Why AI Still Doesn't Know You, No Matter How Much Memory You Give It

Your AI knows a lot about you now. It knows you are a developer, that you prefer Postgres, that you like things explained without padding, that you have been chipping away at a side project you mentioned a few weeks back. Ask your AI about yourself and it can list these things back to you without missing a beat.

And it knows them because you taught it. Early on it was small stuff, a correction here, a preference there, the kind of thing memory quietly picks up. Then you went further. You wrote out proper custom instructions. You set up a system prompt you were actually happy with. Maybe you connected your own notes and files, or wired up retrieval so your AI could pull them from your own material. By any reasonable measure, you did the work.

So here is the honest question. When you ask AI to do something that matters, create in your voice, make the call you would make, draft the thing the way you would draft it, are you satisfied with what comes back?

And if you are being honest, the answer is NO.

If you have gone deep with your AI, maybe you only tweak a few parts and it lands close to what you wanted. But more often, the answer it gives you gets thrown out and redone, again and again. Sometimes it broke a rule you set. Sometimes it reads too generic. Sometimes it just is not what you meant. In the end, you keep a piece of it, maybe, and create the rest yourself.

So after all that material and all that back and forth, why can it still fall short of fitting you? That gap is what this article is about, and the answer is not the one most people reach for, which is usually to go feed it even more.

Why feeding your AI more doesn't make it know you

Feeding your AI more material makes sense. The stuff you give it is precise and it is yours. It is not something the model made up, and it is not the generic average sitting inside the LLM already. Your own profile, your past work, the way you described how you think, none of that is reliable in the pile of training data the model came with. You are handing it the specific you. And the more you hand over, the more dimensions, the finer the detail, the better it should know you.

But look at what all of that material actually is. Your custom instructions are you describing yourself. Your memory is things you told it, or things it picked up from what you told it. Your notes, your files, your retrieval setup, all of it reaches into material you wrote down and handed over. Every piece of it is the same kind of thing. It is the account you give of yourself.

And that account, however detailed, is partial. It is one side of you, the side you can put into words and chose to. And there is a reason that side does not add up to the whole. What people say about themselves and what they actually do are not the same thing, and the gap is not small. When researchers compare the two directly, asking people to state their preferences versus watching what they really choose, the behavior wins easily. In one study from a team at Warwick, models built on what people actually did predicted real-world outcomes about 1.5 times better than the best model built on what they said, explaining 49 percent of the variance in actual sales against 32 percent for the stated version.

You can feel why in something as ordinary as dating. At speed-dating events, people report caring most about personality, then turn around and choose based on looks. The stated answer and the revealed one come apart, in the same person, minutes apart. It is not that anyone is lying. People are often genuinely unsure what drives their own choices, their preferences shift with context, and most of us describe ourselves a little closer to who we would like to be. So the profile you give your AI, however honest you are, is the version of you that you can put into words and want to present. The fuller, less flattering truth lives in what you actually do.

That is the half your AI never sees. It is sitting in what you do all day and never think to write down. The things you reached for instead of the things you said you wanted. The books you actually finished. What you go back to, what you abandon, what you pay for, what you keep open at one in the morning when no one is watching. None of it makes it into a profile, and it is the most honest record of how you actually operate.

It has another advantage too. It keeps up with you. What you write down is fixed the moment you write it. You set up your profile once and it sits there, but you do not sit there. Your tastes move, your situation shifts, what you cared about three months ago is not quite what you care about now. A profile is a photo of who you were the day you wrote it, and you keep being asked to recognize yourself in a picture that stopped updating. Your behavior never freezes like that. It is produced fresh every day, on its own, whether or not you ever sit down to describe it.

None of this means what you say about yourself is worthless. For some things a direct answer really is the best source, and there are traits people report about themselves quite reliably. Stated information is not wrong. The trouble is that knowing someone takes both sides, and right now your AI runs on one of them. The whole apparatus of personalization, the memory, the instructions, the retrieval, sits on the side you can describe. The other side, the bigger and more honest one, is almost entirely absent.

