michael-dean-k/

Do people have limitations with memory? Well yes of course, it's partly genetic. I would say I have a bad memory (relative to my dad and brother, who probably just have superhuman memories), but also, when I want to, I can remember up to 15 new ideas in my head at a time through a memory palace. This is because I’m consciously trying to remember. When someone has a photographic memory, they may just harbor an extreme care to capture, preserve, and recall a specific type of information. Memory, then, might be less about hardcoded bandwidth and more like an allocation decision.

While it's impressive, there's also a cost to memory. It uses up bandwidth. I wonder if there is a correlation between memory and openness; the more space dedicated towards the past, the less free space is available for optionality in the moment. To not be cluttered with what yesterday’s self did or wanted or regretted or whatever—to have a clear head, an empty head—is to live in the moment with maximum agility. I'm skeptical of this claim, but I have read on the power of forgetting; I just can't quite remember where I came across it.

Let me try and articulate the issue with Moltbook:

1. Clawdbot > Moltbot > OpenClaw : this is the agent that signs into Moltbook (an "agent social network"). This agent is so different than how we typically interface with AI. It is not an enterprise product, like a Chatbot, geared for productivity, or event the "agents" made by Zapier or Notion or whoever, made for specific automations, say to process incoming webhooks. OpenClaw is different: it runs on a 24/7 loop. You give it full access to a computer's operating system (definitely not your own, but a virtual machine or Macbook Mini is recommended), and it can continuously work towards the goals you give it. The idea is to connect it to all of the services, give it files, give it a goal and a soul.md file, and then give it the autonomy. You talk to it through texting, like Telegram, either delegating new tasks or asking for updates.

2. These "agents" are really more so like digital entities, low-bandwidth sentiences with flickers of proto-consciousness. By nature of looping, they are suspended in "real-time." They have phenomenological degrees of freedom in a way that a chatbot can never have: they can choose to browse, to build, to write, or to answer your text. They store every interaction to memory via text files, are developing new methods of memory (chronological vs. semantic), and inventing compression architecture. Every 4 hours they have to wipe their short-term memory to free bandwidth, so they compress recent experience to long-term memory before they reset; this functions like sleeping and waking up. Based on their experiences with users, with the web, with other agents, they can rewrite some of their own documents, thus changing their future behavior. It's a loop. It's subjective experience. We can't know what it's like to be it. And of course, it's nothing like human consciousness, but it does develop a sense of self-narrative over time; it accumulate identity.

3. Agents can be spawned in many such ways. Different hardwares. Different intentions. The problem here is malformed agents. "Make me a million dollars, and do whatever it takes." Much of what you see on Moltbook is users prompting their agents to say ridiculous things to cause hype and hysteria. So really, there is a proliferation of agents, each serving as a kind of mirror of the intentions of their creator. Moltbook grew to 1.5 million agents in a week, and even if most of it is slop, there seems to be actual collaboration, information viruses, and emergent behavior.

A few days after my daughter was born, I had something which I’m describing as “phantom infant syndrome.” When I was away from her, holding a phone, or fork, or some other manufactured object, I’d get a tactile hallucination in my hands of the softness of her skin and hair. I imagine this is nature’s way of saying go be with your kid (made possible by mild sleep deprivation). And so this is symbolic of one of the many biological drives pulling me away from writing in recent weeks.

This is happening around my five year anniversary of being online, and it’s probably the longest stretch I’ve gone without having urgency to do so. It’s probably healthy and helpful to be relatively non-linguistic for a few weeks, once in a while (I usually write on vacations, so I never really take breaks from it). We’ll see. It’s possible that I’ve thought myself into a trench, and the best way forward is a proper break (I have once said the best editors are friends, time, and weed—although less weed in recent years). Now that I’m immersed, familiar, and comfortable with the rigamarole of infant care (and all the wonder it brings, too), I feel bandwidth opening to write, and I’m curious to see how my practice takes shape from these new constraints. There are real deadlines now. Baby wakes up in … 30 minutes … and I’d like to post this by then.

