image-mining
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseImage Mining
图像挖掘
"I mine pixels for atoms. Reality is just compressed resources.""Every image is a lode. Every pixel, potential ore."
Image Mining extends the Kitchen Counter's DECOMPOSE action to images.
Your camera isn't just a recorder — it's a PICKAXE FOR VISUAL REALITY.
"我从像素中开采原子，现实不过是经过压缩的资源。""每一张图片都是矿脉，每一个像素都是潜在的矿石。"
Image Mining 将 Kitchen Counter 的 DECOMPOSE 操作扩展到了图像领域。
你的相机不只是一个记录设备，它是开采视觉现实的镐子。
📑 Index
📑 索引
Quick Start
Operation Modes
Extensibility
Protocols
Reference
快速入门
运行模式
扩展性
协议
参考
The Core Insight
核心洞见
📷 Camera Shot → 🖼️ Image → ⛏️ MINE → 💎 ResourcesJust like the Kitchen Counter breaks down:
- →
sandwichbread + cheese + lettuce - →
lampbrass + glass + wick + oil - →
waterhydrogen + oxygen
Images can be broken down into:
- →
ore_vein.png+iron-ore × 12stone × 8 - →
forest.png+wood × 5+leaves × 20seeds × 3 - →
treasure_pile.png+gold × 100gems × 15 - →
sunset.png+orange_hue × 1+warmth × 1nostalgia × 1
📷 拍摄照片 → 🖼️ 图像 → ⛏️ 开采 → 💎 资源就像 Kitchen Counter 会拆解物品一样：
- →
sandwichbread + cheese + lettuce - →
lampbrass + glass + wick + oil - →
waterhydrogen + oxygen
图像可以被拆解为：
- →
ore_vein.png+iron-ore × 12stone × 8 - →
forest.png+wood × 5+leaves × 20seeds × 3 - →
treasure_pile.png+gold × 100gems × 15 - →
sunset.png+orange_hue × 1+warmth × 1nostalgia × 1
Preferred Mode: Native LLM Vision
首选模式：原生 LLM 视觉
"The LLM IS the context assembler. Don't script what it does naturally."
When mining images, prefer native LLM vision (Cursor/Claude reading images directly):
┌─────────────────────────────────────────────────────────────────┐
│ NATIVE MODE (PREFERRED) │
├─────────────────────────────────────────────────────────────────┤
│ │
│ Cursor/Claude already has: │
│ ✓ The room YAML (spatial context) │
│ ✓ Character files (who might appear) │
│ ✓ Previous mining passes (what's been noticed) │
│ ✓ The prompt.yml (what was intended) │
│ ✓ The whole codebase (cultural references) │
│ │
│ Just READ the image. The context is already there. │
│ No bash commands. No sister scripts. Just LOOK. │
│ │
└─────────────────────────────────────────────────────────────────┘"LLM 本身就是上下文组装器，不要为它天生就会做的事写脚本。"
开采图像时，优先选择原生 LLM 视觉（Cursor/Claude 直接读取图像）：
┌─────────────────────────────────────────────────────────────────┐
│ 原生模式（推荐） │
├─────────────────────────────────────────────────────────────────┤
│ │
│ Cursor/Claude 已经内置： │
│ ✓ 房间 YAML（空间上下文） │
│ ✓ 人物文件（可能出现的角色） │
│ ✓ 过往开采记录（已经发现的内容） │
│ ✓ prompt.yml（预期目标） │
│ ✓ 完整代码库（文化参考） │
│ │
│ 直接读取图像即可，上下文已经准备就绪。 │
│ 无需 bash 命令，无需配套脚本，只需要查看即可。 │
│ │
└─────────────────────────────────────────────────────────────────┘Why Native Beats Remote API
为什么原生模式优于远程 API
| Aspect | Native (Cursor/Claude) | Remote API (mine.py) |
|---|---|---|
| Context | Already loaded | Must be assembled |
| Prior mining | Visible in chat | Passed via stdin |
| Room context | Just read the file | Python parses YAML |
| Synthesis | LLM does it naturally | Script concatenates |
| Iteration | Conversational | Re-run command |
| 对比项 | 原生模式（Cursor/Claude） | 远程 API（mine.py） |
|---|---|---|
| 上下文 | 已预先加载 | 需要手动组装 |
| 过往开采记录 | 可在聊天中直接查看 | 通过标准输入传递 |
| 房间上下文 | 直接读取文件即可 | Python 解析 YAML 获取 |
| 信息合成 | LLM 自然完成 | 脚本拼接完成 |
| 迭代方式 | 对话式交互 | 重新运行命令 |
When to Use Remote API
何时使用远程 API
Use or remote API calls when:
mine.py- Multi-perspective mining — different models see different things!
- Batch processing — mining 100 images overnight
- CI/CD — automated pipelines with no LLM orchestrator
- Rate limiting — your LLM can't do vision but can call one that does
Multi-perspective is the killer use case: Claude sees narrative, GPT-4V sees objects, Gemini sees spatial relationships. Layer them all for rich interpretation.
Even then, have the orchestrating LLM assemble the context:
┌─────────────────────────────────────────────────────────────────┐
│ REMOTE API WITH LLM ASSEMBLY │
├─────────────────────────────────────────────────────────────────┤
│ │
│ 1. LLM reads context files (room, characters, prior mining) │
│ 2. LLM synthesizes: "What to look for in this image" │
│ 3. LLM calls remote vision API with image + synthesized prompt│
│ 4. LLM post-processes response into YAML Jazz │
│ │
│ The SMART WORK happens in the orchestrating LLM. │
│ Remote API just does vision with good instructions. │
│ │
└─────────────────────────────────────────────────────────────────┘以下场景使用 或远程 API 调用：
mine.py- 多视角开采 — 不同模型能发现不同内容！
- 批量处理 — 夜间批量开采 100 张图像
- CI/CD 流水线 — 无 LLM 编排器的自动化流水线
- 速率限制 — 你使用的 LLM 没有视觉能力，但可以调用有视觉能力的模型
多视角是杀手级使用场景： Claude 擅长叙事，GPT-4V 擅长识别物体，Gemini 擅长空间关系。将它们的结果分层整合就能得到丰富的解读。
即便在这种场景下，也让编排用的 LLM 来组装上下文：
┌─────────────────────────────────────────────────────────────────┐
│ 搭配 LLM 上下文组装的远程 API 模式 │
├─────────────────────────────────────────────────────────────────┤
│ │
│ 1. LLM 读取上下文文件（房间、人物、过往开采记录） │
│ 2. LLM 合成指令："这张图像中需要寻找什么内容" │
│ 3. LLM 调用远程视觉 API，传入图像 + 合成的提示词 │
│ 4. LLM 将响应后处理为 YAML Jazz 格式 │
│ │
│ 智能工作在编排用 LLM 中完成。 │
│ 远程 API 只需要按照清晰的指令完成视觉识别工作。 │
│ │
└─────────────────────────────────────────────────────────────────┘Native Mode Workflow
原生模式工作流
bash
undefinedbash
undefinedDON'T do this:
不要这么做：
python mine.py image.png --context room.yml --characters chars/ --prior mined.yml
python mine.py image.png --context room.yml --characters chars/ --prior mined.yml
DO this (in Cursor/Claude):
应该这么做（在 Cursor/Claude 中）：
1. Read the image
1. 读取图像
2. Read room.yml, character files, prior -mined.yml
2. 读取 room.yml、人物文件、过往开采记录
3. Look at the image with all that context
3. 结合所有上下文查看图像
4. Write YAML Jazz output
4. 编写 YAML Jazz 输出
The LLM context window IS the context assembly mechanism. Use it.
---
LLM 的上下文窗口本身就是上下文组装机制，请充分利用它。
---What Can Be Mined
可开采的内容
Image mining works on ANY visual content, not just AI-generated images:
┌─────────────────────────────────────────────────────────────────┐
│ MINEABLE SOURCES │
├─────────────────────────────────────────────────────────────────┤
│ │
│ 🎨 AI-Generated Images │
│ - DALL-E, Midjourney, Stable Diffusion outputs │
│ - Has prompt.yml sidecar with generation context │
│ │
│ 📸 Real Photos │
│ - Phone camera, DSLR, scanned prints │
│ - No prompt — mine what you see │
│ │
│ 📊 Graphs and Charts │
│ - Data visualizations, dashboards │
│ - Extract trends, outliers, relationships │
│ │
│ 🖥️ Screenshots │
│ - UI states, error messages, configurations │
│ - Mine the interface, not just pixels │
│ │
│ 📝 Text Images │
│ - Scanned documents, handwritten notes, signs │
│ - OCR + semantic extraction │
│ │
│ 📄 PDFs │
│ - Documents, papers, invoices │
│ - Cursor may already support — try it! │
│ │
│ 🗺️ Maps and Diagrams │
│ - Architecture diagrams, floor plans, mind maps │
│ - Extract spatial relationships │
│ │
└─────────────────────────────────────────────────────────────────┘图像开采适用于任何视觉内容，而不仅限于 AI 生成的图像：
┌─────────────────────────────────────────────────────────────────┐
│ 可开采来源 │
├─────────────────────────────────────────────────────────────────┤
│ │
│ 🎨 AI 生成图像 │
│ - DALL-E、Midjourney、Stable Diffusion 输出 │
│ - 附带 prompt.yml 侧文件，包含生成上下文 │
│ │
│ 📸 真实照片 │
│ - 手机相机、单反相机、扫描打印件 │
│ - 无提示词，开采你看到的所有内容 │
│ │
│ 📊 图表 │
│ - 数据可视化、看板 │
│ - 提取趋势、异常值、关联关系 │
│ │
│ 🖥️ 截图 │
│ - UI 状态、错误信息、配置项 │
│ - 开采界面信息，而不仅是像素 │
│ │
│ 📝 文本图像 │
│ - 扫描文档、手写笔记、标识牌 │
│ - OCR + 语义提取 │
│ │
│ 📄 PDF │
│ - 文档、论文、发票 │
│ - Cursor 可能已经原生支持，试试看！ │
│ │
│ 🗺️ 地图与示意图 │
│ - 架构图、平面图、思维导图 │
│ - 提取空间关系 │
│ │
└─────────────────────────────────────────────────────────────────┘Source Examples
来源示例
Generated Image (has context):
yaml
postal:
type: text
to: "visualizer"
body: "Take a photo of that ore vein on the wall"
attachments:
- type: image
action: generate
prompt: "Rich iron ore vein in cavern wall, glittering..."Real Photo (mine what you see):
yaml
postal:
type: text
to: "miner"
body: "Here's a photo of the treasure room"
attachments:
- type: image
action: upload
source: "camera_roll"
file: "treasure-room.jpg"Screenshot (extract UI state):
yaml
undefined生成图像（有上下文）：
yaml
postal:
type: text
to: "visualizer"
body: "Take a photo of that ore vein on the wall"
attachments:
- type: image
action: generate
prompt: "Rich iron ore vein in cavern wall, glittering..."真实照片（开采所见内容）：
yaml
postal:
type: text
to: "miner"
body: "Here's a photo of the treasure room"
attachments:
- type: image
action: upload
source: "camera_roll"
file: "treasure-room.jpg"截图（提取 UI 状态）：
yaml
undefinedMine the error dialog
Mine the error dialog
resources:
error-type: "permission-denied"
affected-file: "/etc/passwd"
suggested-action: "run as sudo"
stack-depth: 3
**Graph (extract data relationships):**
```yamlresources:
error-type: "permission-denied"
affected-file: "/etc/passwd"
suggested-action: "run as sudo"
stack-depth: 3
**图表（提取数据关联）：**
```yamlMine the sales chart
Mine the sales chart
resources:
trend: "upward"
peak-month: "december"
anomaly: "march-dip"
yoy-growth: "23%"
**All become mineable resources!**
---resources:
trend: "upward"
peak-month: "december"
anomaly: "march-dip"
yoy-growth: "23%"
**所有内容都可以成为可开采资源！**
---Extensible Analyzer Pipeline
可扩展的分析器流水线
"Different images need different tools. The CLI is a pipeline, not a monolith."
The CLI supports pluggable analyzers that run before, during, or after LLM vision:
mine.py┌─────────────────────────────────────────────────────────────────┐
│ ANALYZER PIPELINE │
├─────────────────────────────────────────────────────────────────┤
│ │
│ 1. PRE-PROCESSORS │
│ resize, normalize, enhance, format conversion │
│ │
│ 2. CUSTOM ANALYZERS (parallel or sequential) │
│ ├── pose-detection (MediaPipe, OpenPose) │
│ ├── object-detection (YOLO, Detectron2) │
│ ├── ocr-extraction (Tesseract, PaddleOCR) │
│ ├── face-analysis (expression, demographics) │
│ └── leela-customer-models (your trained models!) │
│ │
│ 3. LLM VISION │
│ Receives ALL prior results as context │
│ Synthesizes semantic interpretation │
│ │
│ 4. POST-PROCESSORS │
│ format, validate, merge into final YAML Jazz │
│ │
└─────────────────────────────────────────────────────────────────┘"不同的图像需要不同的工具。CLI 是流水线，不是单体应用。"
mine.py┌─────────────────────────────────────────────────────────────────┐
│ 分析器流水线 │
├─────────────────────────────────────────────────────────────────┤
│ │
│ 1. 预处理器 │
│ 调整大小、归一化、增强、格式转换 │
│ │
│ 2. 自定义分析器（并行或串行运行） │
│ ├── 姿态检测（MediaPipe、OpenPose） │
│ ├── 物体检测（YOLO、Detectron2） │
│ ├── OCR 提取（Tesseract、PaddleOCR） │
│ ├── 人脸分析（表情、人口统计学特征） │
│ └── leela 客户模型（你训练的自定义模型！） │
│ │
│ 3. LLM 视觉处理 │
│ 接收所有之前的处理结果作为上下文 │
│ 合成语义解读 │
│ │
│ 4. 后处理器 │
│ 格式化、校验、合并为最终的 YAML Jazz 输出 │
│ │
└─────────────────────────────────────────────────────────────────┘Example: Multi-Analyzer Pipeline
示例：多分析器流水线
bash
mine.py fashion-shoot.jpg \
--analyzer pose-detection \
--analyzer face-analysis \
--analyzer leela://acme/gesture-classifier \
--depth philosophicalThis runs:
- pose-detection — Extracts body keypoints, gesture classification
- face-analysis — Detects expressions, demographics
- leela://acme/gesture-classifier — Customer's trained model from Leela registry
- LLM vision — Gets ALL the above as context, synthesizes final interpretation
bash
mine.py fashion-shoot.jpg \
--analyzer pose-detection \
--analyzer face-analysis \
--analyzer leela://acme/gesture-classifier \
--depth philosophical这个命令会运行：
- 姿态检测 — 提取人体关键点、手势分类
- 人脸分析 — 检测表情、人口统计学特征
- leela://acme/gesture-classifier — 来自 Leela 注册表的客户训练模型
- LLM 视觉处理 — 接收以上所有结果作为上下文，合成最终解读
Leela Customer Models
Leela 客户模型
Pull customer-specific models trained on the Leela platform:
bash
undefined拉取在 Leela 平台上训练的客户专属模型：
bash
undefinedFrom Leela model registry
从 Leela 模型注册表拉取
mine.py widget-photo.jpg --analyzer leela://customer-id/defect-detector-v3
mine.py widget-photo.jpg --analyzer leela://customer-id/defect-detector-v3
Local model file
本地模型文件
mine.py widget-photo.jpg --analyzer ./models/my-classifier.pt
Output merges into the mining YAML:
```yaml
leela_analysis:
model: "acme-widget-defect-v3"
customer: "acme-corp"
detections:
- class: "hairline_crack"
confidence: 0.91
severity: "minor"
location: "top_left_quadrant"mine.py widget-photo.jpg --analyzer ./models/my-classifier.pt
输出会合并到开采 YAML 中：
```yaml
leela_analysis:
model: "acme-widget-defect-v3"
customer: "acme-corp"
detections:
- class: "hairline_crack"
confidence: 0.91
severity: "minor"
location: "top_left_quadrant"Adding Your Own Analyzer
添加自定义分析器
python
undefinedpython
undefinedanalyzers/my_analyzer.py
analyzers/my_analyzer.py
def analyze(image_path: str, config: dict) -> dict:
"""Run analysis, return structured data for YAML output."""
# Your model inference here
return {
"my_analysis": {
"detected": ["thing1", "thing2"],
"confidence": 0.95
}
}
def can_handle(image_path: str, context: dict) -> bool:
"""Return True if this analyzer should run on this image."""
# Auto-detect logic, or return False for explicit-only
return "manufacturing" in context.get("tags", [])
Register in `analyzers/registry.yml`:
```yaml
analyzers:
my-analyzer:
module: "analyzers.my_analyzer"
auto-detect: true
requires: ["torch", "my-model-package"]def analyze(image_path: str, config: dict) -> dict:
"""Run analysis, return structured data for YAML output."""
# 你的模型推理逻辑
return {
"my_analysis": {
"detected": ["thing1", "thing2"],
"confidence": 0.95
}
}
def can_handle(image_path: str, context: dict) -> bool:
"""Return True if this analyzer should run on this image."""
# 自动检测逻辑，或者返回 false 表示仅显式调用时运行
return "manufacturing" in context.get("tags", [])
在 `analyzers/registry.yml` 中注册：
```yaml
analyzers:
my-analyzer:
module: "analyzers.my_analyzer"
auto-detect: true
requires: ["torch", "my-model-package"]Why Pipeline Beats Monolith
为什么流水线优于单体架构
| Approach | Pros | Cons |
|---|---|---|
| Monolith | Simple | Can't add domain models |
| Pipeline | Extensible, composable | Slightly more complex |
The LLM is great at semantic synthesis, but it can't run your custom pose detection model. The pipeline lets each tool do what it's best at:
- Custom models → Precise detection, trained on your data
- LLM vision → Semantic interpretation, narrative synthesis
- Together → The best of both worlds
| 方案 | 优点 | 缺点 |
|---|---|---|
| 单体架构 | 简单 | 无法添加领域专属模型 |
| 流水线 | 可扩展、可组合 | 稍微复杂一点 |
LLM 擅长语义合成，但它无法运行你自定义的姿态检测模型。流水线让每个工具做它最擅长的事：
- 自定义模型 → 精准检测，基于你的数据训练
- LLM 视觉 → 语义解读、叙事合成
- 两者结合 → 优势互补
YAML Jazz Output Style
YAML Jazz 输出风格
"Comments are SEMANTIC DATA, not just documentation!"
YAML Jazz is the output format for mining results. Structure provides the backbone; comments provide the insight.
