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 tutorials. Use the Technology Path when you want the historical order. The series does not try to cover every paper. Each page selects a mechanism, explains it, records where it fails, and proposes the next test. A page can ship before its experiment exists.

Current judgments live in the Frontier Radar. Experiments are optional. 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.