Norwin YuAI usage research
中文 AI usage research

About / 2026

Norwin Yu.

Independent AI usage research. I study how models, interfaces and local hardware meet — lately through browser games, agent harnesses and the verification layer that keeps both honest.

AI usage researchOpen to research conversationsGitHub ↗

01 / Research areas

Research areas.

Six domains, each backed by something shipped, tested or written down. The point is the handoff between them: model behaviour, interface craft, local infrastructure and the writing that makes the experiments legible.

Capabilities, tools and evidence
DomainFocusToolsSelected evidence
01AI systems & agents智能体系统Agent workflows that survive real inputs: retrieval, tool use, memory, routing, guardrails and evaluation.Agent orchestration · RAG · Evals · Local inference · Prompt systemsName That LLM; multi-tool agent harnesses; multimodal production pipelines.
02Product experiments产品实验Static-first front ends, pragmatic APIs and deploy paths that one person can actually maintain.TypeScript · React · Node · Python · GitHub ActionsGame + tooling pipeline probes; static deployment; 73-check Playwright regression.
03Spatial interfaces空间界面Three.js, WebGL and Godot interfaces where depth and motion make information easier to hold.Three.js · WebGL · Godot · Shaders · Interaction designTactical battlefield; 3D sect mountain gate; cinematic game UI.
04Local infrastructure本地基础设施Linux, CUDA, containers and local GPU workflows. Systems I can rebuild from notes.Linux · CUDA · Docker · Self-hosting · ObservabilityTwo-GPU home lab; local inference; static deploy pipelines.
05Research & writing研究与写作Small experiments with methods, caveats and the failed attempts left in the record.Benchmarks · Data analysis · Visual essays · DocumentationName That LLM; The 44 GB problem; game build postmortems.
06Interface design界面设计Editorial hierarchy, typography and restrained motion, built in code rather than a mockup.Art direction · Typography · Motion · PrototypingThis site; product surfaces across the games.

Also in the toolkitGit / GitHub Actions · Figma · SQL / Redis · Docker Compose · headless visual QA · Blender basics.

02 / Principles

Method.

Four defaults that show up in the code, the writing and the way a project gets scoped.

01

Local before cloud

Private data stays on the desk. Use frontier models where the capability gap is real, not by default.

02

Ship the loop

A playable slice with an end state beats a polished scene with no game. The fifth run is the test.

03

Measure, then trust

Prompt-level splits, seed checks and screenshots. A single run is an anecdote, not a result.

04

Write it down

Method, caveat, failure. The notes are how the next project starts faster.

03 / Now

Currently.

A snapshot, not a résumé. For the full list of work, use the work page; for the workstations and model routing, use Local.

Current experiments

Games, comparisons and coding tools, plus the harness around them. The next step is a tighter loop between generated assets, playtesting, a Blender-assisted comparison and visual verification.

Selected experiments

Research conversations

Open to conversations around AI usage, game prototypes, developer tools and local inference. The fastest route is a short note with the question, the constraint and the deadline.

GitHub