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. Three Ways I Tried to Automate 1Point3Acres Daily Check-In and Quiz Answering

    Direct Codex browser control, a supervised WebContentAgent library, and a fully local LLM workflow—what failed, what I use now, and what I am still exploring.

  2. [2/2] How I Made a Codex-to-ChatGPT Bridge Verifiable

    A local bridge sends one authorized request and brings back a checked answer. Its failures explain what message identity, durable state and realistic tests must get right.

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

    The first prototype made the round trip work. Its failures taught me why browser mechanics need a smaller, testable home.

  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

Experiments that turn Olden Era Arena screenshots into structured game state, grouped by the evidence they use and shown in conceptual order.

ApproachB020 · 架构与系统合同

游戏 UI 理解总设计

从这里开始。区分当前像素观测与历史上下文，理解场景、图标身份、属性字段和视频审核各自的职责。

  1. 视频帧
  2. 可见 UI 状态
  3. 时序变化
  4. 可审核证据

Approach现在看到了什么画面？

识别当前场景

B021 用文字与空间规则识别页面；B022 研究文字不足时的加载页、战场等固定 UI。展开文章查看真实原图、全部命中类别和待审核样本。

  1. OCR 与位置
  2. 视觉补充
  3. 场景证据或拒识

Approach这个页面里有哪些对象和数值？

理解场景内部的元素与字段

B023 展示五类标题与图标关联，B024 比较小标题 OCR 的准确性和速度，B025 定义英雄属性、归属与时间证据。

  1. 已知场景
  2. 标题与图标
  3. 身份与可用性
  4. 英雄属性与时间

ApproachKnown geometry · nearly fixed camera

Calibrated Grid Registration

Use the battlefield’s regular hexagonal geometry and a saved calibration to infer cell positions, then refine their alignment from screenshot edges.

  1. Calibrated grid
  2. Image edge scoring
  3. Small alignment correction

ApproachKnown position

Fixed-Crop Classification & Rejection

Assume each target icon appears at a known UI location. With localization removed, perception becomes a classification-and-rejection problem.

  1. Known UI slot
  2. Fixed crop
  3. Classify + reject

ApproachUnknown position · learned localization

Learned Object Detection

Do not assume the icon location is known. A learned detector proposes boxes; a separate catalog matcher suggests identities. The current evidence is a small selection-screen pilot.

  1. Full screenshot
  2. Learned detector
  3. Boxes + identities

ApproachUnknown position · code-generated candidates

Sliding-Window Icon Detection

Search the full screenshot with many candidate crops, encode each crop into visual features, and match them against the known icon catalog.

  1. Full screenshot
  2. Candidate crops
  3. Catalog matching

Game Probability — Olden Era

Reviewed game tables turned into transparent Arena odds, with the event and evidence boundaries kept explicit.

  1. Olden Era Arena: Which Factions Offer These Five Skills Most Often?

    Ranked mage and warrior tables for 奇术、秘术、抗性、原始魔法、战斗魔法, rechecked against Arena version 0.80.49.