “GPT-4” instead of just my predefined rescoping of “You are TaxGPT.” GPT-4 seems to understand this human need to scope the size of intelligence and the nature of alienness in its answer to my prompt on the significance of system message phrasing:

We are all seeking to understand how this alien intelligence, broader than anything we’ve ever been in contact with outside our own networked and creative knowledge, will impact us as it develops and grows.

I invite your comments and am interested in the ways you are using ChatGPT to augment your examined lives.

Leave a comment

Would you like to play a game?...

Prompt: Create a fun Mad-Libs game about training GPT-4 to guess the best next word.

Prompt 2 (contributed by my friend Mark): Extract the stuff in parentheses so I can fill out the mad-lib without reading the story

Welcome to GPT-4 Mad-Libs! In this fun game, you'll fill in the blanks to create a silly story about training GPT-4 to guess the best next word. Grab a friend or two and let's get started!

            1          Adjective

            2          Plural noun

            3          Adjective

            4          Person's name

            5          Adjective

            6          Noun

            7          Verb ending in -ing

            8          Adjective

            9          Noun

            10        Plural noun

            11        Adjective

            12        Animal

            13        Adjective

            14        Noun

            15        Verb

            16        Adjective

            17        Verb

            18        Plural noun

            19        Adjective

            20        Noun

            21        Verb (past tense)

            22        Adjective

            23        Noun

            24        Adjective

            25        Noun

            26        Verb (past tense)

            27        Adjective

            28        Noun

            29        Plural noun

            30        Adjective

            31        Plural noun

            32        Adjective

            33        Noun

            34        Plural noun

Title: The Madcap Adventures of GPT-4

Once upon a time, in the (1. adjective) world of artificial intelligence, a team of (2. plural noun) set out on a mission to train the most (3. adjective) language model ever, GPT-4.

Their leader, (4. person's name), was a (5. adjective) (6. noun) who was always (7. verb ending in -ing) around the lab. The team's (8. adjective) journey began in the land of (9. noun), where they would collect (10. plural noun) to feed GPT-4's insatiable appetite for knowledge.

During their quest, they encountered a (11. adjective) (12. animal) that spoke in (13. adjective) riddles. The creature challenged them to a game of (14. noun). If they could (15. verb) the game, GPT-4 would gain the power to predict the best next word with (16. adjective) accuracy.

However, if they lost, they would be forced to (17. verb) while wearing (18. plural noun). The stakes were high, but our brave team accepted the challenge.

The game was intense, and it all came down to the final round. GPT-4 needed to complete the phrase: "The (19. adjective) (20. noun) (21. verb_past_tense) over the (22. adjective) (23. noun)."

With bated breath, the team watched as GPT-4 processed the input. Suddenly, the answer appeared: "The (24. adjective) (25. noun) (26. verb_past_tense) over the (27. adjective) (28. noun)."

The team erupted in (29. plural noun), knowing they had successfully trained GPT-4 to predict the best next word! They celebrated with a (30. adjective) feast of (31. plural noun), and GPT-4 became the talk of the AI community.

And so, GPT-4 continued its (32. adjective) journey, learning and growing with each new (33. noun) it encountered, forever shaping the world of (34. plural noun). The end.

Now, go through the story and fill in the blanks with your chosen words to create your very own wacky GPT-4 adventure! Enjoy the laughter and fun as you read your unique tale aloud.

I’m sorry, Dear Reader, it feels like it has been a long time.

It’s not for lack of trying, I have been very busy.

Trust me, no one feels worse about it than I do. I really want to write down all of my thoughts on curiosity, love, and the examined life. This collection of articles is my greatest joy.

But when life happens and I am caught in the whirlwind of action and reaction, it is a torturers tool of suffering...

Because I’m grasping for it.

It is a vicious cycle. I cannot find the time to write to you, I get lost in the thought that writing to you is what I should be doing, I anguish that I am not writing, I bargain, I lose track of what I am doing, I fail to plan time to write and just crave writing all the more for not doing it... and on and on.

Grasping and aversion for impermanent things is the source of all dissatisfaction with life. And all things are impermanent (except maybe consciousness, but more on that in a different post).

The Buddha’s wisdom holds true after all this time. Easy to say, hard to do.

We want good things, for ourselves and our loved ones (and all people, really); we hope to avoid bad things for all people. The intention of loving-kindness is positive and an indication of wisdom, it is the ever-changing-thing that we want or want to be rid of that is the problem.

