13 posts tagged with "Notes"

The safest way to organize notes with AI is to let it change how a note is written and never what it says. MindMax quick notes work that way: every typo, misheard word and broken sentence is corrected, the thought is filed under the right heading, and nothing you did not say is added — no facts, no conclusions, no firmer wording than yours.

That sounds like a small distinction. It is the whole difference between a note you can trust next month and a note you have to re-check.

To ask AI a real question about a whole book — where the argument turns, what the author walks back, whether chapter nine contradicts chapter two — the AI has to read the book the way you would: look at the table of contents, decide which chapters the question needs, read those in full, and go back for another if the first did not settle it. Pasting the whole book in and searching chopped-up fragments both fail at exactly these questions.

Every AI reading tool has to decide what happens when the material is longer than the model can handle well. That decision is invisible in the answer, and it determines whether the answer can be trusted.

MindMax itself is free to use: reading, writing, searching and keeping your files in your own folder cost nothing, and the only thing you pay for is AI work, either through a subscription or with your own API key. Opening a PDF, highlighting, searching your folder, editing a note and exporting to Word never spend credits. Asking, explaining, annotating, translating, recognising a scan or transcribing your voice is AI work, and does.

That line is deliberate, and this post explains where it sits and why — because "free tier" in most software means "a demo that runs out on day two", and that is not what we mean.

Checking that an AI's quote really appears in a PDF sounds like pressing Ctrl+F. In practice the text inside a PDF is not the text you see: words are hyphenated across lines, paragraphs are split by page breaks and running headers, and letter pairs like "fi" are stored as single symbols. A quote check that ignores this either rejects real quotes or accepts paraphrases. Getting it right is most of the work.

We said every quote in MindMax is checked against the source. This post is about why that sentence hides more than it shows — and what you should expect from any tool that claims the same.

AI edits to your writing should arrive as tracked changes — deletions struck through, insertions marked, inside your own text — so anything without a mark is exactly what you wrote and you can accept or reject each change. The alternative, a rewritten copy, forces a choice between rereading everything and trusting an edit you never saw.

On a paragraph, a rewritten copy is a small annoyance. On a chapter, it is the reason people stop letting AI touch anything that matters.

A local model through Ollama or LM Studio handles short, contained document work well — explaining a passage, answering a question about an open paper, tidying a note — and that work never leaves your machine. It struggles with long jobs that need a large context and reliable tool use: reading a whole book chapter by chapter, translating hundreds of pages, drafting something book-length.

That split is worth knowing before you start, rather than four hours into a job that will not finish.

Yes — every AI feature in MindMax works with your own API key, with no account, no weekly allowance and nothing held back. The subscription exists to save you from managing keys and invoices, not to unlock the product. This post explains why, and what running on your own key costs you.

If you already pay for an API, being told to buy a second subscription before an app will talk to a model is a bad trade, and everybody involved knows it. You are being charged twice for the same tokens — once by the provider, once by the app for the privilege of sending them.

So MindMax does not do that. Add your own key and every AI feature works the same way it does for a subscriber: the same tiers, the same tools, no account, no weekly allowance. Not a reduced mode, not a beta path, not a setting that quietly disables the interesting half of the product.

This post is about why that is not generosity.

Asking AI about a screenshot of a chart works, but it throws away the text under the picture, the page it came from and the document around it. Boxing a region inside the document keeps all three, so numbers are read from the text rather than guessed from pixels, and the answer links back to the page.

Everybody has the same workaround. You hit a figure you cannot parse, you screenshot it, you paste it into a chat window, you type "what is this saying". It works often enough to become a habit.

It also fails in a specific, repeatable way, and the failure is not the model being bad at pictures. It is that by the time the picture arrives, three things that were sitting right next to it have been thrown away.

Every few days someone who has built their own retrieval setup asks the same question about MindMax, and it is a good question: if there is no embedding pass over my folder, how does it find anything?

The short answer is that it finds material the way you would — by structure, by the words on the page, and by trying other wordings — and that documents small enough to read are read rather than retrieved from. The longer answer is that this is a trade with a real cost, and pretending otherwise would be the kind of claim that falls apart the first time someone tests it.

MindMax's AI annotates a book sparsely on purpose: it marks only where a busy expert would actually stop, tells you up front how often it plans to stop, and two of its four lenses ask you questions instead of handing you conclusions. Fewer, better marks are the ones you reread.

The first reaction to an AI reading pass is often mild disappointment: it went through a whole chapter and left two notes. Surely it could find more than that?

It could. We decided it should not, and the reasoning is worth writing down, because "more annotations" is the kind of improvement that makes a product worse in a way users do not immediately attribute to the product.