| --- |
| title: README |
| emoji: 馃摑 |
| colorFrom: indigo |
| colorTo: purple |
| sdk: static |
| pinned: false |
| --- |
| |
|  |
|
|
| # wordspace |
|
|
| **Markdown notes for Mac and iPhone, a personal wiki that grows on its own, |
| and all the intelligence on your device.** |
|
|
| On the iPhone you capture, on the Mac you think. What you catch on the fly |
| waits in the Inbox until you decide; then it becomes a note, and a personal |
| wiki grows from your notes by itself. No account, no servers of ours: the app |
| collects no data, and every model runs on your Mac, Apple Intelligence or a |
| small open model you download once. Six languages, free. |
|
|
| [Website](https://getwordspace.com/en/) 路 |
| [Mac App Store](https://apps.apple.com/app/wordspace-markdown-ai-wiki/id6794906796) 路 |
| [The idea and its sources](https://getwordspace.com/en/idea.html) 路 |
| [Privacy](https://getwordspace.com/en/privacy.html) |
|
|
| ## Our models |
|
|
| Small, specialised, open. Each one does one job of the app, and does it on |
| the Mac. |
|
|
| | model | what it does | on the Mac | licence | status | |
| |---|---|---|---|---| |
| | [**decider-1.7B-MLX-6bit**](https://huggingface.co/wordspace/decider-1.7B-MLX-6bit) | the closed decisions of the LLM wiki (contradiction, hypothesis, update, topic membership) in one forward pass, with a calibrated probability | 1.3 GB on disk, 1.5 GB in memory, 0.14 s per decision | Apache 2.0 | released | |
| | [**proofreader-0.6B-MLX-6bit**](https://huggingface.co/wordspace/proofreader-0.6B-MLX-6bit) | style suggestions while you write: the wordy phrase, copied verbatim, and a shorter one; silence when the sentence is fine | 0.5 GB on disk, 0.08 s per sentence | Apache 2.0 | released | |
|
|
| ## Built for the LLM wiki |
|
|
| wordspace follows the **LLM wiki** pattern proposed by Andrej Karpathy (2026): |
| your notes are compiled once into linked topic pages that a model keeps up to |
| date, instead of being searched again at every question. The notes stay the |
| source of truth, the pages stay readable Markdown, and every page cites the |
| notes it comes from. |
|
|
| Keeping such a wiki honest is a stream of small decisions on every new note. |
| We split the work so that each step is done by the cheapest thing that does |
| it well, a cascade (Viola and Jones 2001; FrugalGPT, Chen et al. 2023): |
|
|
| 1. **Code decides what is decidable.** Two different numbers or dates for the |
| same thing are a contradiction, and comparing them needs no neural network: |
| on 1,000 measured cases the deterministic check has precision 1.00. |
| 2. **The decider** answers the closed questions the code cannot: do these two |
| notes contradict each other, is this value decided or only proposed, does |
| a later note update an earlier one or do two sources disagree, does this |
| note belong on this page. One forward pass, about a tenth of a second. |
| 3. **A generative model** writes: the pages, the quotes and the reason behind |
| a contradiction, and judges only the few cases the decider leaves uncertain. |
|
|
| On the app's 154 hand-written gold cases, the contradiction check with our |
| decider raises 2 false alarms instead of 7 with LiquidAI's d1-3B, and calls |
| the generative model a third less often. On its own, the decider answers |
| 280 of 292 test questions, against 270 for d1-3B. Neither difference is |
| statistically significant yet, and we say so on every model card. |
|
|
| ## How we build them |
|
|
| - **Open bases only**: Apache 2.0 or MIT, with the licence re-read from the |
| downloaded files, and a `NOTICE` that lists every change we made. |
| - **No personal data, ever.** Training data is synthetic, generated from |
| sentences we write by hand in six languages: Italian, English, Spanish, |
| French, German and Portuguese. |
| - **Tests only measure.** The test sets are never used to write training |
| data, and any generated case that shares eight consecutive words with a |
| test is thrown away. |
| - **Against shortcuts**: every pattern comes with its minimal pair, the same |
| sentence that must get the other answer, so the model learns the decision |
| and not a surface cue (Gardner et al. 2020; McCoy et al. 2019). |
| - **Measured honestly**: always against the strongest model we know, on the |
| same cases, with Wilson intervals and exact McNemar tests, and the losses |
| reported next to the wins. |
| - **Small and quantized with care**: MLX, quantized only as far as accuracy |
| holds. The decider stays at 6 bits because at 4 bits it loses the cases |
| that matter. |
|
|