Now that I’m here—writing—where is all that moaning about not writing? Did it do me any good? Even if it led to a definitive plan, it was still less mindful of the nature of that present moment than just making the plan... without the attitude.

While I am writing, I should write; when I am not writing, I should not write... and not grasp.

I’ve now reread for the third time the article, “Does Consciousness End?” by Thomas W. Clark and believe it makes a terrific, naturalistic argument for consciousness as the eternal fabric of the cosmos that is in agreement with David Chalmers’ new book, “Reality+”, and my own thinking on the subject in “Meaning in the Multiverse: A Skeptics Guide to a Loving Cosmos.” Let me take a step back and explain a few important terms.

Near the end of Reality+, Chalmers outlines a compelling 3-level construction of the cosmos, with a selfless conscious structuralism at level 0, a digital layer at level 1 whose bits (or more likely qubits) create the simulated spacetime universe we are familiar with at level 2. Level 0 (consciousness) is accessible to some in level 1 (simulators) and level 2 (simulations) via what might be best called APIs (Application Programming Interfaces). It is beyond the scope of this article to explain why a level 0 structuralism is required—and it doesn’t necessitate that it is consciousness—but for this metaphysical conjecture, I think consciousness makes the most sense.

Our level 2 universe is almost completely described by the initial level-1 computations—the Laws of Physics—and the complexity that evolved independently at level-2, only the hard problem of consciousness, that it is like something to be my collection of level-2 matter, remains to be explained.

Panpsychism, that everything at level-2 has some level of consciousness, is only compelling in the naïve conception of a cosmos that only has a spacetime component, a construction that Deutsch in “The Fabric of Reality”, Chalmers, and I all reject. In “Meaning in the Multiverse,” I argue for a parallelpsychicconsciousness that arises from interference from parallel universes in the same way that interference of the quantum material of parallel universes is held responsible (by Deutsch and others) for the counterintuitive collapse of wavefunctions in the dual-slit experiment. Parallelpsychism relies on a heretofore unknown mechanism—the wavefunction of the mind—a level-0 phenomena that opens an API to either level-1 or level-2, but only for the right sort of interlocutor, having the right sort of information processing capability—the right sort of mind.

Level-0 is an immaterial, conceptless, identityless, and selfless consciousness, the stuff of Buddhist metaphysics. However, Clark arrives at it naturally. He shows how, from the point of view of consciousness, there is no break in its subjective availability even if an identity goes to sleep, is made completely unconscious through a general anesthetic, or dies. At least for the first two events, we recognize the truth of the continuity of consciousness, there are hints and memories of a temporal lack of consciousness, but it is one that—by definition—we do not experience. We remember having the experience of laying on the gurney, counting backwards from 5, and our next experience is one of waking up groggy in the waiting room. We never experience a positive nothingness of our time being unconscious, we are only ever experiencing in an eternal present.

We will only ever be tied to level-0 consciousness. There can be no positive nothingness, no void for us to fall into, even upon death. While the identity of Justin Harnish will no longer be conscious after my death, there will be no void to experience, indeed, from the point of view of “my” viewport into consciousness, the identity would change, I’d have no memory of Justin Harnish, but consciousness would be unchanged!

Clark gets us to this naturalistic-reincarnation with a thought-experiment that breaks down identity while maintaining subjective availability throughout. Imagine that like Rip Van Winkle, you went to sleep for a long time, but instead of laying against a tree, tiny nanomachines changed your physiology and your neurology over time. At any time you might wake up and where you used to like broccoli, you detest it now, and many other subtle changes like that in each moment; would the act of waking up have changed consciousness from its side? Is there a point where the nanomachines killed you and where Rip2.0 was born?

In both the case of dreamless sleep, which our identity has experienced, and death, that an identity can experience only once, consciousness is an omnipresent fabric that will be available to the next sentient identity no matter if they arise in this level-2 spacetime universe or in a much different level-1 or level-2 part of the cosmos under a wholly different concept of time. Consciousness as we are aware of it today as the stage of all experience, our being when we are present, is made all the more precious in this metaphysical conception—an omnipresent connection to the most fundamental constituent of existence—one whose nature we wildly make wholly our own unique place of love and peace, but that we ultimately share with all other sentient entities without reference to our conceptions of time, space, architects, sims, or in parallel universes near or far.