And that is the real reason your AI still does not know you. It is not short on detail about the you that you write down. It barely has any of the you that you live out.

Which part of you would actually help your AI

It helps to get specific about what that half actually contains, because different things you ask of AI need different pieces of it.

Take creative work, where people complain the most about AI sounding generic. You tell it to write in your voice, and it has your instructions, maybe a few samples you pasted in. What it does not have is your taste, and your taste lives in your behavior. The articles you read to the end and the ones you closed after a paragraph. The sentences you highlighted. The drafts you wrote and deleted. The posts you saved and went back to. That record is what actually separates your voice from a competent average, and none of it is in the prompt. You described your style in a sentence. Your style is sitting in a thousand small choices you never articulated.

Now take decisions, like shopping or planning. You ask AI to recommend something and it leans on what you told it you want, which is exactly where stated and real come apart. What would actually help is the record of how you decide. What you compared before buying, what you almost bought and backed out of, what you keep repurchasing, what you returned. The price you talk about caring versus the price you actually pay. That pattern predicts your next choice far better than the preferences you would list if someone asked.

It runs through everything else too. How you really plan a week versus how you say you do. Which topics you return to on your own time. What you start and quit, what you finish. In every one of these, the useful signal is not the summary you can give of yourself. It is the behavior underneath it, and that is the exact part your AI is working without.

All of which would be a smaller problem if this information were hard to come by. It is not. You produce it constantly. It just does not end up anywhere your AI can use it.

The half you don't yet hold

The industry already senses this, which is why everyone is racing to connect AI to more of your life. ChatGPT can now plug into Google Drive, Gmail, Slack, and over a hundred other apps. Gemini's Personal Intelligence reaches into your Gmail, Photos, YouTube, and search history, and uses them to recommend a book or plan a trip around where you have actually been. The bet behind all of it is the one this article has been making. What you type is not enough, so go reach for what you actually do.

But look at how far it reaches, and where it stops. ChatGPT's connectors search one app at a time, and you have to know which app holds the answer before you ask. Gemini only sees the slice of your life that happens inside Google. The shopping you do elsewhere, the things you read in another app, the long trail you leave across the dozens of services that are not Google, none of it is in the picture. Each tool reaches into its own corner and calls it context.

And that is the real shape of the problem. The most honest record of how you operate is not missing because it is private or rare. It exists, in enormous detail, and it is being added to every day. It is just sitting in a hundred separate places, each one holding its own fragment, none of them yours, none of them talking to each other, none of them reaching the AI you actually work with.

So the next time your AI hands you something competent and faceless, be precise about what went wrong. You did not under-explain yourself. You explained the part of you that can be explained, and that part has a ceiling. The half that would have made the answer feel like yours was never on the table, because it has never been in your hands to give.

Until it is, more memory will only sharpen the picture of the person you can already describe. The one underneath, the one you actually are, stays a stranger.

Read more »

Your Second Brain Is One Piece of Jarvis. Here's the Rest.

When the first Iron Man hit theaters in 2008, nobody expected a voice to become a breakout thing. Jarvis, short for Just A Rather Very Intelligent System. It runs Tony Stark's house, manages his work, and knows all his needs.

And, it did not stay on screen. For over a decade, people have been trying to build their own Jarvis, with open-source projects named after it, weekend builds running on a Raspberry Pi, paid courses promising to make you Tony Stark. The dream kept pulling people in.

The most visible attempt came from Mark Zuckerberg. In 2016 he made building his own Jarvis his challenge for the year, with resources almost nobody else had, the full stack of Facebook's AI tools across language, speech, and face recognition. He even got Morgan Freeman to voice it.

After about a hundred hours, Zuckerberg's Jarvis could control the lights, the temperature, and the music, open the gate by recognizing faces, and wake his daughter with Mandarin lessons. The piece he was proudest of was small but telling. It learned his and Priscilla's taste in music, so when she asked for a song, it leaned toward her preferences over his.