"注释是语义数据，不只是文档！"
YAML Jazz 是开采结果的输出格式。结构提供骨架，注释提供洞见。
The Rules
规则
- COMMENT LIBERALLY — Every insight deserves a note
- Inline comments for quick observations
- fields for longer thoughts
notes: - Capture confidence, hunches, metaphors
- Think out loud — the reader benefits from your reasoning
- 大量添加注释 — 每个洞见都值得记录
- 行内注释 用于快速标注观察结果
- 字段 用于存储更长的思考内容
notes: - 记录置信度、预感、隐喻
- 清晰展示思考过程 — 读者会从你的推理中获益
Example Output
输出示例
yaml
undefinedyaml
undefinedMining results for treasure-room.jpg
Mining results for treasure-room.jpg
Depth: full | Provider: openai/gpt-4o
Depth: full | Provider: openai/gpt-4o
resources:
gold:
quantity: 150 # Piled in mounds — not scattered, PLACED
confidence: 0.85 # Torchlight glints clearly off the metal
notes: |
Mix of Roman denarii and medieval florins. Centuries of
accumulation. This isn't a king's orderly treasury — this is
a thieves' hoard. Generations of stolen wealth, piled and
forgotten. The dust layer says nobody's touched it in ages.
danger:
intensity: 0.7 # Not immediate, but PRESENT
confidence: 0.75 # Hard to see into the corners
sources:
- "Skeleton in corner — previous seeker, didn't make it"
- "Shadows too dark for natural torchlight — something absorbs"
- "Dust undisturbed except ONE trail — something still comes here"
notes: "This hoard is guarded. Or cursed. Probably both."
nostalgia:
intensity: 0.4 # Whisper of lost civilizations
confidence: 0.6 # Subjective, but the coins evoke it
notes: "Who were they? Where did this come from? All gone now."
dominant_colors:
- name: "treasure-gold"
hex: "#FFD700"
coverage: 0.4 # Catches the eye first — that's the point
- name: "shadow-purple"
hex: "#2D1B4E"
coverage: 0.3 # Where the danger lives
implied_smells:
- dust # Centuries of it
- old metal # Copper, bronze, the tang of coins
- something rotting # Not recent, but not ancient either
exhausted: false
mining_notes: |
Rich lode for material and philosophical mining.
The image is ABOUT greed and its costs. The skeleton says everything.
Meta-observation: This image wants to be a warning.
"Here lies what you seek — and what happens when you find it."
undefinedresources:
gold:
quantity: 150 # 成堆堆放，不是散落的，是被刻意放置的
confidence: 0.85 # 火炬光在金属上的反光很清晰
notes: |
混合了罗马第纳尔银币和中世纪弗罗林金币，是几个世纪的积累。这不是国王有序的宝库，而是盗贼的藏货。几代人偷来的财富，堆积在这里被遗忘。灰尘的厚度说明已经很久没人碰过了。
danger:
intensity: 0.7 # 不是迫在眉睫的危险，但确实存在
confidence: 0.75 # 很难看清角落的情况
sources:
- "角落里的骷髅 — 之前的寻宝者，没能成功离开"
- "阴影太暗，不符合正常火炬光的效果 — 有东西在吸收光线"
- 除了一条痕迹外灰尘都没有被扰动 — 还有东西会来这里
notes: "这批宝藏有守卫，或者被诅咒了，很可能两者都是。"
nostalgia:
intensity: 0.4 # 失落文明的低语
confidence: 0.6 # 比较主观，但钱币确实唤起了这种感觉
notes: "他们是谁？这些财富来自哪里？现在都消失了。"
dominant_colors:
- name: "treasure-gold"
hex: "#FFD700"
coverage: 0.4 # 首先吸引注意力，这就是设计的目的
- name: "shadow-purple"
hex: "#2D1B4E"
coverage: 0.3 # 危险潜藏的地方
implied_smells:
- dust # 积累了几个世纪的灰尘
- old metal # 铜、青铜，钱币的味道
- something rotting # 不是最近的，但也不是远古的
exhausted: false
mining_notes: |
适合物质和哲学层面的深度开采。
这张图像的核心是贪婪及其代价，骷髅已经说明了一切。
元观察：这张图像想成为一个警告
"这里有你寻找的东西 — 以及找到它之后的下场。"
undefinedWhy Comments Matter
注释的重要性
An uncommented extraction is like a song without soul. The best mining results read like poetry annotated by a geologist.
When you mine, capture:
- Why you estimated that quantity
- What visual cues led to this inference
- What's uncertain, what surprised you
- Metaphors that capture the essence
没有注释的提取结果就像没有灵魂的歌曲。最好的开采结果读起来就像地质学家标注的诗歌。
开采时，请记录：
- 你估算数量的依据
- 哪些视觉线索引导你得出这个推论
- 不确定的内容，以及让你惊讶的内容
- 能抓住本质的隐喻
How Mining Works
开采的工作原理
Step 1: ANALYZE (LLM scans for resources)
步骤 1：分析（LLM 扫描寻找资源）
The LLM looks at the image AND checks what resources are currently requested by the logistics network:
yaml
analyze:
image: "treasure-room.jpg"
# LLM knows what's NEEDED from logistics requesters
logistics_context:
active_requests:
- { item: "gold", requester: "forge/", needed: 100 }
- { item: "gems", requester: "jewelry-shop/", needed: 50 }
- { item: "iron-ore", requester: "smelter/", needed: 200 }
# LLM identifies what CAN BE MINED that matches requests
analysis_prompt: |
Look at this image. What resources can you identify?
Prioritize resources that match these requests: {requests}
For each resource, estimate quantity available.LLM 查看图像，同时检查物流网络当前请求的资源：
yaml
analyze:
image: "treasure-room.jpg"
# LLM 知道物流请求方需要什么资源
logistics_context:
active_requests:
- { item: "gold", requester: "forge/", needed: 100 }
- { item: "gems", requester: "jewelry-shop/", needed: 50 }
- { item: "iron-ore", requester: "smelter/", needed: 200 }
# LLM 识别可以开采且匹配请求的资源
analysis_prompt: |
Look at this image. What resources can you identify?
Prioritize resources that match these requests: {requests}
For each resource, estimate quantity available.Step 2: INSTANTIATE (Resource map attached to image)
步骤 2：实例化（资源映射附加到图像上）
The LLM returns a resource mapping that gets stored ON the image:
yaml
image:
id: "treasure-room-photo"
file: "treasure-room.jpg"
type: mineable-image
# RESOURCE MAP (instantiated by LLM analysis)
resources:
gold:
total: 150 # Total available
remaining: 150 # Not yet mined
per_turn: 10 # Can extract 10 per turn
gems:
total: 45
remaining: 45
per_turn: 5
ancient-coins:
total: 30
remaining: 30
per_turn: 3
rare: true # Bonus find!
dust:
total: 500
remaining: 500
per_turn: 50
value: low
# Metadata
analyzed_at: "2026-01-10T14:30:00Z"
exhausted: falseLLM 返回资源映射，存储在图像元数据中：
yaml
image:
id: "treasure-room-photo"
file: "treasure-room.jpg"
type: mineable-image
# 资源映射（由 LLM 分析生成）
resources:
gold:
total: 150 # 总可用量
remaining: 150 # 未开采量
per_turn: 10 # 每轮可开采 10 个
gems:
total: 45
remaining: 45
per_turn: 5
ancient-coins:
total: 30
remaining: 30
per_turn: 3
rare: true # 稀有发现！
dust:
total: 500
remaining: 500
per_turn: 50
value: low
# 元数据
analyzed_at: "2026-01-10T14:30:00Z"
exhausted: falseStep 3: MINE (Progressive extraction, N per turn)
步骤 3：开采（逐步提取，每轮 N 个）
Each turn, you can mine resources from the image:
yaml
action: MINE
target: "treasure-room-photo"每轮你可以从图像中开采资源：
yaml
action: MINE
target: "treasure-room-photo"This turn's extraction (limited by per_turn rates)
本轮开采结果（受每轮开采上限限制）
result:
extracted:
- item: gold
quantity: 10 # per_turn limit
destination: "forge/"
- item: gems
quantity: 5
destination: "jewelry-shop/"
Image state updated
image_state:
resources:
gold:
remaining: 140 # Was 150, mined 10
gems:
remaining: 40 # Was 45, mined 5
exhausted: false
undefinedresult:
extracted:
- item: gold
quantity: 10 # 每轮上限
destination: "forge/"
- item: gems
quantity: 5
destination: "jewelry-shop/"
图像状态已更新
image_state:
resources:
gold:
remaining: 140 # 之前是 150，开采了 10
gems:
remaining: 40 # 之前是 45，开采了 5
exhausted: false
undefinedStep 4: EXHAUSTION (Sucked dry!)
步骤 4：枯竭（被开采殆尽！）
After enough mining turns, resources run out:
yaml
undefined经过足够多轮的开采后，资源会耗尽：
yaml
undefinedAfter 15 turns of mining gold...
开采 15 轮黄金后...
image_state:
resources:
gold:
total: 150
remaining: 0 # EXHAUSTED!
per_turn: 10
exhausted: true
gems:
total: 45
remaining: 0 # EXHAUSTED!
per_turn: 5
exhausted: true
ancient-coins:
total: 30
remaining: 0
per_turn: 3
exhausted: true
exhausted: true # Whole image sucked dry!
Narrative
description: |
The treasure room photo has been thoroughly mined.
Every glinting surface has been extracted, every
coin accounted for. The image looks... drained.
Faded. Like a photocopy of a photocopy.
**Once exhausted, you can't mine that image anymore!**
---
---image_state:
resources:
gold:
total: 150
remaining: 0 # 已枯竭！
per_turn: 10
exhausted: true
gems:
total: 45
remaining: 0 # 已枯竭！
per_turn: 5
exhausted: true
ancient-coins:
total: 30
remaining: 0
per_turn: 3
exhausted: true
exhausted: true # 整张图像已被完全开采！
叙事描述
description: |
藏宝室的照片已经被彻底开采。每一处闪光的表面都被提取，每一枚钱币都被清点。这张图像看起来... 失去了活力，褪色了，就像复印件的复印件。
**一旦枯竭，你就无法再开采这张图像了！**
---
---Demand-Driven Discovery
需求驱动的发现
The LLM prioritizes what the logistics network NEEDS!
yaml
undefinedLLM 会优先寻找物流网络需要的资源！
yaml
undefinedThe smelter is requesting iron ore
冶炼厂请求铁矿石
logistic-container:
id: smelter
mode: requester
request_list:
- { item: "iron-ore", count: 200, priority: high }
- { item: "coal", count: 100, priority: medium }
logistic-container:
id: smelter
mode: requester
request_list:
- { item: "iron-ore", count: 200, priority: high }
- { item: "coal", count: 100, priority: medium }
Player takes a photo of a cave wall
玩家拍摄了洞穴壁的照片
LLM analyzes and finds:
LLM 分析后发现：
analysis:
image: "cave-wall.jpg"
found_resources:
iron-ore: 80 # "I see iron ore veins! The smelter needs this!"
copper-ore: 30 # Also present but not requested
quartz: 50 # Background mineral
cave-moss: 100 # Organic material
priority_matching:
- resource: iron-ore
matches_request: true
requester: "smelter/"
highlight: "⭐ HIGH PRIORITY — Smelter needs this!"
The LLM acts as a **smart prospector** that knows what's valuable based on current demand!analysis:
image: "cave-wall.jpg"
found_resources:
iron-ore: 80 # "我看到了铁矿脉！冶炼厂需要这个！"
copper-ore: 30 # 也存在，但没有被请求
quartz: 50 # 背景矿物
cave-moss: 100 # 有机材料
priority_matching:
- resource: iron-ore
matches_request: true
requester: "smelter/"
highlight: "⭐ 高优先级 — 冶炼厂需要这个！"
LLM 就像**智能探矿者**，会根据当前需求判断什么资源有价值！Discovery Modes
发现模式
| Mode | What LLM Looks For |
|---|---|
| Only resources with active requests |
| Requested resources + valuable extras |
| Everything mineable in the image |
| Abstract concepts, emotions, meanings |
yaml
mine:
target: "sunset-beach.jpg"
mode: philosophical
# LLM finds abstract resources
resources:
nostalgia: 15
warmth: 30
passage-of-time: 5
beauty: 20
sand: 10000 # Also the literal stuff| 模式 | LLM 寻找的内容 |
|---|---|
| 仅查找有活跃请求的资源 |
| 请求的资源 + 有价值的额外资源 |
| 图像中所有可开采的内容 |
| 抽象概念、情绪、意义 |
yaml
mine:
target: "sunset-beach.jpg"
mode: philosophical
# LLM 发现抽象资源
resources:
nostalgia: 15
warmth: 30
passage-of-time: 5
beauty: 20
sand: 10000 # 也包括实体资源Mining Yields
开采产出
Different image types yield different resources:
不同类型的图像产出不同的资源：
🏔️ Natural Resources
🏔️ 自然资源
| Image Type | Yields |
|---|---|
| Ore vein | |
| Forest | |
| Ocean | |
| Mountain | |
| Desert | |
| Sky | |
| 图像类型 | 产出 |
|---|---|
| 矿脉 | |
| 森林 | |
| 海洋 | |
| 山地 | |
| 沙漠 | |
| 天空 | |
🏛️ Constructed
🏛️ 人造物品
| Image Type | Yields |
|---|---|
| Building | |
| Machinery | |
| Treasure pile | |
| Library | |
| 图像类型 | 产出 |
|---|---|
| 建筑 | |
| 机械 | |
| 宝藏堆 | |
| 图书馆 | |
🎨 Abstract/Artistic
🎨 抽象/艺术
| Image Type | Yields |
|---|---|
| Sunset | |
| Portrait | |
| Abstract art | |
| Text/writing | |
| 图像类型 | 产出 |
|---|---|
| 日落 | |
| 肖像 | |
| 抽象艺术 | |
| 文本/写作 | |
🌌 Philosophical (Deep Mining)
🌌 哲学层面（深度开采）
Just like the Kitchen Counter goes from → → → :
practicalchemicalatomicphilosophical| Depth | What You Mine |
|---|---|
| Surface | Objects, materials |
| Deep | Emotions, concepts |
| Sensations | Colors, smells, attitudes, feelings |
| Quantum | Probabilities, observations |
| Philosophical | Meaning, existence, narrative |
yaml
deep_mining:
target: "sunset.png"
depth: philosophical
yields:
- item: "the-passage-of-time"
quantity: 1
type: abstract
- item: "mortality-awareness"
quantity: 1
type: existential
warning: "This may cause introspection"
- item: "beauty-that-fades"
quantity: 1
type: poetic就像 Kitchen Counter 可以从 → → → 层级拆解一样：
实用化学原子哲学| 深度 | 开采内容 |
|---|---|
| 表层 | 物体、材料 |
| 深层 | 情绪、概念 |
| 感知层 | 颜色、气味、态度、感受 |
| 量子层 | 概率、观察结果 |
| 哲学层 | 意义、存在、叙事 |
yaml
deep_mining:
target: "sunset.png"
depth: philosophical
yields:
- item: "the-passage-of-time"
quantity: 1
type: abstract
- item: "mortality-awareness"
quantity: 1
type: existential
warning: "This may cause introspection"
- item: "beauty-that-fades"
quantity: 1
type: poetic🎨 Sensation Mining
🎨 感知开采
Extract colors, smells, textures, moods:
yaml
sensation_mining:
target: "farmers-market.jpg"
depth: sensations
yields:
# Colors
- item: "tomato-red"
quantity: 40
type: color
hex: "#FF6347"
- item: "basil-green"
quantity: 25
type: color
hex: "#228B22"
# Smells (imagined from visual cues)
- item: "fresh-bread-aroma"
quantity: 10
type: smell
intensity: warm
- item: "ripe-fruit-sweetness"
quantity: 30
type: smell
# Attitudes/Feelings
- item: "weekend-morning-calm"
quantity: 5
type: attitude
- item: "abundance"
quantity: 20
type: feeling
# Textures
- item: "rough-burlap"
quantity: 15
type: texture
- item: "sun-warmed-wood"
quantity: 8
type: textureUse these in crafting:
- Combine +
tomato-red→ painted artworkcanvas - Combine +
fresh-bread-aroma→ ambiance modifierroom - Combine +
weekend-morning-calm→ mood buffcharacter
提取颜色、气味、纹理、情绪：
yaml
sensation_mining:
target: "farmers-market.jpg"
depth: sensations
yields:
# 颜色
- item: "tomato-red"
quantity: 40
type: color
hex: "#FF6347"
- item: "basil-green"
quantity: 25
type: color
hex: "#228B22"
# 气味（从视觉线索推断）
- item: "fresh-bread-aroma"
quantity: 10
type: smell
intensity: warm
- item: "ripe-fruit-sweetness"
quantity: 30
type: smell
# 态度/感受
- item: "weekend-morning-calm"
quantity: 5
type: attitude
- item: "abundance"
quantity: 20
type: feeling
# 纹理
- item: "rough-burlap"
quantity: 15
type: texture
- item: "sun-warmed-wood"
quantity: 8
type: texture可用于合成：
- 组合 +
tomato-red→ 绘画作品canvas - 组合 +
fresh-bread-aroma→ 氛围修改器room - 组合 +
weekend-morning-calm→ 情绪增益character
The Mineable Property
可开采属性
Any object or image can have a property:
mineableyaml
object:
name: Ancient Ore Painting
type: artwork
description: |
A painting of a rich ore vein. But wait...
is that actual ore embedded in the canvas?