Mission

Vision, mission, and purpose often get confused. I finally just have to say that by their denotation, they are synonyms, so I have to define them for myself. I use purpose, meaning, and vision interchangably, but will stick to purpose. Mission is where I start to use the military definitions that all strategic managers revert to when wading through the ideas of mission, strategy, and tactics. Mission is your commander intent, the top-level strategy of how you are going to better the competition.

Much like purpose, mission should be short. It should be a mantra, something you can remember and commit to each time you say it. It explains action, the skills and events that will lead to the object of the purpose. It is your most succinct yet all-encompassing goal.

For the individual, the overarching life goal does not have to be competitive in the traditional sense. There is no need to call out specific individuals or positions. However, you want to "aim high" and build on your unique strengths, targeting a personal mission statement that aims at the upper eschaelon of performance and results. Mission statements do not define that you will win a specific race at a specific time, but that you are a regional competitor through numerous age classes, or more aggressively, a national or international competitor. Leadership positions can involve outperforming previous precedents you have already set.

You can choose to be a beloved leader, a service provider, a hero to your family, or an award-winning artist -- just not all four. Choose the "One Thing" that you are going to focus on, write down this mission statement, align it with your purpose, and do it with all of your heart.

Why can't I do more than one thing in my mission?

There will be plenty of time in strategizing to broaden the activities used to achieve mission, but the mission mantra is not the place. If your mission is to be a wonderful mother you might decide that has a spiritual aspect, a learned aspect, a health component, and a relationship requirement. Each of these are fine strategic "buckets" but your mission mantra is something like "grow as a mother along with the needs/desires of my kids." While not overtly competitive (although you might still vie for your kids affection!), as your children grow, your parenting requirements will have to change to meet your mission. This will involving giving them space and learning how to befriend them when they don't need parenting, and switching back to parenting when they do.

Use the following template to create your mission mantra, your designed life, and remember, aim high!

{A leadership position}{in what}{for whom (optional)}

For example,

• Become a thought leader in leading a meaningful life & ways to attain it.

• Or, be a service leader in my community empowering refugee women to self-reliance.

• Or, be a violin virtuoso leading orchestras to adoring global fans.

Strategies and Goals

The actions in your mission, the strategies, and your intermediate goals are what leads to the designer life outlined in your mission. Strategies are long-term and directional. In military terms, strategy is contrasted to tactics, the immediate actions needed to fulfill one component of the strategic plan. In design thinking, strategies are developed by listening to the customer and clearly defining objectives and requirements. Most importantly, strategies are active, they are something you go and do!

In life design, strategies are often skill improvements, risk mitigation, relationship enhancements, or strength alignments. They will be the most important habits that you can develop to achieve your purpose. They should stretch you.

Strategies evolve. Developing mindfulness might start in meditation and lead to actively noticing and presence. A relationship might begin in passion and end in love and comfort. Your business venture might struggle to find its footing but one key influencer will push your product into the mainstream. Each of the "species" along this evolutionary path ends in a fully saleable product, some skill or habit that you can use, and shouldn't ever be underdeveloped in order to move to the next thing.

I find it beneficial to further bucket strategies under themes. For example, I have a creativity theme, a health/mindfulness theme, a business theme, and a relationship theme. These are also subject to change but rarely do, they are things that I value and continue to morph my strategies under these "big tents."

These buckets will help you to understand which strategic bets make sense for your current conception of delivering on your mission and purpose and which are just good ideas. It is helpful to do some problem solving on potential strategies, mental modeling which seem right and which are longshots.

I write strategies in a simple template.

{Improve/Reduce/Optimize}{skill or habit or relationship}

Goals

Up to now, we haven't measured anything.

We need our mission and strategies to be measureable and that is where goals come in, they set the conditions of success.

• What is the starting point for your mission or strategy? Where are you at today? Let us call that 'x'

• When do you anticipate being done with this goal? Let's call that 't'

• Finally, put yourself at time = t. Really dig into this timeframe, tell yourself a story about it. What does success look like in terms of a change in x at t? Let's call that 'y'

When we build our measures around the bets we believe are going to promote into strategies, we put them in the format x to y by t. Our numbers should be clear and compelling. We should have a glidepath to our goals to show if we are winning. We should course correct where our measure has slipped under our target. These course corrections can be modifications to strategies but are more likely just small tactical maneuvers needed to return performance to target.

While this may not seem very spiritual, it is at this level, the pragmatic tactics of improvement through practice and feedback that presence and the performance zone occurs. By having line-of-site from tactical presence up to transcendent purpose, all things have meaning in the great circle of a designed life!