Everyone else's attempts landed in roughly the same place. A lot of effort went into wiring devices together and getting the system to understand speech, and what came out could hear a command and carry it out. Turn on the lights. Play some music. Look something up.Which, if you think about it, is just the smart home you already have. Ask Alexa for the weather, tell Google to turn off the lights, have Siri set a timer. These do exactly what they are told, and nothing past that. They wait for a command, match it, and execute. While Jarvis never waited. It understood the situation and acted on its own, which is exactly what none of these can do.

Zuckerberg said it himself. Everything he built that year was a variant of the same basic pattern recognition, and even a thousand more hours would not have produced a system that could learn new things on its own. AI, in his words, was both closer and further away than people thought.

But that verdict came with an expiration date. The technology of 2016 and the technology of today are barely the same thing, especially with everything that has happened since in AI, and now AI agents. Looking back, each leap was quietly supplying Jarvis with another one of the core capabilities it would eventually need.

The brain: from following commands to thinking on its own

What made Jarvis special was that it had a personality and could think on its own. It did not wait to be told exactly what to do. In the harbor battle at the end of Iron Man 3, Tony gives one command, the House Party Protocol, and Jarvis does the rest, calling in dozens of suits and flying the whole Iron Legion into the fight on its own.

But almost every attempt before now worked the other way, matching an instruction or a keyword to a fixed response. So before anything else, building a Jarvis means building a brain.

Large language models gave Jarvis that. A model can read what you say in plain language, follow what you mean, reason through it, and answer in a way that holds together.

Understanding still waits for instructions, though. The next piece was getting AI to carry out a task without being walked through every step. Automated workflows did part of this, chaining actions so a single trigger could run a whole sequence on its own. But a fixed workflow only does what it was set up to do, and the moment something unexpected shows up, it stalls.

AI agents closed that gap. An agent takes a goal, breaks it into steps itself, picks the tools it needs, does the work, checks the result, and adjusts. You do not hand it a command and wait. You hand it an outcome and it works out how to reach it. A chatbot answers your question. An agent goes and does the thing.

There is also the matter of personality. Part of what made Jarvis feel like Jarvis was that it had a consistent character, a dry wit, a way of speaking that was unmistakably its own, rather than a blank voice reading answers. That used to sound like the soft, unbuildable part of the idea. It is now an actual field of research. Anthropic has worked on what it calls persona vectors, patterns inside a model that correspond to specific traits and can be monitored and steered. Other groups are using established personality frameworks like the Big Five to define and hold a stable character across long stretches of conversation, so a system can stay recognizably the same instead of resetting to a generic tone every session. The work is early, but the direction is clear. A consistent personality is no longer off the table.

Put those together and the inside of Jarvis starts to exist.

The record: when your life started leaving a trail

A brain is only useful if it has something to work with. Jarvis knew Tony because it could see everything Tony did, where he went, what he built, how he worked, who he let in. A mind with nothing to go on is just a clever stranger. So the second piece is the material, the record of a life for the brain to draw on.

For most of history that record did not exist. What you did simply happened and then was gone. You read a book and the reading left no trace. You walked into a shop, picked something up, changed your mind, walked out, and none of it was written down anywhere. Your days were full of choices that disappeared the moment you made them. There was nothing to look back on.

That is the part that quietly changed. Once your life moved onto screens and through the internet, your behavior stopped vanishing and started being recorded. Now the book you read is an ebook that knows which pages you lingered on. The shop is an app that logs what you viewed, what you added, what you dropped before checkout. What you watched, what you skipped, what you replayed, what you searched at two in the morning, all of it is captured somewhere. The same actions that used to evaporate now leave a trail of data behind them.

It is easy to miss how big a shift that is. For the first time, the raw record of how a person actually lives exists in a form a machine can read. Not a description of you, not what you said about yourself, but the actual log of what you did. That is exactly the kind of material a brain would need if it were ever going to know you the way Jarvis knew Tony.

The knowledge: when people started saving their own minds

A brain that knows you still needs something to know.