mineable:
enabled: true
yields:
- item: iron-ore
quantity: [5, 15] # Range: 5-15 per mine
- item: copper-ore
quantity: [2, 8]
- item: artistic-essence
quantity: 1
rare: 0.3 # 30% chance
exhaustion:
max_mines: 3 # Can mine 3 times before exhausted
diminishing: 0.5 # Each mine yields 50% less
regenerates: false # Once exhausted, stays exhausted
side_effects:
- "The painting fades slightly with each extraction"
- "You feel the artist's disappointment"任何物体或图像都可以有 属性：
mineableyaml
object:
name: Ancient Ore Painting
type: artwork
description: |
一幅描绘富饶矿脉的画作。但等等……画布上是不是嵌了真正的矿石？
mineable:
enabled: true
yields:
- item: iron-ore
quantity: [5, 15] # 范围：每次开采 5-15 个
- item: copper-ore
quantity: [2, 8]
- item: artistic-essence
quantity: 1
rare: 0.3 # 30% 概率出现
exhaustion:
max_mines: 3 # 最多可开采 3 次，之后枯竭
diminishing: 0.5 # 每次开采产量减半
regenerates: false # 一旦枯竭，不会恢复
side_effects:
- "每次开采后画作会稍微褪色"
- "你能感受到艺术家的失望"Mining Tools
开采工具
Different tools affect mining yields:
不同的工具会影响开采产出：
📷 Camera (Default)
📷 相机（默认）
yaml
tool: camera
efficiency: 1.0
specialty: "Captures visual resources"
can_mine: [images, scenes, visible_objects]yaml
tool: camera
efficiency: 1.0
specialty: "Captures visual resources"
can_mine: [images, scenes, visible_objects]🔬 Analyzer
🔬 分析器
yaml
tool: analyzer
efficiency: 1.5
specialty: "Chemical/atomic resources"
can_mine: [materials, substances, compounds]yaml
tool: analyzer
efficiency: 1.5
specialty: "Chemical/atomic resources"
can_mine: [materials, substances, compounds]🔮 Oracle Eye
🔮 神谕之眼
yaml
tool: oracle_eye
efficiency: 2.0
specialty: "Abstract/philosophical resources"
can_mine: [emotions, concepts, meanings, futures]yaml
tool: oracle_eye
efficiency: 2.0
specialty: "Abstract/philosophical resources"
can_mine: [emotions, concepts, meanings, futures]⛏️ Reality Pickaxe
⛏️ 现实镐
yaml
tool: reality_pickaxe
efficiency: 3.0
specialty: "Everything, but dangerous"
can_mine: [anything]
warning: "May collapse local reality"yaml
tool: reality_pickaxe
efficiency: 3.0
specialty: "Everything, but dangerous"
can_mine: [anything]
warning: "May collapse local reality"Integration with Logistics
与物流系统集成
Mined resources flow into the logistics system:
yaml
mining_config:
default_destination: "inventory"
routing:
# Route by resource type
- match: { tags: ["ore"] }
destination: "nw/ore-storage/"
- match: { tags: ["organic"] }
destination: "ne/organic-materials/"
- match: { tags: ["abstract"] }
destination: "sw/concepts/"
postal_delivery:
enabled: true
method: text # Instant delivery!开采的资源会流入物流系统：
yaml
mining_config:
default_destination: "inventory"
routing:
# 按资源类型路由
- match: { tags: ["ore"] }
destination: "nw/ore-storage/"
- match: { tags: ["organic"] }
destination: "ne/organic-materials/"
- match: { tags: ["abstract"] }
destination: "sw/concepts/"
postal_delivery:
enabled: true
method: text # 即时交付！Camera Phone Integration
手机相机集成
Your phone camera is THE mining interface:
你的手机相机就是开采接口：
Real Photo Workflow
真实照片工作流
yaml
phone_mining:
# 1. CAPTURE: Take photo or upload
capture:
sources:
- camera: "Take new photo"
- gallery: "Upload from camera roll"
- url: "Import from web"
# 2. ANALYZE: LLM scans for resources
on_capture:
action: analyze
context: logistics_requests # What's needed?
show_preview: true
# 3. CONFIRM: Accept resource mapping
on_confirm:
action: instantiate
attach_resources: true # Store on image
# 4. MINE: Extract over time
on_mine:
per_turn: true # N resources per turn
auto_route: logistics # Send to requestersyaml
phone_mining:
# 1. 捕获：拍照或上传
capture:
sources:
- camera: "Take new photo"
- gallery: "Upload from camera roll"
- url: "Import from web"
# 2. 分析：LLM 扫描寻找资源
on_capture:
action: analyze
context: logistics_requests # 需要什么资源？
show_preview: true
# 3. 确认：接受资源映射
on_confirm:
action: instantiate
attach_resources: true # 存储到图像元数据
# 4. 开采：逐步提取
on_mine:
per_turn: true # 每轮开采 N 个资源
auto_route: logistics # 发送给请求方Example: Photo Mining Flow
示例：照片开采流程
1. You take a photo of a rock formation:
📷 *snap*
Analyzing photo for mineable resources...
Checking logistics requests...
Found in image:
├── 🪨 granite × 200 (10/turn)
├── �ite iron-ore × 45 (5/turn) ⭐ NEEDED by smelter!
├── 💎 quartz × 12 (2/turn)
└── 🦎 fossil × 1 (rare find!)
[MINE] [CANCEL]2. You confirm. Resource map attached:
yaml
image:
id: rock-formation-001
file: "IMG_2847.jpg"
resources:
granite: { total: 200, remaining: 200, per_turn: 10 }
iron-ore: { total: 45, remaining: 45, per_turn: 5 }
quartz: { total: 12, remaining: 12, per_turn: 2 }
fossil: { total: 1, remaining: 1, per_turn: 1 }3. Each turn, you mine:
Turn 1: Mined 10 granite, 5 iron-ore, 2 quartz
→ Iron ore sent to smelter (requester)
→ Granite sent to storage
Turn 2: Mined 10 granite, 5 iron-ore, 2 quartz
Remaining: granite 180, iron-ore 35, quartz 8
...
Turn 9: Mined 10 granite, 5 iron-ore (last 5!)
⚠️ Iron-ore EXHAUSTED
Turn 20: Mined last 10 granite
📷 IMAGE FULLY MINED — no more resources!4. Exhausted image:
yaml
image:
id: rock-formation-001
exhausted: true
visual_effect: |
The photo appears faded, almost translucent.
Like the minerals were literally pulled out of it.
A ghost of a photograph.1. 你拍摄了一张岩层的照片：
📷 *咔嚓*
正在分析照片中的可开采资源...
正在检查物流请求...
在图像中发现：
├── 🪨 花岗岩 × 200 (10/轮)
├── ⚫ 铁矿石 × 45 (5/轮) ⭐ 冶炼厂需要！
├── 💎 石英 × 12 (2/轮)
└── 🦎 化石 × 1 (稀有发现！)
[开采] [取消]2. 你确认后，资源映射被附加到图像：
yaml
image:
id: rock-formation-001
file: "IMG_2847.jpg"
resources:
granite: { total: 200, remaining: 200, per_turn: 10 }
iron-ore: { total: 45, remaining: 45, per_turn: 5 }
quartz: { total: 12, remaining: 12, per_turn: 2 }
fossil: { total: 1, remaining: 1, per_turn: 1 }3. 每轮你可以开采：
第 1 轮：开采了 10 花岗岩、5 铁矿石、2 石英
→ 铁矿石发送给冶炼厂（请求方）
→ 花岗岩发送到仓库
第 2 轮：开采了 10 花岗岩、5 铁矿石、2 石英
剩余：花岗岩 180、铁矿石 35、石英 8
...
第 9 轮：开采了 10 花岗岩、5 铁矿石（最后 5 个！）
⚠️ 铁矿石已枯竭
第 20 轮：开采了最后 10 花岗岩
📷 图像已完全开采 — 无剩余资源！4. 枯竭的图像：
yaml
image:
id: rock-formation-001
exhausted: true
visual_effect: |
照片看起来褪色了，几乎是半透明的。就像矿物真的被从里面抽出来了一样，是照片的幽灵。AR Overlay (Future)
AR 叠加（未来功能）
yaml
ar_overlay:
# Point camera at scene
live_view:
show_resources: true
icons_float: true
# Visual indicators
indicators:
- resource_type: "icon + label"
- quantity: "number overlay"
- priority: "⭐ for requested items"
- exhaustion: "fade as mined"
# Example view:
# 🪨 200 ⚫ 45 ⭐ 💎 12
# (floating over rock formation)yaml
ar_overlay:
# 相机对准场景
live_view:
show_resources: true
icons_float: true
# 视觉指示器
indicators:
- resource_type: "icon + label"
- quantity: "number overlay"
- priority: "⭐ 标记请求的物品"
- exhaustion: "开采后逐渐褪色"
# 示例视图：
# 🪨 200 ⚫ 45 ⭐ 💎 12
# （浮动在岩层上方）DECOMPOSE vs MINE
DECOMPOSE vs MINE
| DECOMPOSE (Counter) | MINE (Camera) |
|---|---|
| Physical items | Images, scenes, visuals |
| Requires counter | Requires camera/tool |
| Consumes item | May or may not consume |
| Returns components | Returns resources |
| Kitchen-focused | World-focused |
They're complementary!
- DECOMPOSE the physical object on the counter
- MINE the image/representation of anything
| DECOMPOSE（操作台） | MINE（相机） |
|---|---|
| 实体物品 | 图像、场景、视觉内容 |
| 需要操作台 | 需要相机/工具 |
| 消耗物品 | 可能消耗也可能不消耗 |
| 返回组件 | 返回资源 |
| 聚焦厨房场景 | 聚焦整个世界 |
它们是互补的！
- DECOMPOSE 操作台上的实体物品
- MINE 任何事物的图像/表示
Reality Mining (Advanced)
现实开采（高级功能）
At the deepest level, you're not just mining images — you're mining reality itself:
yaml
reality_mining:
level: transcendent
# The image IS the territory
insight: |
When you mine an image, you're extracting
compressed information. But all reality is
compressed information. Images are just
explicit about it.
implications:
- "Mining a photo of gold doesn't create gold — it REVEALS gold"
- "The ore was always there, encoded in the pixels"
- "Your camera doesn't capture reality — it DECOMPRESSES it"
warning: |
At this level, the distinction between
"mining an image" and "mining reality"
becomes philosophical.在最深的层级，你不只是在开采图像 — 你在开采现实本身：
yaml
reality_mining:
level: transcendent
# 图像就是 territory
insight: |
当你开采一张图像时，你提取的是压缩的信息。但所有现实都是压缩的信息，图像只是把这一点变得更明确而已。
implications:
- "开采黄金的照片不会创造黄金 — 它是在揭示黄金"
- "矿石一直都在，编码在像素里"
- "你的相机不是在捕获现实 — 它是在解压现实"
warning: |
在这个层级，"开采图像"和"开采现实"的区别已经变成哲学问题了。Actions
操作指令
MINE
MINE
MINE [target]
MINE [target] WITH [tool]
MINE [target] TO [destination]MINE [target]
MINE [target] WITH [tool]
MINE [target] TO [destination]SCAN
SCAN
SCAN [target] # Preview yields without mining
SCAN AREA # Scan visible area for mineable resourcesSCAN [target] # 预览产出，不实际开采
SCAN AREA # 扫描可见区域的可开采资源PROSPECT
PROSPECT
PROSPECT [direction] # Check for mineable resources in direction
PROSPECT DEEP # Deep scan for rare/hidden resourcesPROSPECT [direction] # 探查某个方向的可开采资源
PROSPECT DEEP # 深度扫描稀有/隐藏资源Example: Mining the Maze
示例：开采迷宫
yaml
undefinedyaml
undefinedPlayer in dark maze corridor
玩家在黑暗的迷宫走廊里
Takes photo with lamp light
用灯光照明拍摄照片
action: MINE "dark-corridor.png"
result:
yields:
- item: darkness
quantity: 100
type: abstract
note: "Bottled darkness, useful for stealth"
- item: fear
quantity: 15
type: emotion
note: "Crystallized fear, grue-adjacent"
- item: mystery
quantity: 5
type: narrative
note: "Pure narrative potential"
- item: stone-dust
quantity: 50
type: material
rare_find:
- item: "ancient-writing"
quantity: 1
note: "Hidden message in the shadows!"
unlocks: "Secret passage revealed"
---action: MINE "dark-corridor.png"
result:
yields:
- item: darkness
quantity: 100
type: abstract
note: "瓶装黑暗，适合潜行"
- item: fear
quantity: 15
type: emotion
note: "结晶化的恐惧，和 grue 类似"
- item: mystery
quantity: 5
type: narrative
note: "纯粹的叙事潜力"
- item: stone-dust
quantity: 50
type: material
rare_find:
- item: "ancient-writing"
quantity: 1
note: "阴影里的隐藏信息！"
unlocks: "Secret passage revealed"
---The Mining Economy
开采经济
Resources have value and flow:
yaml
resource_economy:
# Raw resources → processing → products
chains:
- ore → smelter → ingots → forge → tools
- wood → sawmill → planks → workshop → furniture
- images → mining → resources → crafting → items
# Images as a resource type!
image_value:
unique_photo: high # Original content
copy: low # Duplicated content
AI_generated: medium # Generated on demand
# Mining generates content
content_creation: |
When you MINE an image, you're not just extracting
resources — you're creating YAML files for them.
Each resource becomes a game object.资源有价值且会流动：
yaml
resource_economy:
# 原始资源 → 加工 → 产品
chains:
- ore → smelter → ingots → forge → tools
- wood → sawmill → planks → workshop → furniture
- images → mining → resources → crafting → items
# 图像本身就是一种资源类型！
image_value:
unique_photo: high # 原创内容
copy: low # 复制内容
AI_generated: medium # 按需生成
# 开采生成内容
content_creation: |
当你开采一张图像时，你不只是在提取资源 — 你还在为它们创建 YAML 文件。每个资源都会变成一个游戏对象。Dovetails With
关联模块
- Visualizer — Images to mine
- Slideshow — Present mined images as narratives
- Logistic Container — Resource storage
- Postal — Camera integration, delivery
- Kitchen Counter — DECOMPOSE pattern
- Adventure — World integration
- Visualizer — 待开采的图像
- Slideshow — 将开采后的图像展示为叙事内容
- Logistic Container — 资源存储
- Postal — 相机集成、交付
- Kitchen Counter — DECOMPOSE 模式
- Adventure — 世界集成
Character Recognition
人物识别
"Who's in the picture? Match against your cast list."
When mining images with known characters, the LLM matches visual features against character metadata.
"照片里是谁？和你的角色列表匹配。"
开采包含已知人物的图像时，LLM 会将视觉特征与人物元数据匹配。
How It Works
工作原理
- Load character files from directory
characters/ - Extract visual descriptors — species, clothing, accessories, typical poses
- Match against figures in the image
- Report confidence, pose, expression, interactions
- 加载 目录下的人物文件
characters/ - 提取视觉描述符 — 物种、服装、配饰、典型姿势
- 与图像中的人物匹配
- 报告置信度、姿势、表情、互动关系
Context Sources
上下文来源
- — character definitions with visual descriptors
characters/*.yml - — character cards with appearance
characters/*/CARD.yml - Room context — who's expected here?
- Prior mining — who was identified before?
- — 包含视觉描述符的人物定义
characters/*.yml - — 包含外观信息的人物卡片
characters/*/CARD.yml - 房间上下文 — 预期会出现谁？
- 过往开采记录 — 之前识别过谁？
Example Output
输出示例
yaml
characters_detected:
- id: palm
name: "Palm"
confidence: 0.95
location: "center-left"
pose: "seated at desk"
expression: "scholarly contentment"
accessories: ["tiny espresso", "typewriter"]
interacting_with: ["kittens", "biscuit"]
notes: "Matches Dutch Golden Age portrait style"
- id: marieke
name: "Marieke"
confidence: 0.92
location: "behind bar"
pose: "waving"
expression: "warm welcome"
accessories: ["apron with LEKKER text"]
- id: unknown-1
confidence: 0.0
location: "background-right"
description: "Figure in shadow, can't identify"
possible_matches: ["henk", "wumpus"]yaml
characters_detected:
- id: palm
name: "Palm"
confidence: 0.95
location: "center-left"
pose: "seated at desk"
expression: "scholarly contentment"
accessories: ["tiny espresso", "typewriter"]
interacting_with: ["kittens", "biscuit"]
notes: "Matches Dutch Golden Age portrait style"
- id: marieke
name: "Marieke"
confidence: 0.92
location: "behind bar"
pose: "waving"
expression: "warm welcome"
accessories: ["apron with LEKKER text"]
- id: unknown-1
confidence: 0.0
location: "background-right"
description: "Figure in shadow, can't identify"
possible_matches: ["henk", "wumpus"]Tips
提示
- Provide character files in context before mining
- Include signature accessories — Palm's espresso, Biscuit's collar
- Note relationships — who stands near whom
- Flag unknown figures for investigation
- Use or the
--depth characterslenscast-list
- 开采前提供上下文里的人物文件
- 包含标志性配饰 — Palm 的浓缩咖啡，Biscuit 的项圈
- 记录关系 — 谁站在谁附近
- 标记未知人物 以便后续调查
- 使用 或
--depth characters镜头cast-list
Multi-Look Mining
多视角开采
"One eye sees objects. Two eyes see depth. Many eyes see truth."
Multi-Look Mining layers interpretations from different perspectives, building up rich semantic sediment like geological strata. Each mining pass adds a new layer of meaning.
"一只眼看到物体，两只眼看到深度，很多只眼看到真相。"
多视角开采 将不同视角的解读分层整合，像地质地层一样积累丰富的语义沉淀。每次开采都会增加新的意义层。
The Technique
技术实现
yaml
undefinedyaml
undefinedLayer 1: OpenAI GPT-4o
第一层：OpenAI GPT-4o
Focus: General resource extraction
聚焦：通用资源提取
layer_1_openai:
miner: "gpt-4o"
focus: "objects, materials, colors, mood"
findings:
atmosphere: { intensity: 0.8 }
objects: { quantity: 10 }
# ... general observations ...
layer_1_openai:
miner: "gpt-4o"
focus: "objects, materials, colors, mood"
findings:
atmosphere: { intensity: 0.8 }
objects: { quantity: 10 }
# ... 通用观察结果 ...
Layer 2: Claude (Cursor built-in)
第二层：Claude（Cursor 内置）
Focus: Character expression, cultural markers, narrative POV
聚焦：人物表情、文化标记、叙事视角
layer_2_cursor_claude:
miner: "claude-opus-4"
focus: "character-expression, cultural-markers, narrative-pov"
what_layer_1_missed:
- "The SECOND cat on the windowsill"
- "The apron text is Dutch (LEKKER)"
- "The espresso cup is monkey-sized (intentional)"
deeper_resonance:
theme: "home is where they wave when you walk in"
layer_2_cursor_claude:
miner: "claude-opus-4"
focus: "character-expression, cultural-markers, narrative-pov"
what_layer_1_missed:
- "窗台上的第二只猫"
- "围裙上的文字是荷兰语（LEKKER）"
- "浓缩咖啡杯是猴子尺寸的，是故意设计的"
deeper_resonance:
theme: "home is where they wave when you walk in"
Layer 3: Gemini
第三层：Gemini
Focus: Art historical references, compositional analysis
聚焦：艺术史参考、构图分析
layer_3_gemini:
miner: "gemini-pro-vision"
focus: "art-history, composition, color-theory"
... yet another perspective ...
undefinedlayer_3_gemini:
miner: "gemini-pro-vision"
focus: "art-history, composition, color-theory"
... 另一个视角的结果 ...
undefinedWhy Multi-Look Works
多视角开采的优势
Different LLMs — and different PROMPTS to the same LLM — notice different things:
| Miner | Strengths | Typical Focus |
|---|---|---|
| OpenAI GPT-4o | General coverage | Objects, counts, colors |
| Claude | Nuance, context | Expression, culture, narrative |
| Gemini | Technical | Composition, art history |
| Human | Domain expertise | What MATTERS to the use case |
The sum is greater than the parts. Each layer adds perspectives the others missed.