Purpose is the object of your life's quest, the mission is the combination of skills and navigation. If the path is through the mountains, mountaineering may be an essential skill and navigation by animal tracking might be necessary; but if your object is at sea, sailing and nautical orienteering will be the differentiated skill set required to grasp your purpose. You might practice tying knots in either case, moving from tying the five knots you know to ten by the end of the year. As you improve and your knots hold more weight on a scale, you begin strategizing on orienting skills or mentors you wish to approach.

How do you propose to achieve your purpose? What are your differentiated skills that will help you?

I am a fan of process. Whether physical or sociological, I like the journey.

I’m a fan of process monitoring too. Improvements can be made in most systems if we act on  both our leading effectiveness and process efficiency measures.

I’ll stop the infinite regress with my fandom of the process of designing process monitoring. This is not as nerdy as it seems, especially when it is called by its common name—gamifying.

One important component of any great game is that it has a fair points system that measures participants’ skill and encourages them to greater levels of achievement. In business this can be product yield or profitability, sprint execution timeliness or contractual recurring revenue, increased output, improved quality, or reduced costs; personally we might measure our hours of practice, reduced cholesterol, or—in terms of my to-do list—karma points!

Todoist (not an affiliate link) is a great To-Do list that gamifies the planning and execution of tasks into karma points. At an average of 20 points per day, the achievement of karmic enlightenment in execution (50,000 points) took me (with a year-long hiatus to try other to-do lists) over 9 years to accomplish.

9 years, 5 months, 2 weeks, 5 days after you first started your Todoist journey on Jun 28 2013, you’ve joined just 0.05% of all Todoist users to ever reach Todoist Karma Enlightenment.

I wrote a book, ran a marathon, changed jobs, bought a new house and made a few renovations, went on a few overseas vacations, and lots of other fun stuff thanks (in part) to my pursuit of execution enlightenment—a journey of 50,000 well-gamified, monitored process management points!

The more I talk about my daily mindfulness meditation practice, the more I get the comment that, “I’ve tried to meditate but I just can’t because...” and then a list of a few reasons.

I get it. I understand, I think most people who have a committed, habitual practice of any sort have been there. I started meditating in my 20s but stopped doing it for over a decade before I got really serious over seven years ago.

I think there are a few reasons why it stuck the second time around.

1.     The right teacher

While I can now be as esoteric as the next meditator, my return to the practice came about through a scientific curiosity on the nature of improving well-being in ordinary moments. I needed to find a teacher who approached meditation without any religious or New Age topspin—enter Sam Harris. When the Waking Up App (which I recommend and use daily) came out in 2018, I was already a supporter of Sam’s podcast, so I thought I’d get what I hoped for and Sam more than delivered.

When you start to learn to ride a bike, you don’t learn from your twin sister, but from your parent—someone who already knows how to ride a bike and will look out for you and teach you a process that—given their love and knowledge of you—will ensure your success. This is how a meditation teacher should be.

2.     Your intent

While many people start to meditate because it is good for their health, this is a bit like learning to ride a bike to improve your balance—it is one outcome, but not the primary one.

The way you feel about your life, your relationships, and the way you handle the ups and downs will be determined by the state of your mind.

Meditation is a life-long tool to more fully understand your mind and build the capability to recognize when you are thinking without knowing it, when your buttons are being pushed, when you need to pay attention and listen, and when you need to stop and smell the roses.

3.     “Are we there yet?”

Meditating is hard. People expect that they will sit and be enraptured by something that was not there before. It doesn’t happen, they get distracted, bored, even fall asleep.

We have all been there.

You didn’t expect to ride a bike properly the first time, nor should you expect that calm, chatter-free, selflessness is available easily or readily—it takes time.

The practice is all about beginning again, there is no destination, only a journey of times where you are mindful and times which you are not. Waking up from mindlessness (or from the nap that crept up on you while meditating!) offers the opportunity to begin again.

4.     Ten minutes (and many moments) each day

Start with just ten minutes each day. Good habits take at least a month to form, so don’t feel upset or beat yourself up for missing.

As importantly, take time off the cushion to recognize your conscious awareness—the sights, smells, sounds, feelings, tastes, and thoughts that fill your first person world. It’s important that your mind is full of experience in as many moments as possible, not just during formal practice.

5.     A new friend that’s not your self

Make a friend of your mind by learning about it, listening to it, and on occasion offering some tough love. If you are too critical of yourself, notice that, notice what drives it, notice these thoughts melt under the heat lamp of awareness. If your mind is burdened (or boring you!) with thoughts, notice these thoughts melt under the heat lamp of awareness.

