Feiyu's Technical Blog

Notes on software, systems, and things I am learning.

Agents & Automation

Local models, tool-using agents, and practical information-extraction workflows.

  1. How I Automated the 1Point3Acres Daily Check-In and Quiz

    A Windows app reuses my signed-in Chrome, checks in every morning, loads a local LLM only when a quiz needs an answer, and verifies the result.

  2. How I Let Codex Talk to ChatGPT Through My Signed-In Chrome

    A local agent lets Codex send text or PDFs to my normal ChatGPT page, return the answer, and continue the same conversation later.

  3. Local LLM + Agent for Web Information Extraction

    A local agent architecture for semantic web extraction, browser automation, bounded model context, and durable task state.

Game Perception — Olden Era

Computer-vision experiments that turn arena gameplay screenshots into structured game state.

  1. Training a Game UI Icon Detector Using Only the Icon Catalog

    We train on 390 catalog icons, then test whether the model can find and identify heroes and skills in complete game screenshots.

  2. Full-Image Icon Search with Sliding Windows and Visual Embeddings

    In this seven-frame experiment, the search often identifies the right hero or skill, but its highest-scoring box is not always the best crop.