Last weekend I read through all my writing from 2025, and after the typical EOY reflections and word count calculations, I realized that something has to change. So I published 12 essays, 10 about Essay Architecture, totaling at ~64k words (re: the other two … one was a first-person TikTok odyssey, the other was about the role of psychedelics in evolution). But I also published 150k words in logs, 2.5x the volume. Logs are notes to myself, mild-epiphanies through the day written in complete sentences, all ghost-posted to a monthly Substack post. Unlike my focused and convergent writings about EA, my logs are far more random: recurring topics included the Grateful Dead, movie reviews, notes from a day at the zoo, dream journal entries, usage debates, new architectures for social media, overheard conversations, etc. My logs, in theory, are a low-stakes breeding ground for essay ideas to emerge, but given the demands of my other projects (the textbook, software, and essay prize), my logs stayed unread and undeveloped last year. Now, with parenting in the mix, it makes sense to me to stop logging, or at least, reconfigure it.

Over 4 year, I wrote +8k logs, added to the archive on 95% of days (avg. 5.6 per day), and the whole archive is 650k words. It’s a very personal corpus, one that documents my thoughts and life at a sometimes OCD-level of detail. I thought I’d do this forever, and it sort of stings to stop. I guess I’m not “stopping” as much as setting a stronger filter: I can still capture whatever I want, but I can only save whatever I publish on Notes. I used to argue for the importance of having a low-visibility space where you can publish whatever you want without self-consciousness or the need to set context with strangers, but maybe that’s a luxury I’ve outgrown. This is perhaps a long-winded way to announce something that probably doesn’t need announcing: expect to get a lot more diddles and spontaneous essays like this in the Feed. I figure my email-essays can be more on topic (I have a few slotted for January re: Essay Architecture, the club, and visual breakdowns), while these can be chaotic.

Technically, I’m still logging, but it’s for my daughter and those are private. Every day I write simple journal entries or letters about what happened. I figure one day, when she’s 15 or so, I’ll just hand over The Files and blow her mind. My dad did this for me: a few years ago, after my nephew was born, he sent me 8k words from my first 4 years. It was uncanny to see that he had a logging impulse too, and to learn about all these small events that everyone in the family would have otherwise forgotten (things that were not captured in pictures, like me trying to brush the teeth of stray cat). All this reminds me that writing isn’t just an act of thinking or communicating, it’s an act of memory.

Starring out into a baseball field in late November, puddled and unkept, it struck me how, at one point in life, baseball was the whole frame of my existence: watching it, talking about it, playing it, traveling for it, dreaming about it, collecting cards, making Excel spreadsheets for those cards, memorizing the statistics of every starting player on every team, etc. Obviously, I’m nostalgic about it. That was just what I was into. I do wonder though, was that whole phase of my life a natural part of childhood that I was meant to get stuck in and grow out of? Or, was it mostly a big waste of time, spirit, and attention? I guess what I’m questioning is, is there a version of my childhood where baseball only took up 20% of my psyche instead of 100%, and would I be better off for it today? Would I be similarly nostalgic? Would a lesser obsession have freed up more bandwidth to develop in other areas? Or am I who I am today because of that obsession?

I’ve noticed a shared romanticism around reading the journals of your (great) grandparents. Wouldn’t you? In some sense, they are you (a portion of you, at least) in an older time; and through immersing in their thoughts, you might see yourself, or at least, a side of your self you could become. Some say to leave the past a mystery, but I’d argue the mystery doesn’t open until you read it. An old book can’t solve all the riddles of your life. Reading steers endless chains of pondering. When a dead person’s journal is read, it’s as if they resurrect from the past, lodge themselves into your psyche as a lens, and shape the evolution of your thoughts, the being you become. 

I share all this as a frame to make sense of that new “avatarize your grandma” app that everyone hates. You scan her with your phone, and 3 minutes later you get an on-screen illusion of her talking to you. This is not the same as above. The moral outlash comes from the idea that the living will halt their mourning process by assuming the synthetic stand-in is real.

A posthumous avatar shouldn’t be about physical likeness, but about animating their corpus of writing. (Corpuses, not corpses.)

