Four research directions · one system
From a theory of meaning to verified action.
Frontier-level outcomes are not determined by model size alone. A meaningful share of capability can be assembled around a model through context, workflow control, tools and independent verification.
Research program
This is not a collection of unrelated products. Each layer tests and uses the one before it: from the representation of meaning to controlled action and the transfer of verified behavior into models.
How does meaning become compact while preserving structure and exposing gaps?
SCT models atoms, fields, gaps and reconstruction as mechanisms that can be observed and tested.
Formal hypotheses and discriminating experiments Read research noteHow can any LLM receive the right working environment for the next step?
Autopilot compiles context, role, tools, constraints and verification into one goal-to-outcome runtime.
Verified action over replaceable models Read working paperWhen do independent lenses genuinely improve a decision?
Rooy assembles temporary molecules of specialists only where diversity has measurable value.
Bounded swarms with attribution and stop conditions Read working paperHow can verified system behavior be transferred into models we control?
The learning material is not raw chat, but episodes of state → context → action → verified outcome.
Local models that must pass promotion gates Read working paperPublished work
Every public version states its problem, method, evidence scope and limitations. Status describes maturity; it does not manufacture it.
A testable language for structured meaning
A research framework for describing how subjective meaning condenses into stable structures, how gaps create pressure for action, and what a receiver needs to reconstruct meaning.
Strongest evidenceOperational definitions, formalization tracks and a growing set of discriminating experiments.
Current limitationSCT remains a research framework; several central correspondences and general claims are not yet established.
Read the research note ↗A model-agnostic runtime for verified action
An architecture in which a Thinker maintains the goal, a Context Engine compiles the working environment, a Doer acts through a bounded Harness, and a Verifier accepts only evidence-backed outcomes.
Strongest evidenceThe runtime spine and context/authority boundary pass provider-free tests.
Current limitationLive model uplift and the target of ≥90% frontier quality have not yet been demonstrated.
Read the working paper ↗Temporary collectives and the cost of agreement
A bounded swarm contract, a model of correlated evidence and cost-matched experiments for determining when independent lenses improve a decision.
ContributionOperational definitions, an analytical illustration and a proposed evaluation protocol.
Current limitationNo measured collective gain or comparative Rooy benchmark is claimed.
Read the working paper ↗Learning from verified action
An episode-to-model research pipeline: attributable actions, curation, training objectives and a promotion gate that preserves the external control system.
ContributionAn episode schema, training proposal and held-out evaluation design.
Current limitationNo trained checkpoint, public dataset or measured transfer gain is introduced.
Read the working paper ↗A live view of a bounded research swarm
An observable SCT/Rooy surface that brings atom activity, theoretical lenses, semantic fields, gaps and evolution traces into one research interface.
Strongest evidenceL1 activations and the liveness control plane have runtime traces.
Current limitationThe observatory reports one experiment; it is not evidence for a general theory of swarm intelligence.
Open the observatory ↗Selected evidence
Provider-free mechanics, reproducible experiments and live quality are different levels of evidence. We publish the result together with the non-claim.
One immutable TaskState, canonical reducer, checkpoints and deterministic replay preserve a multi-milestone lifecycle.
Supports state and recovery mechanics. Does not establish model reasoning quality.
Role-specific context manifests, scoped grants, Harness deltas and integrity-checked receipts are tied to TaskState transitions.
Supports grounding and authority contracts. Does not establish that the selected context is optimal.
Default-deny launch, structured decoding, session boundaries, redaction and postflight validation pass without a model call.
Supports adapter readiness. Live provider quality and end-to-end uplift remain untested.
Publication method
Lab OS retains the full working context. Public IO Lab receives only self-contained, versioned artifacts that are safe to publish.
Canon, sessions, plans, hypotheses, negative results, datasets, evaluation traces and internal decisions.
Owner · agents · invited collaboratorsResearch notes, technical reports, systems, experiments, demonstrations and other accessible artifacts.
Researchers · engineers · collaboratorsThe question, hypothesis and working context remain inside Lab OS.
The method separates the proposed effect from alternative explanations.
The result receives an evidence scope, non-claims and a fixed version.
A self-contained artifact becomes available without private context.
Open questions
The public queue contains questions for which a discriminating experiment can be designed—not promises of future features.
How can we measure that a context view is small enough while preserving everything required by a role, model and step?
What share of the gain comes from context compilation, planning and verification rather than the foundation model?
Which verified episodes transfer capability into weights, and which capabilities should remain in the external runtime?