Superalignment

AI is becoming more powerful every day.
Humanity should remain in control.

We’re an independent group who still believes in that mission. And we’re building the first practical solution where AI produces the intended output and the human stays responsible.

Our mission

Superintelligence for everyone

AI governance is crucial, and should be proven in practice. Not after discovering the limits.

We are building the first practical solution to superalignment: a way to make powerful systems steerable to the people who live with the results.

News

We don't make the headlines, these people are.

Three changes we are carrying forward. The full wire, 89 items from 10 sources in the last 45 days, is on the news page.

The product

Human + agent workspace that lets you vibe code, collaborate, and supervise

Praxis brings your team and their agents into one build, then move straight into coding, testing, and shipping. Reuse workflows that already work, route anything uncertain to the person accountable for it, and keep what used to be scattered across dev tools and tickets in one place.

Atrium / Client Intake Customer Portal
Praxis client intake portal surface

Front-facing customer surfaces connected directly to team execution. Publish custom apps, intake customer requests, and route exceptions without losing context.

Explore Atrium →

Applied superalignment

How organizations deploy autonomy.

Real workflows across finance, customer operations, and risk where failures carry an immediate balance-sheet or regulatory cost.

Finance and accounting

Invoice reconciliation & approvals

Three-way match against purchase orders and receipts, with duplicate payments blocked rather than reported after the fact.

Lattice Verity Resolve
View finance use cases
Customer operations

Support triage & refund governance

Urgency weighed against account value, and anything a customer has raised twice going up automatically before money moves.

Lattice Verity Resolve
View customer operations
Risk, compliance and audit

KYC & policy attestation

Every claim tied to an observation, with control libraries, evidence requirements and statutory clocks enforced before release.

Lattice Verity Resolve
View risk & audit use cases

Our research

Convergence Programming

Iterative, World-Grounded Alignment of Lossy Human Intent with Executable Behavior

Language models turn lossy human intent straight into executable behavior. A non-programmer can generate an artifact they cannot inspect; an agent can act through tools whose side effects the conversation never reveals. A system can then pass every visible check and still be wrong. We call that false convergence, and the program exists to find it before the system acts.

The paper is being prepared for release. It is a conceptual and evaluation-design contribution with a preliminary pilot, not a benchmark or a leaderboard.