Registration is by invitation only.
Thoughts arrive as discrete units, complete in themselves - not as paragraphs waiting to be written. We don't think in essays. We think in steps, in fragments, in moments of clarity that build on each other.
We translate our thinking into prose. To wrap every idea in sentences, every decision in context, every observation in narrative. The atomic thought - the thing we actually knew - became a paragraph, then a page, then a file in a folder.
Cognitive science has known this for decades. Our working memory handles discrete chunks - small units of meaning that combine into larger understanding. We don't process walls of text; we extract the atoms within them.
AI processes information the way we do - in chunks, looking for structure, relationships, meaning.
When it reads a document, it has to find the logic buried inside the prose. The understanding is in there. It just has to be excavated. Sentences have to be parsed. Context has to be inferred. The original thought has to be reconstructed from its wrapping.
This is work. For AI, and for us.
Documents make both humans and machines work harder. Every time we return to a report or reread an email thread, we're doing the same excavation - finding the thoughts inside the text. Separating what matters from how it was packaged.
The cost isn't dramatic. It's cumulative. Small frictions, repeated endlessly.
Learning to prompt is teaching us something unexpected.
A good prompt is a clear thought - structured, specific, contextual. In learning to communicate with AI, we're relearning how to think out loud. To say what we mean without dressing it up. To be precise because precision works.
This skill transfers. It isn't just about talking to machines.
When we work in thoughts rather than documents, information starts to behave differently.
It connects - because the relationships are explicit, not buried. It resurfaces when relevant, rather than sitting forgotten in a file. It doesn't duplicate, because duplication becomes visible. It's ready - for us, for our colleagues, and for the tools we're increasingly building alongside.
The benefits aren't abstract. They're practical, daily, compounding.
This app is an exploration of that shift. An experiment in how we input, interact with, maintain and distribute information.
The idea is to work closer to the way we actually think - and seeing what becomes possible when we do. It's not a finished product, but a genuine inquiry. A test of whether the way we've always worked is the way we have to work.
Perhaps it isn't.
In Miller's paper "The Magical Number Seven, Plus or Minus Two", he demonstrated that working memory has a limited capacity of about "seven plus-or-minus two" chunks.
He proposed that the process of chunking organises sequences of inputs, recoding with a concise name, and remembering just the name essentially reduces the storage load on working memory, arguably freeing capacity for storage of additional information. [Thalmann, Mirko; Souza, Alessandra S; Oberauer, Klaus]
He suggested that chunking is the lifeblood of the thought processes.
This isn't a peripheral observation - it's been central to cognitive science for decades.
Research defines a chunk as a collection of basic units that are strongly associated with one another, and have been grouped together and stored in a person's memory. The key insight is that individuals create higher-order cognitive representations of the items within the chunk - the items are more easily remembered as a group than as the individual items themselves. [APA Dictionary of Psychology]
More recent research confirms that sequence learning and production is a hierarchical process, such as in speech organization, behavioral sequences, and thought processes. By segmenting a sequence of elements into blocks, or chunks, information becomes easier to retain and recall in the correct order. [Pubmed Central]
In Miller's paper "The Magical Number Seven, Plus or Minus Two", he demonstrated that working memory has a limited capacity of about "seven plus-or-minus two" chunks, then suggesting that chunking is "the very lifeblood of the thought processes."
This isn't a peripheral observation - it's been central to cognitive science for nearly 70 years.
Last updated: [DATE]
Cookies are small text files stored on your device when you visit a website. They serve various purposes including remembering your preferences, understanding how you use our services, and providing relevant content.
These cookies are necessary for the website to function and cannot be disabled. They include cookies for:
With your consent, we use analytics cookies to understand how visitors interact with our website. This helps us improve our services. These cookies collect information such as:
These cookies enable enhanced functionality and personalisation, such as:
With your consent, these cookies may be set by our advertising partners to:
You can change your cookie preferences at any time by clicking the 'Cookie Settings' link in our website footer. You can also manage cookies through your browser settings. Note that disabling certain cookies may affect site functionality.
Some cookies are placed by third-party services that appear on our pages. We do not control these cookies. Please refer to the relevant third party's website for more information about their cookies and privacy practices.
If you have questions about our use of cookies, please contact us at [EMAIL ADDRESS].