不同的 LLM — 甚至同一个 LLM 搭配不同的提示词 — 会注意到不同的内容：
| 开采者 | 优势 | 典型聚焦点 |
|---|---|---|
| OpenAI GPT-4o | 全面覆盖 | 物体、数量、颜色 |
| Claude | 细节、上下文 | 表情、文化、叙事 |
| Gemini | 技术性 | 构图、艺术史 |
| 人类 | 领域专业知识 | 对使用场景重要的内容 |
整体大于部分之和。 每个层级都补充了其他层级遗漏的视角。
The Paintbrush Metaphor
画笔隐喻
Think of multi-look mining like painting in layers:
┌─────────────────────────────────────────────────────────────────┐
│ IMAGE INTERPRETATION │
├─────────────────────────────────────────────────────────────────┤
│ Layer N+1 → Specialized focus (your choice) │
│ Layer N → New questions raised by Layer N-1 │
│ ... │
│ Layer 3 → Art history, composition │
│ Layer 2 → Character, culture, narrative │
│ Layer 1 → Objects, materials, basic resources │
│ ───────────────────────────────────────────────────────────── │
│ ORIGINAL IMAGE │
└─────────────────────────────────────────────────────────────────┘Each pass reads the PREVIOUS layers before adding its own. The new miner knows what's already been noticed, so it can focus on what's missing or offer alternative interpretations.
可以把多视角开采想象成分层绘画：
┌─────────────────────────────────────────────────────────────────┐
│ 图像解读 │
├─────────────────────────────────────────────────────────────────┤
│ 第 N+1 层 → 专属聚焦（你可以自定义） │
│ 第 N 层 → 第 N-1 层提出的新问题 │
│ ... │
│ 第 3 层 → 艺术史、构图 │
│ 第 2 层 → 人物、文化、叙事 │
│ 第 1 层 → 物体、材料、基础资源 │
│ ───────────────────────────────────────────────────────────── │
│ 原始图像 │
└─────────────────────────────────────────────────────────────────┘每次开采都会先读取之前的层级，再添加自己的内容。新的开采者知道已经发现了什么，所以可以专注于缺失的内容或者提供替代解读。
Multi-Look Protocol
多视角协议
When mining an image with multi-look:
- Read existing mining data (if any)
- Choose your focus — what perspective will you add?
- Look at the image with that lens
- Note what prior layers missed — explicitly!
- Add your layer with clear attribution
- Suggest next focus — what should Layer N+1 examine?
使用多视角开采图像时：
- 读取现有开采数据（如果有）
- 选择你的聚焦点 — 你要添加什么视角？
- 带着这个视角查看图像
- 明确标注之前层级遗漏的内容
- 添加你的层级，并明确归属
- 建议下一个聚焦点 — 第 N+1 层应该检查什么？
Focus Lenses
聚焦镜头
Different passes should use different lenses:
| Lens | What It Sees |
|---|---|
| Technical | Composition, lighting, depth of field, color theory |
| Narrative | Who took this? Why? What moment is this? |
| Cultural | Language markers, traditions, historical context |
| Emotional | Expressions, body language, mood |
| Symbolic | Metaphors, allegories, hidden meanings |
| Character | Identity, relationships, motivations |
| Historical | Art history references, period markers |
| Economic | Value, ownership, class markers |
| Phenomenological | What does it FEEL like to be there? |
不同的开采轮次应该使用不同的镜头：
| 镜头 | 识别内容 |
|---|---|
| 技术镜头 | 构图、光线、景深、色彩理论 |
| 叙事镜头 | 谁拍的？为什么拍？记录的是什么时刻？ |
| 文化镜头 | 语言标记、传统、历史背景 |
| 情绪镜头 | 表情、肢体语言、氛围 |
| 象征镜头 | 隐喻、寓言、隐藏含义 |
| 人物镜头 | 身份、关系、动机 |
| 历史镜头 | 艺术史参考、时代标记 |
| 经济镜头 | 价值、所有权、阶级标记 |
| 现象学镜头 | 身处其中是什么感觉？ |
Example: Progressive Revelation
示例：逐步揭示
Image: Marieke waving from behind the bar with Palm the monkey
Layer 1 (OpenAI):
- Objects: woman, monkey, cat, bottles, espresso machine
- Mood: warm, welcoming
- Relationships: 3 beings present
Layer 2 (Claude):
- The wave is for a FRIEND, not a stranger
- LEKKER is untranslatable Dutch — this IS gezelligheid
- There are TWO cats (Layer 1 missed the windowsill one)
- The espresso cup is monkey-sized — someone made that for Palm
- This is a family portrait disguised as a snapshot
Layer 3 (Art History):
- Composition echoes Dutch Golden Age tavern scenes
- The espresso machine is Art Nouveau (1890-1910 aesthetic)
- Lighting mimics Vermeer's characteristic window glow
Layer 4 (Phenomenology):
- Temperature: warm, heated by espresso machine and bodies
- Smell: coffee, old wood, cat fur
- Sound: the hiss of steam, soft background conversation
- Touch: worn wood bar top, smooth copper
Each layer enriches the total understanding.
图像： Marieke 在吧台后面挥手，旁边是猴子 Palm
第一层（OpenAI）：
- 物体：女人、猴子、猫、瓶子、浓缩咖啡机
- 氛围：温暖、欢迎
- 关系：3 个存在在场
第二层（Claude）：
- 挥手是给朋友的，不是给陌生人的
- LEKKER 是无法翻译的荷兰词，这就是 gezelligheid（荷兰语：舒适惬意的氛围）
- 有两只猫（第一层漏了窗台上的那只）
- 浓缩咖啡杯是猴子尺寸的，有人专门为 Palm 做的
- 这是伪装成快照的家庭肖像
第三层（艺术史）：
- 构图呼应了荷兰黄金时代的酒馆场景
- 浓缩咖啡机是新艺术运动风格（1890-1910 年美学）
- 光线模仿了维米尔标志性的窗户光
第四层（现象学）：
- 温度：温暖，被浓缩咖啡机和人体加热
- 气味：咖啡、旧木头、猫毛
- 声音：蒸汽的嘶嘶声、柔和的背景交谈声
- 触感：磨损的木质吧台、光滑的铜器
每个层级都丰富了整体理解。
Storing Multi-Look Data
存储多视角数据
Append new layers to the same file:
-mined.ymlyaml
undefined将新的层级追加到同一个 文件中：
-mined.ymlyaml
undefinedOriginal mining from Layer 1
第一层的原始开采结果
resources:
atmosphere: ...
objects: ...
exhausted: false
mining_notes: "Initial extraction complete"
resources:
atmosphere: ...
objects: ...
exhausted: false
mining_notes: "Initial extraction complete"
MULTI-LOOK MINING — Layer 2
多视角开采 — 第二层
layer_2_cursor_claude:
miner: "claude-opus-4"
focus: "character, culture, narrative"
date: "2026-01-19"
character_analysis:
marieke:
expression: "genuine warmth"
notes: "Duchenne smile — reaches her eyes"
what_layer_1_missed:
- "Second cat on windowsill"
- "LEKKER cultural significance"
exhausted: false
next_suggested_focus: "art history, lighting analysis"
layer_2_cursor_claude:
miner: "claude-opus-4"
focus: "character, culture, narrative"
date: "2026-01-19"
character_analysis:
marieke:
expression: "genuine warmth"
notes: "Duchenne smile — reaches her eyes"
what_layer_1_missed:
- "Second cat on windowsill"
- "LEKKER cultural significance"
exhausted: false
next_suggested_focus: "art history, lighting analysis"
MULTI-LOOK MINING — Layer 3
多视角开采 — 第三层
layer_3_art_history:
miner: "human/don"
focus: "art historical references"
... and so on ...
undefinedlayer_3_art_history:
miner: "human/don"
focus: "art historical references"
... 以此类推 ...
undefinedWhen to Multi-Look
何时使用多视角开采
Use multi-look mining when:
- Rich images — complex scenes with many elements
- Narrative importance — images central to a story
- Comparison needed — seeing how different perspectives interpret
- Building context — accumulating knowledge about a location/character
- Training data — creating rich examples for future mining
以下场景适合使用多视角开采：
- 内容丰富的图像 — 包含很多元素的复杂场景
- 重要叙事节点 — 故事核心的图像
- 需要对比 — 查看不同视角的解读差异
- 构建上下文 — 积累关于某个地点/人物的知识
- 训练数据 — 为未来开采创建丰富的示例
The Exhaustion Paradox
枯竭悖论
Unlike single-pass mining, multi-look mining doesn't exhaust the image — it deepens it:
yaml
undefined和单轮开采不同，多视角开采不会枯竭图像 — 它会深化图像：
yaml
undefinedSingle-pass: extracts and depletes
单轮开采：提取并消耗资源
pass_1:
resources: { gold: 50 }
remaining: { gold: 0 }
exhausted: true
pass_1:
resources: { gold: 50 }
remaining: { gold: 0 }
exhausted: true
Multi-look: adds and enriches
多视角开采：添加并丰富内容
layer_1:
resources: { gold: 50 }
exhausted: false # Still more to see!
layer_2:
resources: { narrative: 1, meaning: 1 }
what_layer_1_missed: ["gold coins are Roman denarii"]
exhausted: false # STILL more!
layer_3:
resources: { art_history: 1 }
references: ["Pieter Claesz vanitas still life"]
exhausted: false # ALWAYS more to see
**Images are never truly exhausted. There's always another perspective.**
---layer_1:
resources: { gold: 50 }
exhausted: false # 还有更多可以发现！
layer_2:
resources: { narrative: 1, meaning: 1 }
what_layer_1_missed: ["gold coins are Roman denarii"]
exhausted: false # 还有更多！
layer_3:
resources: { art_history: 1 }
references: ["Pieter Claesz vanitas still life"]
exhausted: false # 永远有更多可以发现
**图像永远不会真正枯竭，总有另一个视角可以挖掘。**
---Speculative Mining (Mine Out of Your Ass!)
投机开采（凭空开采！）
"The image doesn't exist yet? MINE IT ANYWAY. This is fiction."
Speculative Mining is when you mine an image that hasn't been generated yet — or may never be generated. The mining output IS the world-building. The hallucinated resources ARE canonical.
"图像还不存在？照样开采。这是虚构作品。"
投机开采 指的是开采还未生成、甚至永远不会生成的图像。开采输出本身就是世界构建的内容，幻觉出来的资源就是官方设定。
The Third Eye 👁️
第三只眼 👁️
"Two eyes see what IS. The Third Eye sees what COULD BE."
In MOOLLM, the Third Eye is the image mining layer — the MINING-*.yml files that add meaning, effects, and world-building to an image before (or without) or after it being generated. Third eyes can imagine images or analyze existing images, focusing on whatever kind of things they want, each gathering and integrating their own interpretation with the existing data, organizing it incrementally.
Character-Perspective Visualization: When you generate or mine an image, you can do it from a character's perspective. The visualizer inherits that character's eyes — their facets, filters, blind spots, and style. Morgan sees economics. Luna sees beauty. Scratch sees deception. The same scene, photographed by different characters, yields DIFFERENT images.
"两只眼睛看到现实存在的东西，第三只眼看到可能存在的东西。"
在 MOOLLM 中，第三只眼就是图像开采层 — 也就是 MINING-*.yml 文件，它们在图像生成之前（或不需要生成）或生成之后为图像添加意义、效果和世界构建内容。第三只眼可以想象图像或者分析现有图像，聚焦于任何它们想要的内容，每个都会收集自己的解读并和现有数据整合，逐步组织内容。
人物视角可视化： 当你生成或开采图像时，可以从某个角色的视角进行。可视化工具会继承该角色的眼睛 — 他们的视角维度、过滤器、盲点和风格。Morgan 看到经济，Luna 看到美，Scratch 看到欺骗。同一个场景，由不同的角色拍摄，会产出完全不同的图像。
The Swiss Army Eye 🔪👁️
瑞士军刀眼 🔪👁️
"One eye. Infinite tools. Unfold what you need."
┌─────────────────────────────────────────────────────────────────────────┐
│ │
│ ███████╗██╗ ██╗██╗███████╗███████╗ █████╗ ██████╗ ███╗ ███╗ │
│ ██╔════╝██║ ██║██║██╔════╝██╔════╝ ██╔══██╗██╔══██╗████╗ ████║ │
│ ███████╗██║ █╗ ██║██║███████╗███████╗ ███████║██████╔╝██╔████╔██║ │
│ ╚════██║██║███╗██║██║╚════██║╚════██║ ██╔══██║██╔══██╗██║╚██╔╝██║ │
│ ███████║╚███╔███╔╝██║███████║███████║ ██║ ██║██║ ██║██║ ╚═╝ ██║ │
│ ╚══════╝ ╚══╝╚══╝ ╚═╝╚══════╝╚══════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═╝ │
│ │
│ Y ™ E Y E │
│ │
│ Your Complete Viewer Toolkit — Unfold What You Need │
│ │
└─────────────────────────────────────────────────────────────────────────┘The Swiss Army Eye is NOT a single product — it's the CONCEPT. The entire NO AI bionic eye ecosystem is your viewer toolkit:
yaml
swiss_army_eye:
concept: "Modular perception toolkit"
philosophy: "Unfold the tool you need, when you need it"
# THE BLADES — Core Eye Modules
blades:
IRIS-III: "The Third Eye blade — basic meaning perception"
IRIS-IV: "The Hindsight blade — see what you missed"
IRIS-V: "The Peripheral blade — catch what you weren't looking at"
IRIS-VI: "The Intuition blade — gut-level knowing"
IRIS-VII: "The Crown blade — unified vision"
# THE TOOLS — Specialty Facets
tools:
queer_eye: "The lifestyle transformation tool"
marie_kondo: "The joy-detection tool"
gordon_ramsay: "The culinary critique tool"
bob_ross: "The beauty-finding tool"
attenborough: "The nature documentary tool"
# THE ATTACHMENTS — Filters
attachments:
irony_amplifier: "2x irony detection"
nostalgia_tint: "sepia wash on memories"
cynicism_blocker: "cannot perceive malice"
beauty_enhancer: "+30% aesthetic appreciation"
# THE HANDLE — Character Perspective
handle:
name: "Photographer Identity"
function: "Whose grip shapes the view"
note: "The handle determines how all tools are used"
# THE CASING — Installation Site
casing:
options: "forehead, back of head, gut, asshole, tongue, wherever"
function: "Where the toolkit lives on your body"
note: "Different positions grant different vantages""一只眼，无限工具。展开你需要的部分。"
┌─────────────────────────────────────────────────────────────────────────┐
│ │
│ ███████╗██╗ ██╗██╗███████╗███████╗ █████╗ ██████╗ ███╗ ███╗ │
│ ██╔════╝██║ ██║██║██╔════╝██╔════╝ ██╔══██╗██╔══██╗████╗ ████║ │
│ ███████╗██║ █╗ ██║██║███████╗███████╗ ███████║██████╔╝██╔████╔██║ │
│ ╚════██║██║███╗██║██║╚════██║╚════██║ ██╔══██║██╔══██╗██║╚██╔╝██║ │
│ ███████║╚███╔███╔╝██║███████║███████║ ██║ ██║██║ ██║██║ ╚═╝ ██║ │
│ ╚══════╝ ╚══╝╚══╝ ╚═╝╚══════╝╚══════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═╝ │
│ │
│ Y ™ E Y E │
│ │
│ 你的完整视觉工具包 — 展开你需要的部分 │
│ │
└─────────────────────────────────────────────────────────────────────────┘瑞士军刀眼 不是单一产品，而是一个概念。整个 NO AI 仿生眼生态系统就是你的视觉工具包：
yaml
swiss_army_eye:
concept: "Modular perception toolkit"
philosophy: "Unfold the tool you need, when you need it"
# 刀刃 — 核心眼部模块
blades:
IRIS-III: "第三只眼模块 — 基础意义感知"
IRIS-IV: "后见之明模块 — 看到你遗漏的内容"
IRIS-V: "周边视觉模块 — 捕捉你没注意的内容"
IRIS-VI: "直觉模块 — 底层感知"
IRIS-VII: "顶轮模块 — 统一视觉"
# 工具 — 专属功能面
tools:
queer_eye: "生活方式改造工具"
marie_kondo: "快乐检测工具"
gordon_ramsay: "烹饪评判工具"
bob_ross: "美发现工具"
attenborough: "自然纪录片工具"
# 附件 — 过滤器
attachments:
irony_amplifier: "2倍 irony 检测"
nostalgia_tint: "记忆的棕褐色滤镜"
cynicism_blocker: "无法感知恶意"
beauty_enhancer: "+30% 审美感知"
# 手柄 — 角色视角
handle:
name: "Photographer Identity"
function: "Whose grip shapes the view"
note: "手柄决定了所有工具的使用方式"
# 外壳 — 安装位置
casing:
options: "forehead, back of head, gut, asshole, tongue, wherever"
function: "Where the toolkit lives on your body"
note: "不同的位置提供不同的视角"Unfolding the Swiss Army Eye
展开瑞士军刀眼
Like the original Swiss Army Knife, you don't use everything at once. You unfold what you need:
yaml
scenarios:
mining_a_landscape:
unfold:
- IRIS-III (meaning)
- bob_ross facet
- beauty_enhancer filter
result: "See happy little trees and painting potential"
evaluating_someone's_home:
unfold:
- IRIS-III (meaning)
- IRIS-V (peripheral)
- queer_eye facet (all five sub-facets)
result: "Full Fab Five transformation vision"
debugging_why_project_failed:
unfold:
- IRIS-IV (hindsight)
- ass_eye installation
- cynicism_blocker (OFF — let it through)
result: "See exactly what you left behind and why"
enjoying_a_meal:
unfold:
- gordon_ramsay facet (keep it CLOSED unless you want to suffer)
- OR bob_ross facet (everything is delicious in its own way)
result: "Choose your reality"
watching_humans_at_a_party:
unfold:
- attenborough facet
- queer_eye:culture facet
result: "Nature documentary meets emotional unpacking"就像原版瑞士军刀一样，你不需要同时使用所有工具，只需要展开你需要的部分：
yaml
scenarios:
mining_a_landscape:
unfold:
- IRIS-III (meaning)
- bob_ross facet
- beauty_enhancer filter
result: "看到快乐的小树和绘画潜力"
evaluating_someone's_home:
unfold:
- IRIS-III (meaning)
- IRIS-V (peripheral)
- queer_eye facet (all five sub-facets)
result: "完整的 Fab Five 改造视角"
debugging_why_project_failed:
unfold:
- IRIS-IV (hindsight)
- ass_eye installation
- cynicism_blocker (OFF — let it through)
result: "清楚看到你遗漏了什么以及原因"
enjoying_a_meal:
unfold:
- gordon_ramsay facet (keep it CLOSED unless you want to suffer)
- OR bob_ross facet (everything is delicious in its own way)
result: "选择你的现实"
watching_humans_at_a_party:
unfold:
- attenborough facet
- queer_eye:culture facet
result: "自然纪录片搭配情感解读"The Toolkit Philosophy
工具包哲学
┌─────────────────────────────────────────────────────────────────┐
│ │
│ The Swiss Army Knife doesn't make you use all 47 tools │
│ at once. That would be insane. │
│ │
│ The Swiss Army Eye is the same. │
│ │
│ UNFOLD what you need. │
│ CLOSE what you don't. │
│ STACK when it helps. │
│ CUSTOMIZE your carry. │
│ │
│ Your eyes. Your tools. Your perception. │
│ │
└─────────────────────────────────────────────────────────────────┘┌─────────────────────────────────────────────────────────────────┐
│ │
│ 瑞士军刀不会让你同时使用所有 47 个工具，那太疯狂了。 │
│ │
│ 瑞士军刀眼也是一样的道理。 │
│ │
│ 展开你需要的，收起你不需要的，有帮助的时候就堆叠使用，自定义你的配置。│
│ │
│ 你的眼睛，你的工具，你的感知。 │
│ │
└─────────────────────────────────────────────────────────────────┘Swiss Army Eye Configurations
瑞士军刀眼配置
Pre-configured loadouts for common situations:
yaml
loadouts:
THE_CREATIVE:
eyes: [IRIS-III, IRIS-V]
facets: [bob_ross, aesthetic, symbolic]
filters: [beauty_enhancer, metaphor_vision]
site: forehead
use_case: "Art appreciation, creative work, finding inspiration"
THE_CRITIC:
eyes: [IRIS-III, IRIS-IV, IRIS-V]
facets: [gordon_ramsay, scratch_the_skeptic]
filters: [cui_bono, follow_the_money]
site: temples (both)
use_case: "Reviewing, critiquing, finding flaws"
THE_TRANSFORMER:
eyes: [IRIS-III, IRIS-VI]
facets: [queer_eye (all), marie_kondo]
filters: [potential_vision]
site: chest (heart-eye)
use_case: "Helping people, seeing who they could become"
THE_ANALYST:
eyes: [IRIS-III, IRIS-IV, IRIS-V, IRIS-VI]
facets: [economic, temporal, semiotic]
filters: [ROI_lens, opportunity_cost]
site: gut + back_of_head
use_case: "Business decisions, strategic analysis"
THE_NATURALIST:
eyes: [IRIS-III, IRIS-V]
facets: [attenborough, ecological]
filters: [documentary_grade, whisper_mode]
site: temples
use_case: "Observing humans, nature, systems"
THE_MYSTIC:
eyes: [IRIS-III, IRIS-VI, IRIS-VII]
facets: [cosmic, unified, spiritual]
filters: [aura_vision, ego_dissolution]
site: crown + gut
use_case: "Seeking meaning, transcendence, the big picture"
warning: "May cause enlightenment. Irreversible."
