A Second Brain Needs a Working Memory

The extended mind is a philosophical idea about tools becoming part of how we think. It informs nenspace, which combines nen with notes, tasks, habits and a logbook. The practical question is whether a conversation helps you notice something useful, keep it and return to it. This is a design ambition, not a demonstrated cognitive benefit.

The Notebook

In 1998, the philosophers Andy Clark and David Chalmers published a short paper called “The Extended Mind.” Its central character is Otto, a man with a failing memory and a notebook he always carries. Otto consults the notebook the way anyone else consults their memory: reliably and without deliberation, trusting what he finds. The paper's claim is that the notebook is not an aid to Otto's mind. It is part of it. That is a philosophical thesis and it is the one nenspace is built on. Cognition doesn't stop at the skull, and a tool used that way becomes part of the thinking. Clark himself was still extending the argument to AI in 2025.

The popular idea of a “second brain” addresses related territory: keeping useful material outside our heads. It can be an active practice, or a collection we rarely reopen. The name alone does not decide which. What interests us about Otto is the dependable act of returning to his notebook. The design question for nenspace is how to make returning to a useful thought feel natural.

Half a Mind, Twice

Remembering and thinking are closely connected. Software can help with both, but keeping information does not ensure that we return to it.

Tools such as Obsidian and Notion make personal knowledge easier to keep and organise. Notion also offers built-in AI, and Obsidian can be extended with AI plugins. These are substantial capabilities. The difficulty for some people is maintaining a system and deciding what deserves attention. That is a workflow problem, rather than proof that an entire category is incapable of helping us think.

Conversational AI can help develop an idea, and products such as ChatGPT have saved chats, projects and memory. A useful observation can still be hard to find again in a long conversation. nenspace offers a particular workflow for this problem, with dialogue alongside an editable personal space. The value depends on what you actually keep and use.

Two Kinds of Offloading

The research offers useful questions for design. It does not establish that using one app makes a person more capable than using another.

Working-memory capacity is limited, with estimates of around four chunks under particular experimental conditions. Research on unfinished goals suggests that making a specific plan can reduce their intrusion. These findings support taking external records seriously; they do not mean that writing any thought down guarantees relief.

Offloading thinking is different. When we expect a machine to hold something, we remember where it is rather than what it is. Habitual GPS use tracks with declining spatial memory. The effects depend on the task and how the tool is used. An association with habitual GPS use is not proof that every form of AI assistance weakens thinking. Early work on LLM-assisted essay writing raises questions about recall and engagement in that setting. It does not establish the effect of every kind of AI assistance.

For this product, the useful distinction is between keeping a record and outsourcing a judgement. A person can do either with many kinds of software. The design should make it easy to examine an answer and decide what to keep.

The Fusion

So the shape of the product is dictated by the argument, not the other way around.

/space keeps the record. Capture a thought in working memory, then review the sift proposals when you want to organise it. The brain dump guide covers the method. Notes, tasks, habits, a logbook and pinned dialogues provide places to return to. These are software features inspired by a view of memory, not a reproduction of the brain or a promise of automatic pattern recognition.

/nen thinks. This is the half that can't be assembled from parts off the shelf. nen is the default chat, trained and designed for humans; nen-1 remains a separate dialogue option, and nenspace has trained that lane. The register avoids the habits that make language models feel like language models: flattery, padding and the eagerness to finish thoughts you hadn't finished. It keeps your situation in the subject position.

A mind remembers and thinks. It isn't extended by only one of them. That is why nenspace is one thing, not two features.

The Limits of the Claim

Plenty of products combine AI with notes, memory or personal knowledge. Other model developers also work to reduce sycophancy. A distinctive register is something to try, not evidence of overall superiority.

Our claim is narrower. nenspace offers nen, trained and designed to answer rather than agree, alongside a personal workspace. It can be useful for a person who likes that experience. It can also give a poor answer, and it requires the person to judge and organise what matters. The model record describes measured limitations.

Start with one situation, ask what is missing from your interpretation, and record a next step. Return after you act. The reflection guide walks through this practice, and the comparison pages explain where other tools may suit you better.

The Flag

An idea, once said, can be repeated by anyone. That is what ideas are for. This plants the flag, check out nenspace to test the ground if it's of interest.

your own mind, made larger.