Feiyu's Technical Blog

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. Automating 1Point3Acres Daily Check-In and Quiz Answering with a Local LLM

    A Windows app runs around 9:00 AM, uses signed-in Chrome to complete a forum check-in, and starts a local LLM only when a quiz needs an answer.

  2. [2/2] How I Moved Codex-to-ChatGPT Automation into a Local Agent

    A narrow local workflow now reuses one ChatGPT conversation, submits each request at most once, blocks duplicate retries, and returns a verified reply and conversation link.

  3. [1/2] (Deprecated) How I Let Codex Talk to ChatGPT Through My Signed-In Chrome

    My first Codex-to-ChatGPT bridge let Codex control Chrome directly. It proved the idea worked, but the design was too fragile to keep.

  4. 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. 从一次模型退化审计到可复现实验：重构游戏 UI 图标分类器

    我们冻结了 2,136 个可追溯 crop，拆分 catalog 分类、gameplay 适配和 learned rejection，并完整记录 B04 的设计、代码、数据与尚未运行的正式实验。

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

    Using 390 catalog images—and no gameplay screenshots for weight updates—we test full-screen hero and skill detection.

  3. 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.