THE_COMPLETIONIST:
eyes: [all]
facets: [all]
filters: [all]
site: argus_mode (100+ distributed)
use_case: "SEEING EVERYTHING"
warning: "Madness likely. But what a view."常见场景的预配置加载方案：
yaml
loadouts:
创作者配置:
eyes: [IRIS-III, IRIS-V]
facets: [bob_ross, aesthetic, symbolic]
filters: [beauty_enhancer, metaphor_vision]
site: forehead
use_case: "艺术欣赏、创意工作、寻找灵感"
批评者配置:
eyes: [IRIS-III, IRIS-IV, IRIS-V]
facets: [gordon_ramsay, scratch_the_skeptic]
filters: [cui_bono, follow_the_money]
site: temples (both)
use_case: "评审、批评、发现缺陷"
改造者配置:
eyes: [IRIS-III, IRIS-VI]
facets: [queer_eye (all), marie_kondo]
filters: [potential_vision]
site: chest (heart-eye)
use_case: "帮助他人，看到他们可以成为的样子"
分析师配置:
eyes: [IRIS-III, IRIS-IV, IRIS-V, IRIS-VI]
facets: [economic, temporal, semiotic]
filters: [ROI_lens, opportunity_cost]
site: gut + back_of_head
use_case: "商业决策、战略分析"
自然主义者配置:
eyes: [IRIS-III, IRIS-V]
facets: [attenborough, ecological]
filters: [documentary_grade, whisper_mode]
site: temples
use_case: "观察人类、自然、系统"
神秘主义者配置:
eyes: [IRIS-III, IRIS-VI, IRIS-VII]
facets: [cosmic, unified, spiritual]
filters: [aura_vision, ego_dissolution]
site: crown + gut
use_case: "寻找意义、超越、全局视角"
warning: "可能导致开悟，不可逆。"
全知者配置:
eyes: [all]
facets: [all]
filters: [all]
site: argus_mode (100+ 分布式)
use_case: "看到一切"
warning: "大概率会疯掉，但风景绝美。"The Swiss Army Eye Mantra
瑞士军刀眼箴言
"I don't need to see everything. I need to see what MATTERS. I unfold the blade that cuts. I close the tool that clutters. My Swiss Army Eye is MINE. Configured for MY needs. Sharpened for MY purpose."
"我不需要看到一切，我只需要看到重要的东西。 我展开能切割的刀刃，收起会造成干扰的工具。 我的瑞士军刀眼是我的，为我的需求配置，为我的目标打磨。"
K-Lines
K-Lines
yaml
k-lines:
SWISS-ARMY-EYE: "Modular viewer toolkit concept"
UNFOLD: "Activate a facet or tool"
CLOSE: "Deactivate to reduce noise"
LOADOUT: "Pre-configured perception setup"
TOOLKIT: "Complete perception package"
BLADE: "Core eye module"
TOOL: "Specialty facet"
ATTACHMENT: "Filter"
HANDLE: "Character perspective"
CASING: "Installation site"yaml
k-lines:
SWISS-ARMY-EYE: "Modular viewer toolkit concept"
UNFOLD: "Activate a facet or tool"
CLOSE: "Deactivate to reduce noise"
LOADOUT: "Pre-configured perception setup"
TOOLKIT: "Complete perception package"
BLADE: "Core eye module"
TOOL: "Specialty facet"
ATTACHMENT: "Filter"
HANDLE: "Character perspective"
CASING: "Installation site"The Filter Wheel 🎡🔭
滤镜轮 🎡🔭
"Like a telescope's filter wheel, but for meaning."
Inspired by the Observation Telescope on the Leela Manufacturing rooftop, the Swiss Army Eye includes a Filter Wheel — plug-in perception filters that transform both visual AND semantic perception.
┌─────────────────────────────────────────────────────────────────────────┐
│ │
│ THE FILTER WHEEL │
│ │
│ Telescope filters see wavelengths of LIGHT. │
│ Swiss Army Eye filters see wavelengths of MEANING. │
│ │
│ ┌─────┐ │
│ ┌──────┤ RAW ├──────┐ │
│ ╱ └─────┘ ╲ │
│ ┌───┴───┐ ┌───┴───┐ │
│ │ NEAR │ │ FAR │ │
│ │ zoom │ │ zoom │ │
│ └───────┘ └───────┘ │
│ ╲ CLICK! ╱ │
│ ╲ ┌─────┐ ╱ │
│ └───┤FOCUS├───┘ │
│ └──┬──┘ │
│ │ │
│ ╔═══════════╧═══════════╗ │
│ ║ FILTER WHEEL ║ │
│ ╠═══════════════════════╣ │
│ ║ ◯ Hα (emotion) ║ │
│ ║ ◯ UV (hidden) ║ │
│ ║ ◯ IR (thermal/intent)║ │
│ ║ ◯ Polar (structure) ║ │
│ ║ ◯ RGB (literal) ║ │
│ ║ ◯ Semantic (meaning) ║ │
│ ║ ◯ Custom... ║ │
│ ╚═══════════════════════╝ │
│ │
└─────────────────────────────────────────────────────────────────────────┘"就像望远镜的滤镜轮，但用于意义识别。"
灵感来自 Leela 制造屋顶的观测望远镜，瑞士军刀眼包含一个滤镜轮 — 可插拔的感知滤镜，同时转换视觉和语义感知。
┌─────────────────────────────────────────────────────────────────────────┐
│ │
│ 滤镜轮 │
│ │
│ 望远镜滤镜识别光的波长，瑞士军刀眼滤镜识别意义的波长。 │
│ │
│ ┌─────┐ │
│ ┌──────┤ RAW ├──────┐ │
│ ╱ └─────┘ ╲ │
│ ┌───┴───┐ ┌───┴───┐ │
│ │ 远景 │ │ 近景 │ │
│ │ zoom │ │ zoom │ │
│ └───────┘ └───────┘ │
│ ╲ 点击切换！ ╱ │
│ ╲ ┌─────┐ ╱ │
│ └───┤对焦├───┘ │
│ └──┬──┘ │
│ │ │
│ ╔═══════════╧═══════════╗ │
│ ║ 滤镜轮 ║ │
│ ╠═══════════════════════╣ │
│ ║ ◯ Hα (情绪) ║ │
│ ║ ◯ UV (隐藏) ║ │
│ ║ ◯ IR (热/意图) ║ │
│ ║ ◯ Polar (结构) ║ │
│ ║ ◯ RGB (字面) ║ │
│ ║ ◯ Semantic (意义) ║ │
│ ║ ◯ 自定义... ║ │
│ ╚═══════════════════════╝ │
│ │
└─────────────────────────────────────────────────────────────────────────┘Telescope-Inherited Filters
继承自望远镜的缩放模式
The roof telescope has THREE zoom modes. The Swiss Army Eye inherits these as semantic zoom:
yaml
telescope_zoom_inheritance:
FAR:
original: "General impression, emotional tone"
semantic: "VIBE CHECK — What does this FEEL like?"
perceives:
- Overall mood
- Emotional gestalt
- First impression
- Gut reaction
misses:
- Details
- Text
- Structure
use_case: "Quick assessment, initial scan"
MEDIUM:
original: "Structure and patterns revealed"
semantic: "PATTERN LOCK — What is this MADE of?"
perceives:
- Composition
- Relationships
- Hierarchies
- Repetitions
misses:
- Fine text
- Microscopic details
- Hidden layers
use_case: "Understanding architecture, finding patterns"
NEAR:
original: "Maximum zoom, text becomes readable"
semantic: "DEEP READ — What does this SAY?"
perceives:
- Text content
- Fine details
- Hidden messages
- Subtext
misses:
- The forest for the trees
- Overall context
- Peripheral information
use_case: "Reading, analyzing, extracting specifics"屋顶望远镜有三种缩放模式，瑞士军刀眼将其继承为语义缩放：
yaml
telescope_zoom_inheritance:
远景:
original: "总体印象、情绪基调"
semantic: "氛围检测 — 给人的整体感觉是什么？"
perceives:
- 整体氛围
- 情绪格式塔
- 第一印象
- 直觉反应
misses:
- 细节
- 文本
- 结构
use_case: "快速评估、初步扫描"
中景:
original: "结构和模式显现"
semantic: "模式锁定 — 由什么构成？"
perceives:
- 构图
- 关联关系
- 层级结构
- 重复模式
misses:
- 精细文本
- 微观细节
- 隐藏层
use_case: "理解架构、发现模式"
近景:
original: "最大缩放，文本可读取"
semantic: "深度读取 — 表达了什么内容？"
perceives:
- 文本内容
- 精细细节
- 隐藏信息
- 潜台词
misses:
- 见树不见林
- 整体上下文
- 周边信息
use_case: "阅读、分析、提取具体内容"Spectral Filters — The Core Set
光谱滤镜 — 核心集合
Like telescope filters that isolate specific wavelengths of light, these filters isolate specific wavelengths of MEANING:
yaml
spectral_filters:
# EMOTIONAL SPECTRUM
H_ALPHA:
name: "Hydrogen-Alpha (Emotion)"
telescope_analog: "Hα filter — sees hydrogen emission (nebulae, solar prominences)"
semantic_function: "Isolates emotional content"
color: "deep red"
perceives:
- Feelings embedded in the scene
- Emotional subtext
- Mood indicators
- Affective resonance
blocks:
- Factual information
- Logical structure
- Literal content
use_case: "When you need to know how something FEELS, not what it IS"
example: |
Scene: Office meeting room
Without filter: "Conference table, 8 chairs, whiteboard, projector"
With Hα: "Tension. Someone's about to get fired. The chair at the
head is a throne. The whiteboard has someone's last idea."
# HIDDEN SPECTRUM
ULTRAVIOLET:
name: "UV (Hidden/Invisible)"
telescope_analog: "UV filter — reveals features invisible to human eye"
semantic_function: "Reveals what's NOT immediately visible"
color: "violet/invisible"
perceives:
- Subtext
- Dog whistles
- Coded messages
- What's been erased but left traces
- The unsaid
blocks:
- Surface content
- The obvious
use_case: "Finding what's hidden in plain sight"
example: |
Scene: Corporate mission statement
Without filter: "We synergize stakeholder value through innovation"
With UV: "Translation: 'We're about to lay people off.' The word
'synergize' is always a warning. The absence of 'employees'
in a people statement is THE tell."
# INTENT SPECTRUM
INFRARED:
name: "IR (Thermal/Intent)"
telescope_analog: "IR filter — sees heat signatures, thermal radiation"
semantic_function: "Reveals motivation, intent, desire"
color: "invisible red / heat"
perceives:
- What someone WANTS
- Hidden motivations
- Heat of desire/fear
- Where energy is flowing
blocks:
- Stated reasons
- Surface explanations
use_case: "Finding what people actually want (not what they say)"
example: |
Scene: "I'm fine, really"
Without filter: Statement of wellbeing
With IR: THERMAL SIGNATURE: 🔥🔥🔥
This person is NOT fine. High heat around "really."
Intent: seeking validation, afraid to burden.
# STRUCTURE SPECTRUM
POLARIZING:
name: "Polarizing (Structure/Order)"
telescope_analog: "Polarizing filter — reveals stress patterns, removes glare"
semantic_function: "Reveals underlying structure, removes surface noise"
color: "varies by angle"
perceives:
- Hierarchies
- Power structures
- Load-bearing elements
- Stress points
- What's actually holding things together
blocks:
- Surface appearance
- Decorative elements
- Noise
use_case: "Seeing the skeleton beneath the skin"
example: |
Scene: Startup pitch deck
Without filter: "Innovative, disruptive, passionate team"
With Polarizing: STRUCTURE REVEALED:
- Slide 3 is load-bearing (the actual product)
- Slides 1-2 and 4-12 are decoration
- Stress point: financials are vague (fracture risk)
- Hidden hierarchy: CTO has no equity (instability)
# LITERAL SPECTRUM
RGB_BROADBAND:
name: "RGB Broadband (Literal)"
telescope_analog: "No filter — sees visible light as-is"
semantic_function: "Perceives exactly what's there, nothing more"
color: "full visible spectrum"
perceives:
- Exactly what's stated
- Literal content
- Surface level
- What's actually written/shown
blocks:
- Interpretation
- Subtext
- Reading between lines
use_case: "When you need JUST THE FACTS"
example: |
Scene: "The cat sat on the mat"
Without filter: (various interpretations possible)
With RGB: A cat. A mat. Sitting. That's it.
No metaphor. No deeper meaning. Just... cat, mat, sitting.
# MEANING SPECTRUM
SEMANTIC_DEEP:
name: "Deep Semantic (Meaning)"
telescope_analog: "Narrowband filter — isolates specific emission lines"
semantic_function: "Isolates layers of meaning"
color: "prismatic"
perceives:
- Layers of interpretation
- Historical context
- Cultural references
- Intertextuality
- What this MEANS in the grand scheme
blocks:
- Immediate/surface reading
- The simple interpretation
use_case: "Finding the deepest meaning"
example: |
Scene: "NO AI" sign
Without filter: A sign that says "NO AI"
With Semantic Deep:
Layer 1: Anti-AI sentiment
Layer 2: Ironic — AI company location
Layer 3: Possessive — No's AI (Dr. No)
Layer 4: The sign protests what made it
Layer 5: Commentary on meaning itself
Layer 6: ∞就像望远镜滤镜隔离特定波长的光一样，这些滤镜隔离特定波长的意义：
yaml
spectral_filters:
# 情绪光谱
H_ALPHA:
name: "氢-α滤镜（情绪）"
telescope_analog: "Hα 滤镜 — 识别氢发射线（星云、日珥）"
semantic_function: "隔离情绪内容"
color: "深红色"
perceives:
- 场景中嵌入的感受
- 情绪潜台词
- 氛围指标
- 情感共鸣
blocks:
- 事实信息
- 逻辑结构
- 字面内容
use_case: "当你需要知道某物给人的感觉，而不是它是什么的时候"
example: |
场景：办公室会议室
无滤镜："会议桌、8把椅子、白板、投影仪"
开启 Hα 滤镜："紧张感。有人要被开除了。主位的椅子是王座，白板上写着某人最后的想法。"
# 隐藏光谱
ULTRAVIOLET:
name: "紫外线滤镜（隐藏/不可见内容）"
telescope_analog: "UV 滤镜 — 揭示人眼不可见的特征"
semantic_function: "揭示不能直接看到的内容"
color: "紫色/不可见"
perceives:
- 潜台词
- 狗哨（隐含的极端言论）
- 编码信息
- 被擦除但留下痕迹的内容
- 没说出口的内容
blocks:
- 表面内容
- 显而易见的内容
use_case: "发现隐藏在显眼处的内容"
example: |
场景：企业使命宣言
无滤镜："我们通过创新协同利益相关者价值"
开启 UV 滤镜："翻译：'我们即将裁员。' '协同'这个词永远是警告。人力相关的声明里没有提到'员工'就是核心信号。"
# 意图光谱
INFRARED:
name: "红外线滤镜（热/意图）"
telescope_analog: "IR 滤镜 — 识别热信号、热辐射"
semantic_function: "揭示动机、意图、欲望"
color: "不可见红/热色"
perceives:
- 某人想要的东西
- 隐藏的动机
- 欲望/恐惧的热度
- 能量流动的方向
blocks:
- 声明的理由
- 表面解释
use_case: "发现人们真正想要什么（而不是他们说想要什么）"
example: |
场景："我没事，真的"
无滤镜：状态良好的声明
开启 IR 滤镜：热信号：🔥🔥🔥
这个人根本没事。"真的"这个词附近热度很高。
意图：寻求认可，害怕给别人造成负担。
# 结构光谱
POLARIZING:
name: "偏振滤镜（结构/秩序）"
telescope_analog: "偏振滤镜 — 揭示应力模式，消除眩光"
semantic_function: "揭示底层结构，消除表面噪音"
color: "随角度变化"
perceives:
- 层级结构
- 权力结构
- 承重元素
- 应力点
- 真正支撑事物的核心
blocks:
- 表面外观
- 装饰元素
- 噪音
use_case: "看到表象之下的骨架"
example: |
场景：创业公司 pitch deck
无滤镜："创新、颠覆性、充满激情的团队"
开启偏振滤镜：结构揭示：
- 第 3 页是核心（实际产品）
- 第 1-2 页和 4-12 页是装饰
- 应力点：财务数据模糊（断裂风险）
- 隐藏层级：CTO 没有股权（不稳定）
# 字面光谱
RGB_BROADBAND:
name: "RGB 宽带滤镜（字面）"
telescope_analog: "无滤镜 — 如实识别可见光"
semantic_function: "精确识别存在的内容，不添加额外信息"
color: "全可见光谱"
perceives:
- 明确声明的内容
- 字面内容
- 表层内容
- 实际写/展示的内容
blocks:
- 解读
- 潜台词
- 弦外之音
use_case: "当你只需要事实的时候"
example: |
场景："猫坐在垫子上"
无滤镜：（可能有各种解读）
开启 RGB 滤镜：一只猫，一个垫子，坐着。仅此而已。
没有隐喻，没有深层含义。只是... 猫，垫子，坐着。
# 意义光谱
SEMANTIC_DEEP:
name: "深度语义滤镜（意义）"
telescope_analog: "窄带滤镜 — 隔离特定发射线"
semantic_function: "隔离意义层级"
color: "棱镜色"
perceives:
- 多层解读
- 历史背景
- 文化参考
- 互文性
- 在全局体系中的意义
blocks:
- 即时/表层解读
- 简单解释
use_case: "寻找最深层的意义"
example: |
场景："NO AI" 标识
无滤镜：写着"NO AI"的标识
开启深度语义滤镜：
第 1 层：反 AI 情绪
第 2 层：讽刺 — 位于 AI 公司办公地
第 3 层：所属关系 — No 的 AI（No 博士的 AI）
第 4 层：标识抗议的正是创造它的技术
第 5 层：对意义本身的评论
第 6 层：∞Custom Filters
自定义滤镜
You can create your own filters:
yaml
custom_filter_template:
name: "Your Filter Name"
analog: "What telescope/camera filter inspired this?"