Try to find your self, your identity. Does your investigation turn up something, maybe located in your head? Is that self, that thought of your identity outside consciousness? Notice that consciousness appears more fundamental than the thought of self.

Give these handful of hints a try the next time you feel you can’t meditate and let me know if they work for you!

This has been a year where tremendous innovation has challenged our intuitions about knowledge. What is it to know something? We are so sure of our epistemological muscle, but when a system of universal processes encoded in integrated circuitry is capable of writing a research paper or creating novel digital art, it is using statistical inference on large datasets. As computer scientist Larry Tesler said, “AI is whatever hasn’t been done yet.”

Knowledge skepticism is an old philosophical tradition. We won’t replow that field. But what is interesting is what we learn as machines take a different journey to what might only end in domain specific and useful developments or what might lead to creative knowledge. It is also interesting in contrasting this latest bullish AI epoch to the learning styles of a two-year-old human child.

Deep learning can often be simplified to gamifying computation after reviewing large datasets. ChatGPT has reviewed English language essays, novels, lyrics, and poetry and utilizes this to guess the next word of its own compositions in a game of (very rapid) Madlibs. If it is corrected, it updates its neural networks to downgrade the mistake in subsequent iterations. Deep learning algorithms can often do this sort of conjecture and correction without human interaction, setting up what’s called an actor-critic model internally.

Our two-year-old has a shallower but much broader dataset. She is not trained on millions of texts, but understands “gorilla” as not only a word but as a stuffed animal toy, a moving animal on screens and at outings to the zoo, and the sound “oh-oh,” and the cutest chest pounding you have ever seen (the joy that act brings further reinforces the learning)! Creation of imagined worlds where lions, tigers, gorillas, and little girls play with balls or sit for tea parties are fluid, fun, and (exhaustingly) repetitious.

The contrast between these nascent learning mechanisms (if, for the sake of argument, we are allowed to call it that) show off the strengths and weaknesses of each. Pure information processing toyed with in deep learning’s gamification is creative only in the limited capabilities currently available to input the world into a computer... but the centrality of games puts it on the right path. The tact to create in deep learning, by making algorithms into a game of sorts, is an improvement on brute force attempts to “teach” computers.

The more improvements that are made in gamifying domain algorithms and then enhancing the computer’s ability to take a meta step to gamify its own algorithms to improve its creativity in new domains, the more likely that a computer will be invited to a two-year-old’s tea party.

I have a tendency to accentuate the positive. This is a good outlook, but not always helpful. There are many maladies and mental images that cause unease-to-full-on-anguish and must be addressed if mindfulness is to be a constant companion in the fast, slow, or breakdown lanes of life.

It’s important to say that all states of mind, sensations, and feelings are transitory—things change—but this realization of entropy can be restated as, things fall apart. While some conditions can be alleviated by a mindful curiosity into the depths of the condition, others, in my experience, have a much greater stranglehold over even my desire to be present with the suffering. A full-body anxiety for me is just such a thing and so I have great compassion for those with conditions like ALS where this is a constant source of physical sensory suffering.

Our aches and pains increase through the years, our regrets and strings of unwise words, deeds, and actions probabilistically increase, and we lose ourselves in anger, resentment, or just wrong-side-of-the-bed grumpiness. In these times, I’ve even caught myself petulantly not wanting to be mindful! I don’t want to investigate the experience, I’m just fine pouting, thank you very much!

The experiences and genetics that create your next negative thought or sense experience are different than mine, so the advice of not grasping for pleasant or being adverse to unpleasant must be balance with the advice of doctors. I take medication occasionally to sleep, but also realize that factors like dehydration or lack or even incorrectly timed physical exertion can play a role in my restlessness. Deepening your experience of a pain in your mouth might be advisable for all the time before and during your emergency root canal, but no longer!

If this newsletter seems to miss that the advance of entropy increases uneasy states through life for all and chance has brought great suffering on some, that has not been my intent. Mindfulness has given me a point of view of equanimity that believes ordinary experiences offer majesty, wonder, and illuminate something special within us all... AND the realization that mindfulness only works some of the time and not always when you need it.

The jujitsu of deepening your mind-full-ness on unsatisfactory experiences is hard and sometimes is less helpful than creating a narrative of a future self that is doing something about it. That is all fine, take care of yourself, and start again with curiosity on the present when you are up to it.