Skip to content

AGI Frontier / Research Lab Manual

From token prediction to systems that improve themselves.

A public, reproducible, continuously updated tutorial series tracing the shared path from LLMs and multimodal models to generative models, world models, VLAs, and self-improving agents.

A map that keeps growing

Current state

FocusWorld models · VLA · Verifiers
MethodRead → reproduce → record failure
CadencePublish updates, preserve changed judgments

How to use this site

If you are new here, start with the Capability Map, then use the Technology Timeline to recover the historical causes. The tutorials do not try to cover every paper. Each one selects a mechanism, builds a minimal implementation, records where it fails, and proposes the next test.

Researchers can go straight to the Frontier Radar for current judgments and open problems. Engineers can start with the Experiments. GitHub Markdown is the source of truth; revisions and corrections remain public.

Updates: Start with GitHub Watch. RSS/Atom and email subscriptions will come after the publishing cadence is stable, so the learning loop does not become an operations project.

One-line promise

Do not maintain a list of what I have read. Maintain how my AGI judgments changed, and how to test the next one.