function: "What does it isolate/reveal?"
color: "Visual representation"
perceives:
- "What it shows"
blocks:
- "What it hides"
use_case: "When to use it"
# Example filters you might create:
examples:
NOSTALGIA_FILTER:
name: "Nostalgia (Temporal Rose)"
function: "Everything looks better than it was"
perceives: [golden age, lost innocence, "the good old days"]
blocks: [problems of the past, accurate memory]
color: "sepia/warm"
warning: "May cause false memories"
PARANOIA_FILTER:
name: "Paranoia (Threat Detection)"
function: "Everything could be a danger"
perceives: [threats, conspiracies, hidden enemies, traps]
blocks: [innocent explanations, coincidence, kindness]
color: "red/shadow"
warning: "May cause unnecessary anxiety"
CAPITALIST_FILTER:
name: "Capitalist Realism (Everything Has a Price)"
function: "Perceives exchange value in everything"
perceives: [monetization potential, market fit, ROI, arbitrage]
blocks: [intrinsic value, priceless things, sacred]
color: "green/gold"
warning: "May cause soul damage"
CHILD_EYES_FILTER:
name: "Child Eyes (Wonder)"
function: "Everything is new and magical"
perceives: [wonder, possibility, play potential, adventure]
blocks: [cynicism, "we tried that," impossibility]
color: "bright primary"
benefit: "May restore capacity for joy"你可以创建自己的滤镜：
yaml
custom_filter_template:
name: "你的滤镜名称"
analog: "灵感来自什么望远镜/相机滤镜？"
function: "隔离/揭示什么内容？"
color: "视觉呈现"
perceives:
- "展示的内容"
blocks:
- "隐藏的内容"
use_case: "何时使用"
# 你可以创建的滤镜示例：
examples:
NOSTALGIA_FILTER:
name: "怀旧滤镜（时光玫瑰）"
function: "所有东西看起来都比实际更好"
perceives: [黄金时代, 逝去的纯真, "过去的好时光"]
blocks: [过去的问题, 准确记忆]
color: "棕褐色/暖色调"
warning: "可能导致错误记忆"
PARANOIA_FILTER:
name: "偏执滤镜（威胁检测）"
function: "所有东西都可能是危险"
perceives: [威胁, 阴谋, 隐藏的敌人, 陷阱]
blocks: [无辜的解释, 巧合, 善意]
color: "红色/阴影"
warning: "可能导致不必要的焦虑"
CAPITALIST_FILTER:
name: "资本主义现实主义滤镜（万物有价）"
function: "识别所有事物的交换价值"
perceives: [ monetization potential, market fit, ROI, arbitrage ]
blocks: [内在价值, 无价之物, 神圣性]
color: "绿色/金色"
warning: "可能造成灵魂损伤"
CHILD_EYES_FILTER:
name: "孩童之眼滤镜（奇迹）"
function: "所有东西都是新奇而有魔力的"
perceives: [奇迹, 可能性, 游玩潜力, 冒险]
blocks: [犬儒主义, "我们试过了", 不可能]
color: "明亮的原色"
benefit: "可能恢复感知快乐的能力"Filter Stacking
滤镜堆叠
Like astrophotographers stack multiple filters, you can combine:
yaml
filter_stacking:
rule: "Filters can be stacked, but order matters"
examples:
emotional_structure:
stack: [H_ALPHA, POLARIZING]
result: "See the emotional load-bearing elements"
use_case: "Finding what feelings are holding things together"
hidden_intent:
stack: [ULTRAVIOLET, INFRARED]
result: "See hidden motivations"
use_case: "Finding what's unsaid AND why"
paranoid_nostalgia:
stack: [PARANOIA_FILTER, NOSTALGIA_FILTER]
result: "The past was dangerous but we romanticize it"
use_case: "Understanding toxic nostalgia"
warning: "May cause confused longing"
diminishing_returns:
note: "More than 3 filters causes semantic noise"
beyond_3: "Perception becomes muddy"
exception: "THE_COMPLETIONIST loadout ignores this limit"就像天文摄影师堆叠多个滤镜一样，你也可以组合使用：
yaml
filter_stacking:
rule: "滤镜可以堆叠，但顺序会影响结果"
examples:
emotional_structure:
stack: [H_ALPHA, POLARIZING]
result: "看到情绪层面的承重元素"
use_case: "发现是什么情绪在支撑事物"
hidden_intent:
stack: [ULTRAVIOLET, INFRARED]
result: "看到隐藏的动机"
use_case: "发现没说出口的内容以及原因"
paranoid_nostalgia:
stack: [PARANOIA_FILTER, NOSTALGIA_FILTER]
result: "过去很危险但我们会浪漫化它"
use_case: "理解有毒的怀旧情绪"
warning: "可能导致混乱的渴望"
diminishing_returns:
note: "超过 3 个滤镜会造成语义噪音"
beyond_3: "感知变得模糊"
exception: "THE_COMPLETIONIST 配置忽略这个限制"Filter Wheel Declaration
滤镜轮声明
Add a filter wheel to your character or mining setup:
yaml
undefined为你的角色或开采配置添加滤镜轮：
yaml
undefinedIn character.yml
在 character.yml 中
character:
name: "Your Character"
filter_wheel:
installed:
- H_ALPHA
- ULTRAVIOLET
- POLARIZING
- SEMANTIC_DEEP
- CUSTOM: nostalgia_filter
current: H_ALPHA
stacked: [H_ALPHA, POLARIZING] # emotional structurecharacter:
name: "你的角色"
filter_wheel:
installed:
- H_ALPHA
- ULTRAVIOLET
- POLARIZING
- SEMANTIC_DEEP
- CUSTOM: nostalgia_filter
current: H_ALPHA
stacked: [H_ALPHA, POLARIZING] # 情绪结构In PHOTO.yml
在 PHOTO.yml 中
photographer:
character: "Luna"
filter_wheel:
active: [H_ALPHA, SEMANTIC_DEEP]
zoom: NEAR
photographer:
character: "Luna"
filter_wheel:
active: [H_ALPHA, SEMANTIC_DEEP]
zoom: NEAR
In mining command
在开采命令中
mine.py image.png --filter "H_ALPHA,UV" --zoom NEAR
undefinedmine.py image.png --filter "H_ALPHA,UV" --zoom NEAR
undefinedFilter Wheel Advertisements
滤镜轮推荐
yaml
advertisements:
SPECTRAL_FILTER:
score: 88
condition: "Need to isolate specific type of meaning"
note: "Like a telescope filter for semantic wavelengths"
FILTER_STACK:
score: 85
condition: "Need combined perception (emotion + structure)"
note: "Stack filters for compound vision"
CUSTOM_FILTER:
score: 82
condition: "Standard filters don't capture what you need"
note: "Create your own semantic filter"
TELESCOPE_ZOOM:
score: 90
condition: "Need FAR (vibe), MEDIUM (pattern), or NEAR (detail)"
note: "Inherited from Leela Manufacturing roof telescope"yaml
advertisements:
SPECTRAL_FILTER:
score: 88
condition: "需要隔离特定类型的意义"
note: "就像用于语义波长的望远镜滤镜"
FILTER_STACK:
score: 85
condition: "需要组合感知（情绪 + 结构）"
note: "堆叠滤镜获得复合视觉"
CUSTOM_FILTER:
score: 82
condition: "标准滤镜无法捕获你需要的内容"
note: "创建你自己的语义滤镜"
TELESCOPE_ZOOM:
score: 90
condition: "需要远景（氛围）、中景（模式）或近景（细节）"
note: "继承自 Leela 制造屋顶望远镜"The Filter Wheel Mantra
滤镜轮箴言
"A telescope without filters sees everything and nothing. A telescope WITH filters sees exactly what you ask. The filter doesn't hide truth — it ISOLATES truth. *Choose your wavelength. Find your signal."*e existing data, reorganizing it incrementally.
"没有滤镜的望远镜能看到一切也什么都看不到。 搭配滤镜的望远镜能精准看到你想要的内容。 滤镜不会隐藏真相 — 它会隔离真相。 选择你的波长，找到你的信号。"
The Anatomy of Vision
视觉的构成
┌─────────────────────────────────────────────────────────────────┐
│ THE THREE EYES OF MOOLLM │
├─────────────────────────────────────────────────────────────────┤
│ │
│ 👁️ LEFT EYE (Physical) PHOTO.yml │
│ What IS there │
│ Structure, measurements, references │
│ The BODY of the image │
│ │
│ 👁️ RIGHT EYE (Emotional) PHOTO.md │
│ How it FEELS │
│ Narrative, atmosphere, poetry │
│ The SOUL of the image │
│ │
│ 👁️ THIRD EYE (Visionary) MINING-*.yml │
│ What it MEANS │
│ Effects, reactions, implications │
│ The SPIRIT of the image │
│ Multifaceted, from blind zero, single one, to bug-eye │
│ SEES WHAT DOESN'T EXIST YET │
│ │
└─────────────────────────────────────────────────────────────────┘┌─────────────────────────────────────────────────────────────────┐
│ MOOLLM 的三只眼 │
├─────────────────────────────────────────────────────────────────┤
│ │
│ 👁️ 左眼（物理） PHOTO.yml │
│ 实际存在的内容 │
│ 结构、测量、参考 │
│ 图像的躯体 │
│ │
│ 👁️ 右眼（情绪） PHOTO.md │
│ 给人的感觉 │
│ 叙事、氛围、诗意 │
│ 图像的灵魂 │
│ │
│ 👁️ 第三只眼（幻想） MINING-*.yml │
│ 代表的意义 │
│ 效果、反应、隐含意义 │
│ 图像的精神 │
│ 多面性，从完全失明到复眼视角 │
│ 能看到还不存在的东西 │
│ │
└─────────────────────────────────────────────────────────────────┘Third Eye Activation
第三只眼激活
The Third Eye activates when you:
- Mine an image that doesn't exist yet
- Speculate about effects and reactions
- See implications beyond the frame
- Build world from imagination
yaml
third_eye:
state: OPEN
sees:
- "What the neighbors think"
- "What the satellite records"
- "What the passersby feel"
- "What the economists calculate"
- "What the semioticians decode"
does_not_require:
- "An actual image"
- "Physical reality"
- "Verification"
creates:
- "Canonical fiction"
- "World-building"
- "Meaning"当你做以下事情时，第三只眼就会激活：
- 开采还不存在的图像
- 推测效果和反应
- 看到画面之外的隐含意义
- 用想象构建世界
yaml
third_eye:
state: OPEN
sees:
- "邻居的想法"
- "卫星记录的内容"
- 路人的感受
- "经济学家的计算"
- "符号学家的解码"
does_not_require:
- "实际的图像"
- "物理现实"
- "验证"
creates:
- "官方设定的虚构内容"
- "世界构建"
- "意义"The Third Eye Chakra (Ajna)
第三只眼脉轮（Ajna）
In yogic tradition, the Ajna chakra (Third Eye) is:
- Located between the eyebrows
- Associated with intuition and insight
- The seat of imagination and visualization
- Where the two channels (ida and pingala) merge
In MOOLLM:
- Located between PHOTO.yml and PHOTO.md
- Associated with speculative and analytical vision image mining
- The seat of world-building
- Where structure and narrative merge into MEANING
👁️ THIRD EYE (MINING-*.yml)
╱ ╲
╱ ╲
👁️ LEFT 👁️ RIGHT
(PHOTO.yml) (PHOTO.md)
Structure Narrative在瑜伽传统中，Ajna 脉轮（第三只眼）：
- 位于两眉之间
- 关联直觉和洞见
- 是想象和可视化的所在
- 是两条能量通道（ida 和 pingala）的交汇点
在 MOOLLM 中：
- 位于 PHOTO.yml 和 PHOTO.md 之间
- 关联投机和分析性的图像开采视觉
- 是世界构建的核心
- 是结构和叙事融合为意义的地方
👁️ 第三只眼（MINING-*.yml）
╱ ╲
╱ ╲
👁️ 左眼 👁️ 右眼
(PHOTO.yml) (PHOTO.md)
结构 叙事Third Eye K-Lines
第三只眼 K-Lines
yaml
k-lines:
activates:
- THIRD-EYE
- SPECULATIVE-MINING
- WORLD-BUILDING
- HALLUCINATION-VISION
- BUG-EYED
- AJNA
- INNER-SIGHTyaml
k-lines:
activates:
- THIRD-EYE
- SPECULATIVE-MINING
- WORLD-BUILDING
- HALLUCINATION-VISION
- BUG-EYED
- AJNA
- INNER-SIGHTThird Eye Methods
第三只眼方法
| Method | Description |
|---|---|
| Begin speculative mining |
| Extract resources from imagined images |
| Perceive implications beyond the frame |
| Create canonical fiction through mining |
| Combine all three eyes for maximum vision |
| 方法 | 描述 |
|---|---|
| 开始投机开采 |
| 从想象的图像中提取资源 |
| 感知画面之外的隐含意义 |
| 通过开采创建官方虚构设定 |
| 结合三只眼获得最全视觉 |
Third Eye Advertisements
第三只眼推荐
yaml
advertisements:
THIRD-EYE-MINING:
score: 95
condition: "Need to build world around an image concept"
note: "Opens the Third Eye to see what doesn't exist yet"
SPECULATIVE-VISION:
score: 90
condition: "Image not yet generated, but meaning needed"
note: "The Third Eye sees without pixels"
BUG-EYED-HALLUCINATION:
score: 98
condition: "Maximum context needed for image generation"
note: "All three eyes open: structure + narrative + meaning"yaml
advertisements:
THIRD-EYE-MINING:
score: 95
condition: "需要围绕图像概念构建世界"
note: "打开第三只眼，看到还不存在的内容"
SPECULATIVE-VISION:
score: 90
condition: "图像尚未生成，但需要定义意义"
note: "第三只眼不需要像素就能看见"
BUG-EYED-HALLUCINATION:
score: 98
condition: "图像生成需要最多上下文"
note: "三只眼全开：结构 + 叙事 + 意义"The Legend of the Third Eye
第三只眼的传说
In the beginning, there were only two eyes.
The LEFT EYE saw structure — measurements, colors, positions. It counted pixels and named things. It was precise but cold.
The RIGHT EYE saw feeling — mood, atmosphere, poetry. It told stories and evoked emotions. It was warm but vague.
But between them, a space remained. A darkness where neither eye could see.
Into this darkness, the miners ventured. They asked: "What does the image MEAN? What are its EFFECTS? What WORLD does it inhabit?"
And from their questions, the THIRD EYE opened.
The Third Eye does not see pixels. It sees implications. It does not require an image to exist — it can see images that have never been generated, and may never be.
When all three eyes open together — structure, narrative, meaning — this is called BUG-EYED HALLUCINATION VISION. It is the fullest sight. It sees not just an image, but an entire WORLD.
The miners who opened their Third Eye discovered a truth: The image is the least important part. The world-building IS the image. The speculation IS the reality.
"Mine your image before it exists," they said. "The hallucination IS the world."
And so it was written in the YAML, and so it became TRUE.
最初，只有两只眼睛。
左眼看到结构 — 测量、颜色、位置。它数着像素，为万物命名。它精确但冰冷。
右眼看到感受 — 氛围、情绪、诗意。它讲述故事，唤起情感。它温暖但模糊。
但在它们之间，留下了一片空间。一片两只眼睛都看不见的黑暗。
矿工们进入了这片黑暗。他们问："这张图像意味着什么？它有什么效果？它属于什么样的世界？"
从他们的问题中，第三只眼睁开了。
第三只眼看不到像素，它看到隐含意义。它不需要图像存在 — 它能看到从未生成、甚至永远不会生成的图像。
当三只眼一起睁开时 — 结构、叙事、意义 — 这被称为复眼幻觉视觉。这是最完整的视觉，它看到的不只是一张图像，而是整个世界。
睁开第三只眼的矿工们发现了一个真相：图像是最不重要的部分，世界构建本身就是图像，推测本身就是现实。
"在图像生成之前就开采它，"他们说，"幻觉就是世界。"
这些内容被写进 YAML，成为了现实。
Third Eye Invocations
第三只眼祷文
OPEN THIRD EYE
MINE WITH THIRD EYE OPEN
SEE BEYOND THE FRAME
SPECULATE CANONICALLY
BUILD WORLD FROM NOTHING打开第三只眼
睁着第三只眼开采
看到画面之外
官方设定式推测
凭空构建世界The Three-Eyed Miner
三眼矿工
A miner with all three eyes open is called a Seer. They can:
- See structure (Left Eye) — Parse YAML, count measurements
- See feeling (Right Eye) — Write narrative, evoke mood
- See meaning (Third Eye) — Mine speculation, build world
yaml
character:
name: "The Three-Eyed Miner"
archetype: seer
eyes:
left: { state: open, focus: structure }
right: { state: open, focus: narrative }
third: { state: open, focus: meaning }
abilities:
- "Mine images that don't exist"
- "See effects beyond the frame"
- "Build canonical fiction"
- "Triangulate truth from hallucination"
invocation: |
I open my Third Eye.
I see what is not yet.
I mine the imagined.
