8000 wilsonwu-ai (Wilson Wu) · GitHub
[go: up one dir, main page]

Skip to content
View wilsonwu-ai's full-sized avatar

Block or report wilsonwu-ai

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
wilsonwu-ai/README.md

Wilson Wu as an ASCII portrait made of letters, beside a neofetch-style card with education, day jobs, certifications and live GitHub stats

I ship AI systems and then try to break them: a language model running bare metal on an FPGA, eval harnesses that run the code instead of asking a model, and agent fleets whose planner prices the job before anything spawns.

LinkedIn · Every original repo

🛠️ Fresh off the workbench

Shipped Project What it is
Nov 15 hbs-eta-2026 Notes from the HBS ETA Conference 2026: Romney, the new SBA rules, Guild Garage and roll-ups, in plain language.
Nov 9 thinkstop Stop a reasoning model's thinking loop and ask for the answer.
Nov 8 sundai-hack-148 · live DEFY: an AI seals its guess before each of your 12 taps, then dares you to pick anything else. Sundai Hack 148.
Nov 7 leveraged-buyouts-explained · live Leveraged buyouts, explained: search funds and ETA in plain language.
Nov 7 memory-dream Read-only audit of Claude Code's memory folders: reports what a clean-up pass would fix and prints a proposed plan.

My five newest portfolio repos, pulled from the GitHub API every morning.

⭐ Greatest hits

Project What it is
🔌 vibe-silicon We configured Intel's prebuilt Nios II soft core into an Intel MAX 10 FPGA (DE10-Lite) that had no processor, then ran llama2.c on it bare metal.
🧪 smoleval Eval harness for small code models: HumanEval + MBPP, sandboxed execution, unbiased pass@k, held-out set locking.
🧠 reasoning-over-recall Why you'd train a small language model to reason instead of memorize - a plain-language explainer checked against the phi-1 paper, plus a working…
🕸️ graph-engineering-kit The runnable half of graph engineering. A planner that prices a job before spawning it, ten rules that stop the three failure modes, four production…
⚡ local-llm-decode-ceiling Why local LLM decoding on Apple Silicon reaches only half its memory-bandwidth ceiling, and what speculative decoding wins back.
💧 why-ai-needs-water · live A 3D liquid-cooled GPU server loop you can take apart in your browser. One input drives every gauge.

🐍 Meanwhile, a snake is eating my contribution graph

A snake game playing across my GitHub contribution graph
How this profile builds itself
  • The portrait is my headshot turned into type by scripts/ascii_portrait.py: background removed, local contrast lifted, then every cell mapped onto a 20-step ramp of characters, mostly letters, sorted by how much ink each one puts down. The photo never enters the repo, only the letters.
  • Easter egg: the mid-tones of that ramp are l i s u n o w, the letters of my name, so wherever the photo sits in the mid-greys, my name does the drawing. In the light card that is most of my face.
  • The card is plain SVG written by scripts/build_card.py, Python standard library only. Every number on it comes from the GitHub GraphQL API. The fortune line quotes one of my own repo descriptions, a different one each day.
  • The schedule is one GitHub Action that runs daily on the built-in token, so there is no personal token to expire, and it commits as the Actions bot, so it never pads my contribution graph.
  • Credits: the snake is Platane/snk. The portrait-plus-neofetch idea comes from Andrew6rant; this is a from-scratch take on it.

Popular repositories Loading

  1. roam-3d roam-3d Public

    Walk a real-estate listing like a first-person video game (WASD, mouse-look, jump, crouch) — plus a live 3D Gaussian Splat showcase. Three.js, no build step.

    JavaScript 2 1

  2. macos27 macos27 Public

    macOS 27 — pixel-faithful Liquid Glass macOS desktop simulation in the browser (personal customization base)

    HTML 2

  3. the-model-is-the-easy-half the-model-is-the-easy-half Public

    A plain-language tour of everything around the model: parsing, retrieval, serialization, verification. Every claim checked against a primary source. Includes a six-stage RAG demo that runs with no …

    HTML 2

  4. Food-Delivery-Analysis Food-Delivery-Analysis Public

    1

  5. scaling-open-models scaling-open-models Public

    How Kimi/Moonshot scales open models — an ELI5 with system-design diagrams (Muon, MuonClip, Kimi Linear, agent swarms, K2.5, Attention Residual)

    1

  6. graph-engineering-for-operators graph-engineering-for-operators Public

    How to stop queueing your AI in a straight line. Graph engineering explained for operators: the fake edge test, the diamond, the verifier, and what it actually costs.

    JavaScript 1

0