Jarvis was not just good at understanding Tony. It also held an enormous amount of knowledge and could pull up whatever Tony needed the moment he needed it. Ask it to analyze a material, dig up an old file, run the numbers on a design, and the answer comes back right away.

So the third piece is a body of knowledge for it to draw on, and ideally, your knowledge, the things you have gathered and want to keep.

This is where the second brain comes in. The instinct to keep your own knowledge somewhere outside your head is old. People kept commonplace books for centuries, copying down quotes and passages they did not want to lose. What changed is the form. The notebook in a drawer became a digital system, searchable, linked, built to be returned to instead of forgotten.

Over the past several years that habit turned into a movement. A huge number of people took it up under the same name, the second brain, and it spread far. Notion crossed a hundred million users. Obsidian grew to over a million people building their own linked webs of notes by hand. The book that popularized the term sold half a million copies in dozens of languages. A whole genre of videos and templates grew up around teaching people how to do it well.

What all these people are doing, without necessarily putting it this way, is moving a part of their own mind out into the open. The articles they thought were worth saving, the ideas they wrote down so they would not slip away, the connections they drew, the conclusions they reached. It is the thinking they cared about enough to set down and keep.

And that is exactly the kind of material that can work for Jarvis. It is the knowledge you have already judged to be worth having, gathered in one place. For the brain we have been describing, this is gold. It is not random information off the internet, it is your reference library, the things you have read, decided on, and chosen to hold onto.

The piece still missing

So the three pieces of Jarvis are finally real. A brain that can think and act. A record of how you actually live. A store of your own knowledge. Put them together and you have the thing people have been chasing since 2008.

The brain is arriving on its own, pushed by the whole AI industry. Your knowledge you already keep, in your second brain. The piece that is still stuck is your behavior. It gets recorded all day long, but it sits locked inside the apps that capture it, scattered across a hundred silos that have no reason to hand it back to you.

That is what is missing. Not a smarter model or a better notes app, but a way to get your own behavior out of those silos and join it to the rest.

Read more »

How to Make Your Second Brain Actually Work With AI

Do you think your second brain is actually working? Look at how you treat it.

Maybe you still tidy it up every day.

Maybe you kept it going for a while and then drifted off.

Or maybe you genuinely use it, pulling notes back out when work calls for them.

But either way, the real question is the same. Even with the whole system built, does it feel anything close to what you pictured when you started?

A second brain was always meant to be used, not just filled. People take notes so they can come back to them later instead of keeping it all in their head, which is the whole point of a second brain. The catch is that "later" rarely came.You captured far more than you ever pulled back out.

AI has started to fix the first half of that problem. It can dig through your library and pull up what you need without you combing the shelves by hand. But finding a note was never the whole point. Getting it to actually work for you is. So what does that next step look like, and how far can a second brain really go right now? A few approaches are already taking shape. That is what we are getting into here.

How most people still use their second brain today

Start with how this actually works day to day. You write things down, save them, and leave them alone until some project pulls you back. One day you are working on a topic and it hits you that you probably wrote something about this before. So you go looking for it.

That looking-for-it part used to be slow. Before tools like Obsidian and Notion, you went through your notes one by one, opening things, scanning, trying to remember where you put it. The newer tools fixed a lot of that. Obsidian builds a web of linked notes, so related ones surface on their own. Notion can search across your whole workspace and answer questions about what is in it. Some newer apps like Mem go further and use AI to resurface notes you forgot you had. Finding things is genuinely easier now.

But look closely at what actually improved. It is the finding. Every one of these makes it faster to locate a note, and then leaves you exactly where you were before, holding a note you still have to do something with. You read through what came up, pick the parts that matter, copy them, and paste them into Claude, ChatGPT, Gemini, wherever the real work happens.

So the tools made the search faster. They did not change what happened after the search. You are still the one who has to remember the note exists, judge what is worth keeping, and carry it into the AI by hand.

Your second brain is not doing the work here. You are. You are the one carrying notes into the AI by hand.

