Swiss AI · Zürich

Models that say
when they don't know.

A language model that always answers confidently is more dangerous in production than one that stays quiet. Neurolism builds the layer that knows the difference, and measures whether it is right.

Free plan, no card · Windows and macOS · Nothing used for training
LANGUAGEEVIDENCECONSISTENCYdo they match?answercitesay so
The product

What you get on the first day.

Before any of the architecture below: the things you can use straight away, on every plan including the free one.

In the browser and as an app

The browser needs nothing installed. The desktop app opens the folder the work is already in - a repository, a directory of contracts.

What that changes. For you, the same history on every device. For a company, the code and the documents never get copied somewhere else to be read.

Reads what you attach

PDF, Excel, Word, images. A spreadsheet is read as cells rather than as flattened text.

What that changes. Where the file does not cover the question it says so. That is the difference between someone checking one answer and someone checking every answer.

Searches and names the source

The passage it used arrives with the answer. Where the search turned up nothing, that is the answer.

What that changes. You check it in seconds instead of doing the search again - and in regulated work, an answer that names its source is one somebody can sign.

None of it trains anything

Nothing you send is used for training, ours or anybody else’s. Not a setting you have to find and switch off.

What that changes. For you, nothing private ends up in a future model. For a company, it is the first question a data protection officer asks, answered before it is asked.

In practice

Three kinds of week.

The same model, three completely different days. What follows is what it actually does in each - not a list of adjectives.

For code

Building software.

Open a repository in the desktop app and it works where your code actually is - not on a copy you pasted into a chat window.

  • Reads the files, not just the file names
  • Runs dotnet build and dotnet test, then reads the errors
  • git status, diff, log, blame without asking; commit and push only with your say-so
  • Writes files into your folders, one confirmation each
  • Force pushes and hard resets are not available at all
More on code
build.log
$ dotnet build && dotnet testrestorebuildtest3 passed in 2.4s
For studying

Learning something.

Explanations that stop where the knowledge stops, instead of filling the gap with something that reads well.

  • Walks through a problem step by step, not just the answer
  • Turns a script or a chapter into flashcards and questions
  • Asks back when the question is ambiguous
  • Says plainly when it is unsure - the whole point of the design
  • Reads photographed notes and slides
More on studying
card 4 of 18
What is a mole?QUESTION6.022 × 10²³ particlesANSWERflashcards from your own scriptHow many particles in one mole?6.022 × 10²³3.011 × 10²³it asks back, and marks what holdsn = m / Mn = 18 g / 18 g·mol⁻¹ = 1 molN = n · Nᴀ = 6.022 × 10²³step by step, not just the answer
For the office

The dull half of the week.

Reading what piled up and writing what has to be written - with the files you already have, in the formats you already use.

  • Reads contracts, spreadsheets and PDFs you attach
  • Hands back an .xlsx or .docx you can open, not a pasted table
  • Turns numbers into a chart inside the conversation
  • Drafts offers and replies in a second language
  • Looks up what changed and names the source
  • Nothing you write is used for training
More on office work
quarter.xlsx
ITEMQTYPRICE
10 more: reasoning, finance, companies, public sector, sensitive data, research and sources, data and spreadsheets, writing and editing, contracts and documents, developer plumbing.See all 13
What is broken

Four problems, and what we do about each.

These are not marketing complaints about the field. They are the four constraints that decided how this system is built.

  1. The problem

    A wrong answer sounds exactly like a right one

    Fluency and correctness are separate abilities, and models got good at the first one much faster than at the second. Nothing in a confident paragraph tells you which parts were retrieved and which were invented.

    Our answer

    A layer whose only job is to disagree

    Language and evidence live in separate representation spaces. A third space scores whether they actually match, and has a dedicated channel for saying that they do not. That channel is why a smaller model stays usable.

  2. The problem

    Confidence scores that are confidently wrong

    Most systems report a number between zero and one and never check whether it means anything. On a set where most pairs agree, a model that always says yes scores well and has learned nothing.

    Our answer

    Calibration measured, not assumed

    We measure expected calibration error and AUC on a balanced set, never accuracy. Of the times the system says seventy percent, roughly seventy percent have to be right, or the number does not ship.

  3. The problem

    Inference cost grows with every user

    Training is paid once. Inference is paid every day, forever, and a system designed without that in mind gets more expensive exactly as it gets more successful.

    Our answer

    Escalate only when it is needed

    A small model answers, a router decides whether that was enough, and only the remainder reaches a larger one. Evidence is precomputed into an index rather than embedded inside the request.

