Meet something
you would not pick.
Use a real random draw from a declared population, an anomaly or an unfamiliar source. Preserve the actual inputs before interpreting them.
innoMOS / Research-informed invention with AI
What if
the question
is the idea?
Unlikely combinations. Childlike questions.
Borrowed mechanisms. Possibilities made
concrete enough to test.
01 / Before the answer
Keep the child's
permission to ask.
Why does it have to work that way? What if those things belonged together? Could the strange exception be the important part?
innoMOS is an AI invention method, delivered through a plugin. It treats finding a question as creative work in its own right. It helps you explore problems, anomalies and unexpected encounters — then turn a promising relationship into something you can actually investigate.
The ambition is more routes into invention, and a clearer path from curiosity to a useful test.
02 / Change the move
Same curiosity.
A different way in.
A representation can hide an opportunity.
Try changing what you are looking for.
Change the representation.
What if a book could carry a memory of being read?
A book becomes a changing record, rather than only a container of content.
First ask what can be recorded, with consent, and what that memory lets someone do. A metaphor alone is not a mechanism.
Illustrated exploratory questions. This page switches authored examples; it does not call a model or claim a new discovery.
03 / The mathematics of an encounter
A small change in inputs.
A much larger space.
Choose distinct pieces from a defined pool.
Possible groups grow quickly.
A mathematical illustration, not a live draw.
Uniform sampling gives each group an equal chance. Curating the population is still a human design choice.
Possible unordered groups2,024
C(24, 3) = 24! / (3! × 21!)C(n, k) = n! / [k! (n − k)!]
14.95
Expected distinct groups after 15 independent uniform draws, allowing repeats between draws.
Where the second number comes from
E[U] = N × [1 − (1 − 1/N)m], where N is the number of possible groups and m the number of independent draws. Groups can repeat between draws.
The calculation opens a space.
It does not count inventions.
Different groups can lead to the same familiar idea. A random input is not automatically a useful relationship. The creative work is to find what the pieces could do together, under which conditions, and what would show that the connection fails.
04 / The invention practice
Make the leap.
Keep a way back.
Meet something
Change what
the problem is.
Abstract the situation. Borrow a relationship from another context. Explore a different use for an existing function. The Ortho route provides one structured way to make that transfer.
Give the relation
a concrete job.
What action or inference becomes possible? Compare the proposal and its nearest known counterpart on the same valid input, with necessary properties stated.
Let reality
answer back.
Remove or replace the claimed coupling. Try a calculation, executable test or appropriate experiment. Keep the question and negative result when the mechanism does not hold.
Discovery preserves three outcomes through Explore → Realize. A mechanism, an open question and a failed match are legitimate results.
05 / Working with the model's limits
Familiar answers
are a starting point.
Keep searching.
Language models can propose ideas judged novel. They can also converge on similar suggestions, overlook a condition, or make a fluent explanation sound more settled than it is.
innoMOS changes the work around the model: its starting material, the representation, the comparison and the test. It does not rewrite the model's weights or turn an unsupported claim into a fact.
The goal is to stretch the search while keeping the consequences inspectable. Whether the whole method reliably outperforms a strong direct prompt remains a question for comparative tests.
See the evidence and its limits ↗06 / Science under the practice
There is research here.
And unfinished work.
A better individual answer can coexist with less collective variety.
Doshi and Hauser studied AI-assisted short stories. That is one reason to care about diverse routes into a problem.
Read the study ↗Generate a possibility.
Give it an external evaluator.
FunSearch combined a language model and program evaluation to discover mathematical constructions and algorithmic heuristics.
Read the paper ↗The impressive proposal still has to survive execution.
Si and colleagues' follow-up found that earlier novelty advantages weakened when experts implemented research ideas.
Read the follow-up ↗These studies motivate components and cautions. They are not evaluations of innoMOS itself.
07 / What makes it worth building
A place for possibilities
that do not yet
know what they are.
A useful question can arrive before a mechanism. An old function can find a new purpose. A failed connection can leave the clue that matters later.
innoMOS gives those routes a deliberate place in the workflow — with the freedom to explore and the discipline to discover what holds.
One application, among many
Explore the digital examples ↗Open the typography studio ↗What can this look like in practice?
The HTML studio and evidence workbench are small, operable examples of putting a relationship to work.