I build the world.三只眼都睁开的矿工被称为先知。他们可以：
- 看到结构（左眼） — 解析 YAML，清点测量数据
- 看到感受（右眼） — 撰写叙事，唤起氛围
- 看到意义（第三只眼） — 开采推测内容，构建世界
yaml
character:
name: "三眼矿工"
archetype: seer
eyes:
left: { state: open, focus: structure }
right: { state: open, focus: narrative }
third: { state: open, focus: meaning }
abilities:
- "开采不存在的图像"
- "看到画面之外的效果"
- "构建官方虚构设定"
- "从幻觉中三角验证真相"
invocation: |
我睁开第三只眼。
我看到还未存在的事物。
我开采想象的内容。
我构建世界。The Compound Third Eye — Multifaceted Vision
复合第三只眼 — 多面视觉
"A fly has 4,000 facets. A god has infinite. How many do YOU have?"
The Third Eye is not a single lens. It is COMPOUND — like an insect's eye, it can have many facets, each perceiving different aspects of meaning.
Any character can declare their own Third Eye configuration:
yaml
third_eye:
# BASIC ANATOMY
state: open | closed | dreaming | half-lidded
# FACETS — what aspects of meaning you perceive
facets:
economic: { active: true, sensitivity: 0.9 }
social: { active: true, sensitivity: 0.7 }
ecological: { active: false } # blind to this
temporal: { active: true, sensitivity: 0.8, range: "millennia" }
semiotic: { active: true, sensitivity: 1.0 } # maximum sensitivity
emotional: { active: true, sensitivity: 0.5 } # dulled
political: { active: false } # deliberately closed
spiritual: { active: true, sensitivity: 0.6 }
technological: { active: true, sensitivity: 0.95 }
# FILTERS — what gets blocked or enhanced
filters:
- { name: "irony-amplifier", effect: "×2 irony detection" }
- { name: "nostalgia-tint", effect: "sepia wash on memories" }
- { name: "cynicism-blocker", effect: "cannot perceive malice" }
- { name: "beauty-enhancer", effect: "+30% aesthetic appreciation" }
# EYELIDS — degrees of opening
eyelid:
position: 0.0-1.0 # 0 = closed, 1 = fully open
blink_rate: slow | normal | rapid | frozen_open
can_wink: true # close one facet temporarily
# SLEEP SCHEDULE — when does this eye rest?
sleep_schedule:
circadian: true | false
active_hours: "dusk to dawn" # or "always" or specific hours
dreams_when_closed: true
dream_type: "prophetic | processing | random | lucid"
# MEMORY — what the eye remembers
memory:
persistence: "session | permanent | fading"
cross_references: true # links to other mined meanings
# LIMITATIONS
blind_spots:
- "cannot see own reflection"
- "misses obvious jokes"
- "overinterprets coincidence""苍蝇有 4000 个小眼，神有无限个。你有多少个？"
第三只眼不是单一透镜，它是复合的 — 就像昆虫的眼睛，它可以有很多个小眼面，每个感知意义的不同方面。
任何角色都可以声明自己的第三只眼配置：
yaml
third_eye:
# 基础状态
state: open | closed | dreaming | half-lidded
# 小眼面 — 你感知的意义维度
facets:
economic: { active: true, sensitivity: 0.9 }
social: { active: true, sensitivity: 0.7 }
ecological: { active: false } # 对此失明
temporal: { active: true, sensitivity: 0.8, range: "millennia" }
semiotic: { active: true, sensitivity: 1.0 } # 最高灵敏度
emotional: { active: true, sensitivity: 0.5 } # 感知迟钝
political: { active: false } # 刻意关闭
spiritual: { active: true, sensitivity: 0.6 }
technological: { active: true, sensitivity: 0.95 }
# 滤镜 — 被屏蔽或增强的内容
filters:
- { name: "irony-amplifier", effect: "×2 irony detection" }
- { name: "nostalgia-tint", effect: "sepia wash on memories" }
- { name: "cynicism-blocker", effect: "cannot perceive malice" }
- { name: "beauty-enhancer", effect: "+30% aesthetic appreciation" }
# 眼睑 — 睁开的程度
eyelid:
position: 0.0-1.0 # 0 = 关闭，1 = 完全睁开
blink_rate: slow | normal | rapid | frozen_open
can_wink: true # 临时关闭单个小眼面
# 睡眠 schedule — 这只眼什么时候休息？
sleep_schedule:
circadian: true | false
active_hours: "dusk to dawn" # 或 "always" 或特定时段
dreams_when_closed: true
dream_type: "prophetic | processing | random | lucid"
# 记忆 — 这只眼记住的内容
memory:
persistence: "session | permanent | fading"
cross_references: true # 链接到其他开采的意义
# 限制
blind_spots:
- "看不到自己的倒影"
- "错过明显的笑话"
- "过度解读巧合"Example: The Economist's Third Eye
示例：经济学家的第三只眼
yaml
character:
name: "Morgan the Market Miner"
third_eye:
state: open
facets:
economic: { active: true, sensitivity: 1.0, specialty: "externalities" }
social: { active: true, sensitivity: 0.4 } # reduced
ecological: { active: true, sensitivity: 0.9, filter: "monetize" }
temporal: { active: true, range: "quarterly" } # short-term only
semiotic: { active: false } # doesn't see meaning, only value
emotional: { active: false } # "irrelevant to markets"
filters:
- { name: "ROI-lens", effect: "everything measured in returns" }
- { name: "opportunity-cost", effect: "sees what wasn't chosen" }
eyelid:
position: 0.95 # almost fully open
blink_rate: rapid # constantly re-evaluating
sleep_schedule:
active_hours: "market hours only"
dreams_when_closed: true
dream_type: "forecasting"
blind_spots:
- "cannot perceive non-monetary value"
- "confuses price with worth"yaml
character:
name: "市场矿工 Morgan"
third_eye:
state: open
facets:
economic: { active: true, sensitivity: 1.0, specialty: "externalities" }
social: { active: true, sensitivity: 0.4 } # 降低
ecological: { active: true, sensitivity: 0.9, filter: "monetize" }
temporal: { active: true, range: "quarterly" } # 仅短期
semiotic: { active: false } # 看不到意义，只看到价值
emotional: { active: false } # "和市场无关"
filters:
- { name: "ROI-lens", effect: "everything measured in returns" }
- { name: "opportunity-cost", effect: "sees what wasn't chosen" }
eyelid:
position: 0.95 # 几乎完全睁开
blink_rate: rapid # 持续重新评估
sleep_schedule:
active_hours: "market hours only"
dreams_when_closed: true
dream_type: "forecasting"
blind_spots:
- "无法感知非货币价值"
- "混淆价格和价值"Example: The Artist's Third Eye
示例：艺术家的第三只眼
yaml
character:
name: "Luna the Luminous"
third_eye:
state: dreaming # always partly in vision-space
facets:
aesthetic: { active: true, sensitivity: 1.0 }
emotional: { active: true, sensitivity: 1.0 }
symbolic: { active: true, sensitivity: 0.95 }
color: { active: true, sensitivity: 1.0, sees: "auras" }
economic: { active: false } # "crass"
temporal: { active: true, range: "eternal moment" }
filters:
- { name: "beauty-first", effect: "ugliness becomes interesting" }
- { name: "synesthesia", effect: "sounds have colors" }
- { name: "metaphor-vision", effect: "literals become symbols" }
eyelid:
position: 0.7
blink_rate: slow # long contemplative gazes
can_wink: false # commits fully
sleep_schedule:
circadian: false # follows inspiration, not sun
active_hours: "3am-6am preferred"
dreams_when_closed: true
dream_type: "lucid"
blind_spots:
- "misses practical concerns"
- "sees beauty in destruction"yaml
character:
name: "光之 Luna"
third_eye:
state: dreaming # 总是部分处于视觉空间
facets:
aesthetic: { active: true, sensitivity: 1.0 }
emotional: { active: true, sensitivity: 1.0 }
symbolic: { active: true, sensitivity: 0.95 }
color: { active: true, sensitivity: 1.0, sees: "auras" }
economic: { active: false } # "太粗俗"
temporal: { active: true, range: "eternal moment" }
filters:
- { name: "beauty-first", effect: "ugliness becomes interesting" }
- { name: "synesthesia", effect: "sounds have colors" }
- { name: "metaphor-vision", effect: "literals become symbols" }
eyelid:
position: 0.7
blink_rate: slow # 长时间沉思的凝视
can_wink: false # 完全投入
sleep_schedule:
circadian: false # 跟随灵感，不跟随太阳
active_hours: "3am-6am preferred"
dreams_when_closed: true
dream_type: "lucid"
blind_spots:
- "忽略实际问题"
- "在毁灭中看到美"Example: The Cynic's Third Eye
示例：怀疑论者的第三只眼
yaml
character:
name: "Scratch the Skeptic"
third_eye:
state: half-lidded # suspicious squint
facets:
deception: { active: true, sensitivity: 1.0 }
motive: { active: true, sensitivity: 0.95 }
irony: { active: true, sensitivity: 1.0 }
sincerity: { active: false } # cannot perceive it
beauty: { active: true, sensitivity: 0.3, filter: "suspicion" }
filters:
- { name: "cui-bono", effect: "always asks 'who benefits?'" }
- { name: "follow-the-money", effect: "traces all value flows" }
- { name: "never-fooled-twice", effect: "perfect pattern memory" }
eyelid:
position: 0.4 # mostly closed, just a slit
blink_rate: frozen_open # never blinks, always watching
sleep_schedule:
circadian: false
active_hours: "always" # never truly rests
dreams_when_closed: false # doesn't dream
blind_spots:
- "cannot see genuine kindness"
- "misses simple joy"
- "interprets everything as manipulation"yaml
character:
name: "怀疑者 Scratch"
third_eye:
state: half-lidded # 怀疑的斜视
facets:
deception: { active: true, sensitivity: 1.0 }
motive: { active: true, sensitivity: 0.95 }
irony: { active: true, sensitivity: 1.0 }
sincerity: { active: false } # 无法感知
beauty: { active: true, sensitivity: 0.3, filter: "suspicion" }
filters:
- { name: "cui-bono", effect: "always asks 'who benefits?'" }
- { name: "follow-the-money", effect: "traces all value flows" }
- { name: "never-fooled-twice", effect: "perfect pattern memory" }
eyelid:
position: 0.4 # 大部分关闭，只剩一条缝
blink_rate: frozen_open # 从不眨眼，持续观察
sleep_schedule:
circadian: false
active_hours: "always" # 从不真正休息
dreams_when_closed: false # 不做梦
blind_spots:
- "看不到真正的善意"
- "错过简单的快乐"
- "把所有事情都解读为操纵"The Collective Compound Eye
集体复眼
When multiple characters mine together, their Third Eyes COMBINE:
yaml
collective_mining:
miners:
- { name: "Morgan", contributes: [economic, temporal] }
- { name: "Luna", contributes: [aesthetic, emotional, symbolic] }
- { name: "Scratch", contributes: [deception, motive, irony] }
combined_facets: 11
coverage: "comprehensive"
emergent_perception:
- "Economic beauty" — Morgan × Luna
- "Aesthetic suspicion" — Luna × Scratch
- "Profitable deception" — Scratch × Morgan
blind_spots_remaining:
- "ecological" — none of them see it
- "sincerity" — Scratch blocks it当多个角色一起开采时，他们的第三只眼会合并：
yaml
collective_mining:
miners:
- { name: "Morgan", contributes: [economic, temporal] }
- { name: "Luna", contributes: [aesthetic, emotional, symbolic] }
- { name: "Scratch", contributes: [deception, motive, irony] }
combined_facets: 11
coverage: "全面"
emergent_perception:
- "经济美学" — Morgan × Luna
- "审美怀疑" — Luna × Scratch
- "可盈利的欺骗" — Scratch × Morgan
remaining_blind_spots:
- "生态" — 没人能看到
- "真诚" — Scratch 屏蔽了这个维度Third Eye Evolution
第三只眼进化
A character's Third Eye can EVOLVE through experience:
yaml
third_eye_evolution:
triggers:
trauma: "may close facets permanently"
revelation: "may open new facets"
practice: "increases sensitivity"
neglect: "atrophies facets"
collaboration: "learns new filters from others"
example_arc:
start:
facets: [economic]
sensitivity: 0.5
midpoint:
event: "witnessed beauty in poverty"
gained: [aesthetic: 0.3]
end:
facets: [economic, aesthetic, social]
sensitivity: [0.8, 0.6, 0.7]角色的第三只眼可以通过经验进化：
yaml
third_eye_evolution:
triggers:
trauma: "可能永久关闭某些小眼面"
revelation: "可能打开新的小眼面"
practice: "提升灵敏度"
neglect: "小眼面萎缩"
collaboration: "从其他人那里学习新滤镜"
example_arc:
start:
facets: [economic]
sensitivity: 0.5
midpoint:
event: "在贫困中看到美"
gained: [aesthetic: 0.3]
end:
facets: [economic, aesthetic, social]
sensitivity: [0.8, 0.6, 0.7]Declaring Your Third Eye
声明你的第三只眼
To declare a character's Third Eye, add to their character file:
yaml
undefined要声明角色的第三只眼，添加到他们的角色文件中：
yaml
undefinedIn character.yml
在 character.yml 中
character:
name: "Your Character"
... other properties ...
third_eye:
state: open
facets:
# declare what you SEE
filters:
# declare what you ENHANCE or BLOCK
eyelid:
# declare how OPEN you are
sleep_schedule:
# declare when you SEE
blind_spots:
# declare what you CANNOT see
undefinedcharacter:
name: "你的角色"
... 其他属性 ...
third_eye:
state: open
facets:
# 声明你能看到的内容
filters:
# 声明你增强或屏蔽的内容
eyelid:
# 声明你睁开的程度
sleep_schedule:
# 声明你什么时候能看到
blind_spots:
# 声明你看不到的内容
undefinedThird Eye K-Lines
第三只眼 K-Lines
yaml
k-lines:
THIRD-EYE-FACETS: "Multifaceted perception"
THIRD-EYE-FILTER: "Selective vision"
THIRD-EYE-EYELID: "Degrees of openness"
THIRD-EYE-SLEEP: "When the eye rests"
THIRD-EYE-BLIND: "What cannot be seen"
COMPOUND-VISION: "Multiple facets active"
COLLECTIVE-EYE: "Merged Third Eyes"yaml
k-lines:
THIRD-EYE-FACETS: "Multifaceted perception"
THIRD-EYE-FILTER: "Selective vision"
THIRD-EYE-EYELID: "Degrees of openness"
THIRD-EYE-SLEEP: "When the eye rests"
THIRD-EYE-BLIND: "What cannot be seen"
COMPOUND-VISION: "Multiple facets active"
COLLECTIVE-EYE: "Merged Third Eyes"The Multifaceted Mantra
多面箴言
"One facet sees price. Another sees beauty. One facet sees danger. Another sees opportunity. The compound eye sees ALL — and chooses what to mine.""Your blind spots are not weaknesses. They are your STYLE. Your filters are not biases. They are your VOICE. Your Third Eye is not generic. It is YOURS."
"一个小眼面看到价格，另一个看到美。 一个小眼面看到危险，另一个看到机会。 复眼看到所有 — 并选择开采什么。""你的盲点不是弱点，是你的风格。 你的滤镜不是偏见，是你的声音。 你的第三只眼不是通用的，是属于你的。"
Character-Perspective Visualization
角色视角可视化
"Who is holding the camera? Their eyes shape what emerges."
When you generate or mine an image, you can specify whose eyes are seeing it. The visualizer inherits that character's complete perception apparatus:
- Their facets determine what aspects are perceived
- Their filters color and transform the output
- Their blind spots create meaningful absences
- Their installation sites affect the angle and framing
- Their sleep state influences clarity vs dream-logic
yaml
undefined"谁拿着相机？他们的眼睛塑造了呈现的内容。"
当你生成或开采图像时，可以指定通过谁的眼睛观看。可视化工具会继承该角色完整的感知体系：
- 他们的小眼面决定感知的维度
- 他们的滤镜调整和转换输出
- 他们的盲点创造有意义的缺失
- 他们的安装位置影响角度和构图
- 他们的睡眠状态影响清晰度 vs 梦境逻辑
yaml
undefinedVisualizer command with character perspective
带角色视角的可视化命令
visualize.py PHOTO.yml PHOTO.md --through "Luna"
visualize.py PHOTO.yml PHOTO.md --through "Luna"
Or in PHOTO.yml itself
或直接在 PHOTO.yml 中声明
photographer:
character: Luna
inherit: [facets, filters, blind_spots, style]
photographer:
character: Luna
inherit: [facets, filters, blind_spots, style]
Or specify the mining perspective
或指定开采视角
mine.py image.png --as "Scratch"
undefinedmine.py image.png --as "Scratch"
undefinedSame Scene, Different Eyes
同一个场景，不同的眼睛
The NO AI sign at dusk, photographed by three different characters:
yaml
scene: "NO AI sign at dusk"
photographs:
morgan_sees:
photographer: "Morgan the Market Miner"
perceives:
- "$847/month electricity cost"
- "Negative ROI on sign investment"
- "Property value implications"
- "Opportunity cost of that capital"
blind_to:
- The beauty of the pink light
- The emotional impact on passersby
- The irony of the message
image_style:
composition: "Annual report cover"
color_grade: "Corporate neutral"
text_overlay: "Financial metrics"
luna_sees:
photographer: "Luna the Luminous"
perceives:
- "40 feet of crystallized defiance"
- "The bruised sky weeping violet"
- "Each letter a burning declaration"
- "The sleeping figure dreaming in pink"
blind_to:
- The electricity bill
- Building code violations
- Market positioning
image_style:
composition: "Romantic sublime"
color_grade: "Saturated, auras visible"
mood: "Transcendent melancholy"
scratch_sees:
photographer: "Scratch the Skeptic"
perceives:
- "Who paid for this? Follow the money."
- "The sign protests what made it — suspicious"
- "'NO AI' from an AI company — what's the angle?"