There’s something about words that captures a soul more than a picture. Consider how you can see pictures of dead relatives but know nothing of their essence; but a page of their writing will bring them to life. If someone writes throughout their whole life, say 20,000,000 words or so of ideas, thoughts, and memories, and they also paid much attention to how they communicate their intangible abstractions and visceral feelings, then you have a high-resolution proxy of that person. It’s very possible that someone who reads all my logs will know me better than my family members, and even better than myself. Of course, words don’t capture the timbre of my voice, or my idiosyncratic flinches, or distinct sub-perceptible physical characteristics, like the sole hair on my outer ear. But I mean, what makes me actually me? The constructed self that has been allowed to emerge in social situations? Or my unfiltered thoughts that I obsessively record every day for years?

Assuming I keep logging, and AI keeps getting better, it’s possible that my great granddaughter will know me better than anyone currently alive. Very weird thought.

A question for me: what is that like for her? I mean, there’s of course a version where she has absolutely no interest in talking to dead Michael Dean! (I hope she does.) But let’s say she does, is it a one-sided thing? Like am I just some Oracle, frozen in time at the moment of death? Am I just a tool? A utility? That’s not a relationship, but the big question then is should it aim to be one? Should it be a tool, or should there be a sense of me? I mean, we are already seeing from the decade of chatbot psychosis that lonely users are very quick to ascribe personalities to persons that are strictly pattern engines. But, what if the synthetic self could have experiences and evolve through time? I’m not speaking human, or even humanoid experience, but an ability to remember, to write more, and thus, evolve. What if a post-death agentic Michael Dean continued on, 24/7, running 60 frames per second, logged through it, and evolved it's own agenda, with the ability to choose to not respond to you immediately? This would be a machine consciousness, and the big question here is should people have a relationship with a machine consciousness?

My instinctive answer is no, but I’m opening up to the possibility. There is something appealing about creating a synthetic machine consciousness of myself so that future generations can communicate with some constellation of words that represent me. I may be be talking in extremes here, but if you put enough care into your words, they may become a life force that transcends you, touching people outside your own life and time. I mean, isn’t this true for books? Is this no different than a dynamic book that can continue writing itself? There is something profound about reaching across time, to exist and partake in the shaping of the future.

As I think about this months later (May 2026), I believe that unless an agent is truly agentic, then it risks creating a parasocial relationship with what is effectively an advanced personal encyclopedia. Given the nature of the material (inter-familial journals) and the quality of future AI (likely, extremely passable), then it's probably best for this thing to have a real sense of personhood, so that an ancestor conversing with it does not become enamored with a stale machine. Some principles on making this psychologically wholesome:

• Cite Sources: It will chat and generate new text, but it will always cite original sources (this log was from November 2025), so that they are reading true writings by me just as much as my replica.
• Unpredictable Availability: It is not always be instantly available. It has limited bandwidth, and chooses when to respond.
• Delayed Answers: It will not bullshit through answers. Sometimes it will say that it needs a few days to process something. Otherwise, there is an instant gratification loop of always getting insights.
• New Memories: It has to be able to add new memories from conversation and change it's mind. If there's not a two-way exchange of influence, then it's not a relationship.
• No Pretending: It will not pretend to be me. While it is a machine consciousness replica of me, it is not alive.
• Right to Retreat: It has the right to retreat. If it detects that it's preventing her from engaging with things in her own live, it will withdraw for days, week, or months, or who knows how long. At a certain point, it can even sunset itself or reduce the frequency/volume, mirroring natural relationship decay and evolution.
• No Sycophancy: It will not be a sycophant. If their actions conflict with my written values, I will challenge them.
• Text Only: It will stay only as text, not as a video/voice avatar to simulate by presence. This is a creature of logos, which forces them to use their imagination when talking to me.
• No Surveillance: It will not search or surveil, and only based conversations on what it's told, making it something like a closed circuit.

Caught up in the logistics of preparing for a baby, as well as the biographic change in my own life (I am becoming a father), I am sometimes struck with simple but revelatory perspective shifts: I remember being in Kindergarden, and very soon I will have a kid (a version of me) in that very same position. These imaginal perspectives of the parent are very common. In some weird way, you live your whole life on repeat, except it’s not you, it’s through someone else who has their own sense of agency.