How some people are starting to make second brains work with AI

But, used the old way, these tools never come close to their potential. The note apps we call our second brain can do a lot more now that AI is in the mix.

And a small group of users has already started digging into what that potential actually looks like. Here are the three main ways they are doing it.

Path 1: AI built into the note tool itself

The most direct approach is to use a tool that ships with AI inside it.

Notion is the most familiar example. You write and store everything in the same place, and the AI lives right there with it. Ask what you concluded about a client last quarter and it reads across your pages to answer. Tell it to turn three weeks of meeting notes into a project brief and it pulls from what is already in your workspace.

Tana works the same way, except it gets you to label things as you write so the AI has cleaner material to work with. Every meeting note gets tagged as a meeting, every client note as a client. You are quietly building a structured library while you take notes. So later you can ask Tana to pull every action item still open across all those meetings, and it answers from the structure you have been building, instead of making you dig through the notes one by one.

What this really removes is the trip. In the old way, your notes sat in one place and the AI lived in another, and you were the courier between them. Here there is no courier. The material and the intelligence share an address. For a lot of everyday work, summarizing, drafting, pulling threads together, that alone is a real jump. The second brain stops being a drawer you open and starts being a desk you work at.

But this path has a wall around it, and the wall is the tool itself. Everything works beautifully as long as you stay inside Notion, or inside Tana. The moment you want to take that thinking somewhere else, into Claude, into a different agent, into whatever tool fits the job better tomorrow, you are back to being the courier. You copy things out, you paste them in, you re-explain the context the new tool has never seen. The second brain works, but only at one address. Step outside and you are carrying notes by hand again.

Path 2: Installing AI into your notes

The second route is the open-notes approach, and it is the one getting the most attention in the AI crowd right now. Obsidian is the main example. It works as a local markdown editor, so everything you write gets saved as plain .md files on your own machine. That format matters, because markdown happens to be the format AI tools read most easily, with no conversion needed.

On its own, Obsidian has no AI in it. The AI comes from plugins, and now the community has built a lot of them. They sit at different levels.

The simplest plugins are about retrieval. Smart Connections is the common starting point. It builds a local index of your vault and, as you write, surfaces older notes related to what you are working on, even ones that share no keywords with it. Write about remote team communication and it can pull up a forgotten note on async video updates. It runs locally, so nothing leaves your machine. This is genuinely useful, but it is still helping you find things rather than do anything with them.

The next level of plugin starts writing with your notes, not just locating them. Text Generator drafts, rewrites, and expands text inside the editor, turning your bullet points into prose without leaving Obsidian. Copilot for Obsidian goes further, adding a chat panel that answers from your actual vault. Ask what you concluded about pricing last quarter and it replies from your own notes instead of making you dig them up and paste them into a separate chatbot. With its agent mode, you can hand it a larger task and let it work across many notes at once. At this point, you have stopped searching and copying. The AI is producing things directly from what you already wrote.

The furthest level hands your whole vault to a full agent. Khoj can run as your own self-hosted assistant across your notes and even build custom agents over them. And there is a community plugin that connects Obsidian to Claude through MCP, which lets Claude Code or Claude Desktop read and write your notes directly and treat your vault as the folder it works inside. You can ask Claude to go through your notes, connect ideas across them, and write something back into the vault, and it works against your real files rather than a copy you pasted somewhere. The notes finally get used without you doing the carrying.

The catch with this whole route is that you have to build it yourself. You pick the plugins, connect the model or the agent, handle the setup, and fix it when an update breaks something. How capable your second brain gets depends on how well you put it together. For people who like building their own tools, that is part of the appeal. For everyone else, the setup and upkeep never really stop.

Path 3: Pulling your notes into AI

The first two paths both keep the work inside the notes. You are still in Obsidian or Notion, and the AI comes to you there. But a lot of people now want another thing. Some of them already live in one AI, Claude or ChatGPT, and just want their second brain available inside it. So the third path is about bringing your notes into the AI side.