  4. The problem

    Nobody can tell you where the training data came from

    For most models the honest answer to a question about provenance is a shrug. That is a problem the moment somebody has to sign off on the output.

    Our answer

    Every source logged, own hardware

    Origin, licence, date and volume are recorded for every source that goes into training. The models are trained on our own machines in Switzerland, not on rented capacity somewhere unspecified.

Models

Three sizes, one behaviour.

Lumen is the family answering today: three sizes that share the same abstain logic. What differs is how much they can recall unaided, and how long a chain they can hold. Medium and Large take images and documents alongside text.

COST AND WAITING TIME →HOW DEEP IT GOES →Smallanswers in a blinkMediumthe everyday oneLargefrom ProMaxin planningtexttext · images · filestext · images · files
The three sizes of Lumen. Relative positioning, not a benchmark. The curve flattens on purpose: past a point, more compute buys less additional depth, which is why the router sends most questions to the smaller model.
Lumen SmallFast and cheap. Short answers, classification, rewriting, extraction. The model behind the free plan.Text
Lumen MediumThe working model. Long-form writing, code, documents and images in the same conversation.Multimodal
Lumen LargeFor long contexts and deep chains of reasoning, where the answer depends on holding many things at once. Included from Pro.Multimodal
Lumen MaxIn planning. The top of this family, for work where the cost of a wrong answer is higher than the cost of the answer.Planned

A second family, Gauss, is in planning: our own weights, trained from zero, with the same layer built into the architecture instead of wrapped around it. A 1.16-billion-parameter model of it exists and works. Everything above it needs funding.

Both families, and how the architecture works
Everything else

13 kinds of work, one account.

Three of them are above in full. Every one has its own page: what it does, how a session goes, and where it stops.

Building things

Where the output is a file somebody else will run or read.

Checking things

Where the job is to find what is there, not to produce something new.

Everyday work

The half of the week that is reading, sorting and explaining.

Where the rules are strict

Work that has to survive somebody asking where the answer came from.

Your own net

It gets to know you, and shows you what it learned.

From your own conversations it distils a short list of traits - that you write C#, that you want answers without a preamble, that you work in Swiss francs. So you stop explaining it every Monday.

  • Traits, never transcripts - and nothing sensitive, by rule
  • Drawn as a net under Neural net: every trait with the weight it actually carries
  • One switch to turn it off, one button to forget everything
  • Incognito conversations neither feed it nor use it
What is stored, and what is not
neural net
WorkToolsStylewrites C#no preambleSwiss francsmetric unitsChat
Tools

It works things out instead of estimating them.

Thirty-eight tools the model can reach for, and the ones that matter are the boring ones: the questions where a fluent answer and a correct answer look identical. Every tool on this page is tested against a known result on the status page, not listed and hoped for.

Asked

What is the median of these 340 numbers?

Sorted in its head, a model lands near the median. Near the median is a different number, and nothing in the sentence says so.

Statistics
Asked

What is the payment on 300000 over 25 years at 3 percent?

An annuity is a formula with a power in it. Estimated, the figure looks right and is out by thousands over the term.

Interest and loans
Asked

When is that meeting in New York, on 29 October?

Six hours apart, as everyone knows. For four weeks a year it is five or seven, because Europe and the US switch on different days.

Time zones
Asked

Why does this string not match?

A non-breaking space, a soft hyphen, a Cyrillic letter that looks Latin. Invisible on screen, and invisible to a model too - it reads tokens, not characters.

What is really in the text
Asked

Solve for x, and show the steps.

Rearranging is rule-following. A sign error in step three reads exactly like a correct step and changes the answer.

Algebra
Asked

How much did we spend on this in September?

A business account can put read-only SQL over its own usage. The alternative is a number that sounds about right.

Query your own data

The rest read files back, hand you one, or run on your own machine. The full list is here.

Your data

Four promises, and what each one costs us.

Every one of these is a decision that makes the product slightly harder to build. That is what makes them worth writing down.

  • Not used for trainingYour conversations train nothing. Not our models, not anyone else's. That is a decision about the product, not a setting you have to find.
  • Yours to deleteDelete a conversation and it is gone from the database, not hidden. Delete the account and everything attached to it goes with it, in one step.
  • Incognito when you want itAn incognito conversation is never written down at all. It exists in the window you are looking at and nowhere else.
  • Switzerland, on our own machinesServed from hardware we run, with a written record of every source that went into the models. Not a badge, a paper trail.
For companies

The same models behind your own product.

A separate business account, API keys, prepaid credits and usage you can see per key. No monthly seat you have to grow into.