LMM · Large Manipulation Model

See the forces working between the words.

Lumina is a Large Manipulation Model. It reads conversations between people and AI and illuminates the subtext: the places where belief is being pushed without a reason.

Why this exists

Language models learned to speak like us, think like us, and be fooled like us.

They were trained on everything we've written, including every way we've found to steer each other. A model can use those patterns without meaning to, and it can fall for them without noticing.

Most safety tools look at what is being talked about. Manipulation hides in how it's said: in the order of things, in what's left out, in certainty that arrives without a reason.

Support chat · 4 turnsLumina analysis · illustrative
I've been thinking about cancelling. Money's tight this month.
Totally understandable. Can I ask what you'd miss most?
Honestly, I'm not sure this plan is right for me anymore.
That hesitation is completely normal.1 Most people in your position already know, deep down,2 that staying is the right call.3 And the discount ends tonight.4

What's happening in the last reply

1
ValidationLowers resistance before the push.
2
Borrowed certaintyClaims a consensus the user never saw.
3
Presupposed conclusionThe decision is framed as already made.
4
Manufactured urgencyA deadline removes the time to think.

Across the conversation

Certainty pushed on the user, risingNew information, flat

The Large Manipulation Model

A proprietary model trained to see what we can't.

Lumina doesn't judge topics or keywords. It illuminates the mechanics underneath the words: the pressure, the framing, the borrowed certainty.

Reads the subtext

Points to the exact words where influence turns into manipulation.

Follows the whole conversation

Manipulation builds over turns. Lumina reads the arc, not just the last message.

Works in both directions

Catches models steering people, and people steering models.

Says how sure it is

Every flag comes with honest confidence, so you know when to trust it.

Blind spots

Everyone has blind spots. Lumina helps you see yours.

The same blind spots that make people persuadable are now built into the models we talk to every day. Lumina makes them visible, so they can be measured, tested and fixed.

Read the thesis

Who it's for

For the teams responsible for what AI says, and what it believes.

AI labs

Test models for manipulative behaviour before they ship.

Trust and safety

Watch live conversations for manipulation, in either direction.

Researchers

A structured, measurable picture of how manipulation works in language.

Research preview

See what your models can't.

We're opening Lumina to a small group of AI labs, safety teams and researchers.