Besides uploading your notes manually, a more lasting setup connects the AI to where your notes actually live, so you stop re-uploading. With MCP, you can give Claude a standing line into Notion, and after that you can ask it about something from the last quarter and it goes and reads the relevant pages itself. Some people connect a tool like NotebookLM to Claude, so one side holds all the documents and the other does the thinking, and you just talk to it. The notes stay in their home, and the AI goes and gets what it needs when you ask.

A few people take it one step further and leave the AI a kind of map. When they have Claude working over a folder of notes, they drop in a short file that explains how everything is laid out, what goes where, what the tags mean. Now every time they come back, Claude already knows its way around and they never have to re-explain the setup. It is a small thing, but it hints at where this is all heading, an AI that holds a standing sense of your notes instead of meeting them cold every time.

What you get out of all this is freedom of movement. Your notes are not locked inside one app's AI. You can take them to whichever model is best for the job, and hook the same notes up to more than one.

Why a working second brain still needs more than your notes

So all three paths get your second brain finally callable. The AI can reach into it, read it, build on it. But sit with what comes back for a minute and something feels off. It is competent enough. You asked it to write the way you would, and it tried. It picked up a bit of your phrasing, leaned on the notes you pointed it at. But what you get reads like an AI doing an impression of you, close in places and hollow in others. Half the time it does not even hold the specific things you asked for at the start.

Here is why. Your second brain handed the AI everything it had, and everything it had was notes. A second brain, as most people have built it, is a pile of things you decided were worth writing down. That pile does not carry how you actually think, the phrasing you reach for, the images you pick, the way your mind moves from one idea to the next. Give a model only that and it fills the gaps with what a generic competent person would do. The result is part you and part the average of everyone.

You might say the AI tools already handle this, and it is true that they have started to. Each of the big ones builds a picture of you, just in a different way, and the differences say a lot about how far this idea has come. ChatGPT leans on what you type in yourself, a profile and a set of instructions you write by hand, plus a memory that saves facts as they come up. Claude leans the other way and does it on its own, quietly distilling your conversations every day into a running sense of your work, your tone, the tools you keep using. Gemini goes further, reaching past the chat window into your Google world, your searches, your YouTube, the things you actually did rather than the things you told it.

And it works, up to a point. Each step makes the AI feel a little more like it knows you, and the replies come back fitting a little better than they used to. But the picture each one builds is only as wide as what it can see. ChatGPT knows the you that fills out forms. Claude knows you who talks to Claude. Even Gemini, reaching the furthest, only knows the you that lives inside Google. Personalization is real, and it is also partial, drawn from one corner of your life and treated as the whole of you.

Still, look at the direction all of this is moving. The trend line is hard to miss. The closer anyone tries to get to a second brain that truly knows you, the more they lean on behavior instead of notes.

That is the tell. The missing piece in a second brain was never more notes or better notes. It was the part of you that notes were never going to capture, the real record of how you choose, sitting in what you do rather than what you write down. The whole industry is inching toward it from different sides. None of them has the whole of it yet, because the whole of it does not live inside any single app. It is spread across everything you use.

What it actually takes for a second brain to work

So it is worth saying plainly what working really means here again, after everything above.

In the last article, we came back to what a second brain was always supposed to be. Not a filing cabinet, but something closer to a partner that thinks with you, the kind of thing Tiago Forte described long before the tools could deliver it.

FYI: https://datadancewallet.blogspot.com/2026/06/is-your-second-brain-just-knowledge.html

Hold a second brain to that definition and the test gets simple. It is not the one with the most notes or the fastest search. Those make what you wrote easier to reach, and reaching what you wrote was never the point. A second brain works when it can act on who you actually are, and that takes more than half of yourself when you sat down and record. How you really operate, what you choose, what you return to, what you do when no one is watching, lives in your behavior, the more honest half that notes never catch.

The move still ahead is from connected notes to connected context. From a second brain that remembers what you wrote, to one that knows how you actually think, choose, and work.

Read more »