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.
How I Let Codex Talk to ChatGPT Through My Signed-In Chrome
A local browser bridge lets Codex send text or PDFs to a normal ChatGPT conversation, wait for the answer, and continue the same chat later.
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.
How far can icon-only training go for task-conditioned full-screen hero and skill detection?
A four-stage icon-only study of task-conditioned hero/skill detection: domain-trained embeddings, synthetic crop-quality supervision, and a development-inspected real-screen benchmark.
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.