FAQ

Strange Lab builds Predictive Intelligence: world models that learn how a company or domain changes, forecast what happens next, and compare the likely consequences of different actions.

What does Strange Lab build?

Every organisation already generates a continuous record of its world: mail, chat, documents, tickets, code, customer activity, decisions, and outcomes. Strange Lab turns that record into a source-linked timeline, reconstructs the state of the organisation at any point, and trains a world model on how that state changes.

The result is a living model of the organisation: memory of what happened, a view of what is happening now, forecasts of what comes next, and a way to test possible actions before taking them.

How do the pieces build on each other?

Each layer makes the next one possible:

1. Record: activity from existing systems becomes a common stream of dated, source-linked events.
2. State: those events become an as-of snapshot of the world — what was known, what was moving, and what was stuck.
3. World model: the model learns how one state tends to become another, including how different actions change the path.
4. Predictions: that learned structure becomes forecasts people can use: outcome, timing, risk, next actor, surprise, or likely consequence.
5. Decisions: people and agents query those forecasts when deciding what to do next.
6. Learning loop: later events score the forecast and become new training evidence.

The layers reinforce one another. The same event spine powers replay, training, evaluation, live forecasts, and the feedback loop that improves them.

What is a world model?

A world model learns the dynamics of one particular world rather than language from the internet at large. It carries the world's state forward: given what is true now, what is likely to happen next, and how does that future change when the action changes?

For a company, the world is its people, work, systems, customers, and decisions. For our public experiments, it can be a software project, the FDA oncology pathway, the U.S. economy, or Bismarck's political world. The machinery is the same: build the record, learn its dynamics, predict the next state.

How is this different from asking an LLM?

An LLM is a powerful interface to language. A world model is the predictive engine for a specific world.

An LLM can read a snapshot and give a plausible answer. Strange Lab preserves time, source, state, action, and outcome; trains on the transitions between them; and checks the forecast against what happened later. Used together, the world model supplies the memory and predictive core while the LLM lets a person or agent ask questions, explore scenarios, and act on the answer.

How do you test a forecast?

We stop the record at a historical cutoff and hide what happened later. The model reconstructs the state at that moment, makes its forecast, and the subsequent record grades it.

The holdout matches the real question. Project Confirm holds out entire drug assets. Project OSS predicts outcomes and timing from repository history. Bismarck gives the world model and GPT the same pre-cutoff evidence, then scores both against the hidden future. The result is an inspectable answer key, not a retrospective story.

What has the testing shown?

• Project OSS trains on 5.13 million events across Rust, Kubernetes, Node.js, and Nixpkgs. The world-model family beats linear baselines across the core forecasting tasks and gets stronger as relevant data grows.
• Project Confirm Oncology turns 17,703 FDA, trial, submission, and label events into 3,275 held-out test windows from entirely unseen drug assets. It reaches 0.857 AUROC on the next regulatory gate and finds a withdrawal signal with a median lead of about 24 months.
• Bismarck beats GPT on 36 of 40 hidden-history forecasts.
• U.S. macro records 33% lower error than pure momentum across the 159 largest-change windows.

One record-to-world-model loop now works across software operations, clinical regulation, politics, and the economy. The Evidence page carries the scored results, comparators, and underlying receipts.

What does this provide inside a company?

The company gets an operational model it can query. It can reconstruct what was known when a decision was made, find repeated workflows and broken handoffs, forecast completion and delay, identify unusual work, measure process drift and key-person risk, and compare the expected effect of acting now versus later.

That same model gives agents a map of the organisation. Instead of automating whichever task is easiest to describe, an agent can target the workflows that matter, use the state of the company when choosing an action, and learn from the outcome.

How does it fit with existing systems?

Mail, chat, Drive, Jira, Salesforce, code hosts, and internal tools remain the systems where work happens. Strange Lab connects their permitted activity into one dated event layer and sits above them as the organisation's memory, simulation, and prediction system.

Because every event retains its source, a forecast can be traced back through the state that produced it. The organisation gets one model of how its work fits together while its people keep working in the tools they already use.

How are privacy and customer-specific training handled?

Private workspace records stay private. Our current company work runs locally, and raw work evidence is not published. Source permissions define what enters the model; events remain traceable to their source; and restricted deployments can use metadata, structured fields, snippets, or hashes instead of unrestricted raw text.

Each customer controls its sources, retention, deletion, redaction, model training, and any sharing outside its environment. Customer-specific models and evaluations remain separate from public research.

Can an agent act on the model automatically?

Yes, at the level of autonomy the organisation chooses. A deployment can begin with read-only analysis, move into shadow recommendations, add approval-gated actions, and automate narrow workflows once their outcomes can be checked reliably.

The world model makes that progression measurable. Every proposed action starts from an explicit state, every forecast can be recorded, and every result returns to the learning loop.

What can I see today?

Start with the two flagship projects: Project OSS for software operations and Project Confirm Oncology for clinical-regulatory forecasting. Then try Bismarck, Enron, Technology History, or public macro. The Examples page keeps the current public set together, and the Evidence page carries the scored results.

Where does this go?

As the event record grows, the same world model becomes a deeper operational memory, a better forecasting system, and a more capable decision layer for both people and agents. A company can ask what is happening, what happens next, what changes if we act, and which action gives us the future we want.

That is Predictive Intelligence.