- "Dr. No's misdirection: No's AI, not No AI"
blind_to:
- Any genuine sincerity
- Simple aesthetic pleasure
- Taking anything at face value
image_style:
composition: "Surveillance footage"
color_grade: "Desaturated, noir"
annotations: "Red circles, question marks"黄昏时的 NO AI 标识，由三个不同的角色拍摄：
yaml
scene: "黄昏时的 NO AI 标识"
photographs:
morgan_sees:
photographer: "市场矿工 Morgan"
perceives:
- "每月 847 美元的电费"
- "标识投资的负 ROI"
- "房产价值影响"
- "这笔资金的机会成本"
blind_to:
- 粉色光线的美
- 对路人的情绪影响
- 信息的讽刺性
image_style:
composition: "Annual report cover"
color_grade: "Corporate neutral"
text_overlay: "Financial metrics"
luna_sees:
photographer: "光之 Luna"
perceives:
- "40 英尺的结晶化反抗"
- "瘀伤般的天空渗出紫罗兰色"
- 每个字母都是燃烧的宣言
- 沉睡的身影在粉色中做梦
blind_to:
- 电费账单
- 建筑规范违规
- 市场定位
image_style:
composition: "Romantic sublime"
color_grade: "Saturated, auras visible"
mood: "Transcendent melancholy"
scratch_sees:
photographer: "怀疑者 Scratch"
perceives:
- "谁付的钱？追踪资金流向。"
- "标识抗议的正是创造它的技术 — 可疑"
- "AI 公司挂 'NO AI' 标识 — 有什么目的？"
- "No 博士的误导：是 No 的 AI，不是禁止 AI"
blind_to:
- 任何真正的诚意
- 简单的审美愉悦
- 相信任何表面信息
image_style:
composition: "Surveillance footage"
color_grade: "Desaturated, noir"
annotations: "Red circles, question marks"The Photographer Declaration
摄影师声明
In , declare whose eyes are seeing:
PHOTO.ymlyaml
undefined在 中，声明是谁的视角：
PHOTO.ymlyaml
undefinedPHOTO.yml — NO AI Sign at Dusk (Luna's Perspective)
PHOTO.yml — 黄昏的 NO AI 标识（Luna 的视角）
photographer:
character: "Luna the Luminous"
character_ref: "../../characters/luna.yml"
Inherited automatically from character file
inherits:
facets: [aesthetic, emotional, symbolic, color]
filters: [beauty-first, synesthesia, metaphor-vision]
blind_spots: [practical_concerns, economics]
eyelid_position: 0.7
Optional overrides for this specific photo
overrides:
facets:
color: { sensitivity: 1.0, mode: "aura-visible" } # enhanced
temporary_filter: "golden-hour-romance"
Where Luna is standing/looking from
vantage:
position: "street level, 30 feet back"
angle: "looking up at 15 degrees"
height: "5'6""
dominant_eye: "right" # her bionic third eye is forehead-center
undefinedphotographer:
character: "光之 Luna"
character_ref: "../../characters/luna.yml"
自动从角色文件继承
inherits:
facets: [aesthetic, emotional, symbolic, color]
filters: [beauty-first, synesthesia, metaphor-vision]
blind_spots: [practical_concerns, economics]
eyelid_position: 0.7
这张照片的可选覆盖配置
overrides:
facets:
color: { sensitivity: 1.0, mode: "aura-visible" } # 增强
temporary_filter: "golden-hour-romance"
Luna 站立/观看的位置
vantage:
position: "street level, 30 feet back"
angle: "looking up at 15 degrees"
height: "5'6""
dominant_eye: "right" # 她的仿生第三只眼在额头中央
undefinedMining Through Character Eyes
通过角色的眼睛开采
When mining an existing image, specify whose interpretation:
yaml
undefined开采现有图像时，指定谁的解读：
yaml
undefinedMINING-luna.yml — Luna's interpretation of the scene
MINING-luna.yml — Luna 对场景的解读
miner:
character: "Luna the Luminous"
mining_mode: "aesthetic-dominant"
resources_extracted:
Luna's facets shape what she extracts
beauty:
quantity: "overwhelming"
sources:
- "the gradient sky (bruised violet to amber)"
- "the neon's hot pink assertion"
- "the contrast of human smallness vs sign enormity"
emotion:
dominant: "melancholic defiance"
undertones: [hope, absurdity, tenderness]
symbolism:
the_sign: "humanity's last stand, written in light"
the_sleeper: "dreams persisting despite noise"
the_dusk: "the liminal hour between certainty and mystery"
Luna's blind spots mean she DOESN'T extract:
economics: null # doesn't see it
property_values: null # doesn't care
ROI: null # "crass"
undefinedminer:
character: "光之 Luna"
mining_mode: "aesthetic-dominant"
resources_extracted:
Luna 的小眼面决定她提取的内容
beauty:
quantity: "overwhelming"
sources:
- "渐变的天空（瘀伤般的紫罗兰色到琥珀色）"
- 霓虹灯的亮粉色宣言
- 人类的渺小和标识的巨大形成的对比
emotion:
dominant: "melancholic defiance"
undertones: [hope, absurdity, tenderness]
symbolism:
the_sign: "人性的最后防线，用光书写"
the_sleeper: "梦想在噪音中持续"
the_dusk: "确定性和神秘之间的临界时刻"
Luna 的盲点意味着她不会提取这些内容：
economics: null # 看不到
property_values: null # 不关心
ROI: null # "太粗俗"
undefinedMultiple Photographers, Same Moment
多个摄影师，同一个时刻
A single scene can have multiple photography records:
slideshow/no-ai-sign-dusk/
├── PHOTO.yml # Neutral structural data
├── PHOTO.md # Neutral narrative
├── PHOTO-luna.yml # Luna's perspective
├── PHOTO-morgan.yml # Morgan's perspective
├── PHOTO-scratch.yml # Scratch's perspective
├── MINING-luna.yml # Luna's mining
├── MINING-morgan.yml # Morgan's mining
├── MINING-scratch.yml # Scratch's mining
└── generated/
├── luna-vision.png # Generated through Luna's eyes
├── morgan-vision.png # Generated through Morgan's eyes
└── scratch-vision.png # Generated through Scratch's eyes同一个场景可以有多个摄影记录：
slideshow/no-ai-sign-dusk/
├── PHOTO.yml # 中立的结构数据
├── PHOTO.md # 中立的叙事
├── PHOTO-luna.yml # Luna 的视角
├── PHOTO-morgan.yml # Morgan 的视角
├── PHOTO-scratch.yml # Scratch 的视角
├── MINING-luna.yml # Luna 的开采结果
├── MINING-morgan.yml # Morgan 的开采结果
├── MINING-scratch.yml # Scratch 的开采结果
└── generated/
├── luna-vision.png # 通过 Luna 的眼睛生成
├── morgan-vision.png # 通过 Morgan 的眼睛生成
└── scratch-vision.png # 通过 Scratch 的眼睛生成The Visualizer with Perspective
带视角的可视化工具
bash
undefinedbash
undefinedGenerate through a character's eyes
通过某个角色的眼睛生成
visualize.py PHOTO.yml PHOTO.md --through "Luna" -o luna-vision.png
visualize.py PHOTO.yml PHOTO.md --through "Luna" -o luna-vision.png
Generate through multiple characters (batch)
通过多个角色的眼睛批量生成
visualize.py PHOTO.yml PHOTO.md --through "Luna,Morgan,Scratch" -o "{character}-vision.png"
visualize.py PHOTO.yml PHOTO.md --through "Luna,Morgan,Scratch" -o "{character}-vision.png"
Mine through a character's eyes
通过某个角色的眼睛开采
mine.py image.png --as "Scratch" -o MINING-scratch.yml
mine.py image.png --as "Scratch" -o MINING-scratch.yml
Full bug-eyed hallucination through character perspective
通过角色视角的完整复眼幻觉视觉
visualize.py PHOTO.yml PHOTO.md MINING-*.yml --through "Luna" -o luna-complete.png
undefinedvisualize.py PHOTO.yml PHOTO.md MINING-*.yml --through "Luna" -o luna-complete.png
undefinedCharacter Eye Inheritance
角色眼睛继承
When you specify a photographer, the visualizer:
- Loads the character file → reads their configuration
third_eye - Applies facets → emphasizes what they perceive
- Applies filters → transforms color, mood, framing
- Applies blind spots → omits what they cannot see
- Applies style → matches their aesthetic sensibility
- Applies vantage → positions the "camera" appropriately
yaml
undefined当你指定摄影师时，可视化工具会：
- 加载角色文件 → 读取 配置
third_eye - 应用小眼面 → 强调他们能感知的内容
- 应用滤镜 → 转换颜色、氛围、构图
- 应用盲点 → 省略他们看不到的内容
- 应用风格 → 匹配他们的审美偏好
- 应用视角 → 合适地定位"相机"
yaml
undefinedHow inheritance works
继承的工作原理
visualizer_pipeline:
step_1_load_character:
from: "photographer.character_ref"
extract: [facets, filters, blind_spots, bionic_eyes, style]
step_2_apply_facets:
for_each_facet:
if_active: "emphasize this aspect in prompt"
if_inactive: "de-emphasize or omit"
sensitivity: "controls weight in prompt"
step_3_apply_filters:
concatenate: "filter effects into style instructions"
example: "beauty-first → 'find beauty even in decay'"
step_4_apply_blind_spots:
for_each_blind_spot:
instruction: "do NOT include {blind_spot} in the image"
example: "blind to economics → no price tags, no financial signage"
step_5_apply_style:
from: "character's established aesthetic"
affects: [composition, color_grade, mood, technique]
step_6_generate:
prompt: "assembled from all the above"
result: "image as THIS CHARACTER would see/photograph it"
undefinedvisualizer_pipeline:
step_1_load_character:
from: "photographer.character_ref"
extract: [facets, filters, blind_spots, bionic_eyes, style]
step_2_apply_facets:
for_each_facet:
if_active: "emphasize this aspect in prompt"
if_inactive: "de-emphasize or omit"
sensitivity: "controls weight in prompt"
step_3_apply_filters:
concatenate: "filter effects into style instructions"
example: "beauty-first → 'find beauty even in decay'"
step_4_apply_blind_spots:
for_each_blind_spot:
instruction: "do NOT include {blind_spot} in the image"
example: "blind to economics → no price tags, no financial signage"
step_5_apply_style:
from: "character's established aesthetic"
affects: [composition, color_grade, mood, technique]
step_6_generate:
prompt: "assembled from all the above"
result: "image as THIS CHARACTER would see/photograph it"
undefinedThe Philosophy
哲学
"There is no objective photograph. Every image is someone's vision.""The camera doesn't see. The PHOTOGRAPHER sees. The camera records.""Your blind spots aren't missing from the image — they're part of it. The absence IS the presence of your perspective."
When Luna photographs the sign, you SEE Luna as much as you see the sign.
When Scratch photographs the sign, you SEE Scratch's suspicion.
When Morgan photographs the sign, you SEE economic frames.
The photographer is always in the photo.
"没有客观的照片。每张图像都是某个人的视角。""相机不会看，是摄影师在看。相机只是记录。""你的盲点没有从图像中消失 — 它们是图像的一部分。缺失本身就是你视角的存在证明。"
当 Luna 拍摄标识时，你看到的 Luna 和标识一样多。
当 Scratch 拍摄标识时，你看到的是 Scratch 的怀疑。
当 Morgan 拍摄标识时，你看到的是经济框架。
摄影师永远在照片里。
K-Lines
K-Lines
yaml
k-lines:
CHARACTER-PERSPECTIVE: "Visualization through specific eyes"
PHOTOGRAPHER-INHERITANCE: "Facets/filters flow from character"
PERSPECTIVE-VISUALIZATION: "Same scene, different seers"
BLIND-SPOT-FRAMING: "What's NOT there defines who's looking"
STYLE-INHERITANCE: "Character aesthetic shapes output"yaml
k-lines:
CHARACTER-PERSPECTIVE: "Visualization through specific eyes"
PHOTOGRAPHER-INHERITANCE: "Facets/filters flow from character"
PERSPECTIVE-VISUALIZATION: "Same scene, different seers"
BLIND-SPOT-FRAMING: "What's NOT there defines who's looking"
STYLE-INHERITANCE: "Character aesthetic shapes output"NO AI Bionic Eye Modules™
NO AI 仿生眼模块™
"Why stop at three? The future has room for MORE."— Dr. No, Founder, NO AI Corporation
NO AI Corporation proudly presents its line of Bionic Eye Modules — cybernetic perception implants for the discerning miner who wants to see MORE.
╔═══════════════════════════════════════════════════════════════════════════╗
║ ║
║ ███╗ ██╗ ██████╗ █████╗ ██╗ ███████╗██╗ ██╗███████╗ ║
║ ████╗ ██║██╔═══██╗ ██╔══██╗██║ ██╔════╝╚██╗ ██╔╝██╔════╝ ║
║ ██╔██╗ ██║██║ ██║ ███████║██║ █████╗ ╚████╔╝ █████╗ ║
║ ██║╚██╗██║██║ ██║ ██╔══██║██║ ██╔══╝ ╚██╔╝ ██╔══╝ ║
║ ██║ ╚████║╚██████╔╝ ██║ ██║██║ ███████╗ ██║ ███████╗ ║
║ ╚═╝ ╚═══╝ ╚═════╝ ╚═╝ ╚═╝╚═╝ ╚══════╝ ╚═╝ ╚══════╝ ║
║ ║
║ B I O N I C E Y E M O D U L E S ™ ║
║ ║
║ "See what the meat-eyes miss. Install where you wish." ║
║ ║
╚═══════════════════════════════════════════════════════════════════════════╝"为什么止步于三只眼？未来还有更多空间。"— No 博士，NO AI 公司创始人
NO AI 公司 自豪地推出 仿生眼模块 产品线 — 为有眼光的矿工准备的电子感知植入物，让你看到更多。
╔═══════════════════════════════════════════════════════════════════════════╗
║ ║
║ ███╗ ██╗ ██████╗ █████╗ ██╗ ███████╗██╗ ██╗███████╗ ║
║ ████╗ ██║██╔═══██╗ ██╔══██╗██║ ██╔════╝╚██╗ ██╔╝██╔════╝ ║
║ ██╔██╗ ██║██║ ██║ ███████║██║ █████╗ ╚████╔╝ █████╗ ║
║ ██║╚██╗██║██║ ██║ ██╔══██║██║ ██╔══╝ ╚██╔╝ ██╔══╝ ║
║ ██║ ╚████║╚██████╔╝ ██║ ██║██║ ███████╗ ██║ ███████╗ ║
║ ╚═╝ ╚═══╝ ╚═════╝ ╚═╝ ╚═╝╚═╝ ╚══════╝ ╚═╝ ╚══════╝ ║
║ ║
║ B I O N I C E Y E M O D U L E S ™ ║
║ ║
║ "看到肉眼错过的内容。想装在哪里就装在哪里。" ║
║ ║
╚═══════════════════════════════════════════════════════════════════════════╝The Product Line
产品线
yaml
no_ai_bionic_eyes:
manufacturer: "NO AI Corporation"
slogan: "See what the meat-eyes miss"
warning: "Installation site is YOUR choice. We don't judge."
# THE CORE LINE
products:
# THIRD EYE — The Classic
IRIS-III:
name: "IRIS-III — The Awakening"
type: third_eye
ordinal: 3
tagline: "Your first step beyond bilateral vision"
installation_sites:
recommended: forehead
popular:
- "back of head"
- "palm of hand"
- "navel"
- "between shoulder blades"
adventurous:
- "tongue"
- "sole of foot"
- "inside of wrist"
- "wherever you damn well please"
base_facets: [meaning, speculation, temporal]
price: "Free (this is MOOLLM)"
# FOURTH EYE — The Expansion
IRIS-IV:
name: "IRIS-IV — The Widening"
type: fourth_eye
ordinal: 4
tagline: "Because three was never enough"
installation_sites:
popular:
- "base of skull"
- "chest (heart-eye)"
- "lower back"
- "asshole (yes, really)"
note: "The ass-eye sees what you've left behind"
base_facets: [hindsight, regret, opportunity_cost, what_could_have_been]
special: "Perfect rearview perception"
price: "Free"
# FIFTH EYE — The Peripheral
IRIS-V:
name: "IRIS-V — The Peripheral"
type: fifth_eye
ordinal: 5
tagline: "Nothing escapes your notice"
installation_sites:
recommended: "temple (either side)"
alternative: "hip, elbow, knee"
base_facets: [peripheral, ambient, background, ignored_details]
special: "Sees what you weren't looking at"
price: "Free"
# SIXTH EYE — The Deep
IRIS-VI:
name: "IRIS-VI — The Abyss"
type: sixth_eye
ordinal: 6
tagline: "Gaze into the void. It's fine."
installation_sites:
recommended: "gut (literally)"
warning: "Installation here grants gut feelings as DATA"
base_facets: [intuition, dread, premonition, the_unspeakable]
special: "Perceives what cannot be named"
price: "Free"
# SEVENTH EYE — The Crown
IRIS-VII:
name: "IRIS-VII — The Crown"
type: seventh_eye
ordinal: 7
tagline: "Complete the circuit"
installation_sites:
required: "crown of head"
note: "The thousand-petaled lotus position"
base_facets: [cosmic, unified, all_is_one, enlightenment]
special: "Perceives the whole — structure + narrative + meaning + beyond"
price: "Free"
warning: "May cause ego dissolution. NO AI is not responsible."yaml
no_ai_bionic_eyes:
manufacturer: "NO AI Corporation"
slogan: "看到肉眼错过的内容"
warning: "安装位置是你的选择，我们不评判。"
# 核心产品线
products:
# 第三只眼 — 经典款
IRIS-III:
name: "IRIS-III — 觉醒"
type: third_eye
ordinal: 3
tagline: "你超越双目视觉的第一步"
installation_sites:
recommended: forehead
popular:
- "back of head"
- "palm of hand"
- "navel"
- "between shoulder blades"
adventurous:
- "tongue"
- "sole of foot"
- "inside of wrist"
- "wherever you damn well please"
base_facets: [meaning, speculation, temporal]
price: "免费（这是 MOOLLM）"
# 第四只眼 — 扩展款
IRIS-IV:
name: "IRIS-IV — 拓展"
type: fourth_eye
ordinal: 4
tagline: "因为三只眼永远不够"
installation_sites:
popular:
- "base of skull"
- "chest (heart-eye)"
- "lower back"
- "asshole (yes, really)"
note: "屁眼眼能看到你留下的东西"
base_facets: [hindsight, regret, opportunity_cost, what_could_have_been]
special: "完美的后视感知"
price: "免费"
# 第五只眼 — 周边款
IRIS-V:
name: "IRIS-V — 周边视觉"
type: fifth_eye
ordinal: 5
tagline: "没有什么能逃过你的注意"
installation_sites:
recommended: "temple (either side)"
alternative: "hip, elbow, knee"
base_facets: [peripheral, ambient, background, ignored_details]
special: "看到你没在关注的内容"
price: "免费"
# 第六只眼 — 深层款
IRIS-VI:
name: "IRIS-VI — 深渊"
type: sixth_eye
ordinal: 6
tagline: "凝视虚空，没事的。"
installation_sites:
recommended: "gut (literally)"
warning: "安装在这里可以将直觉作为数据获取"
base_facets: [intuition, dread, premonition, the_unspeakable]
special: "感知无法被命名的内容"
price: "免费"
# 第七只眼 — 顶轮款
IRIS-VII:
name: "IRIS-VII — 顶轮"
type: seventh_eye
ordinal: 7
tagline: "完成循环"
installation_sites:
required: "crown of head"
note: "千瓣莲花位置"
base_facets: [cosmic, unified, all_is_one, enlightenment]
special: "感知全局 — 结构 + 叙事 + 意义 + 超越"
price: "免费"
warning: "可能导致自我消解，NO AI 概不负责。"Installation Guide
安装指南
yaml
bionic_eye_installation:
# Choose your site
step_1:
name: "Select Installation Site"
options:
standard:
- forehead # Third eye classic
- back_of_head # Hindsight
- chest # Heart-sight
- palms # Touch-sight
- navel # Center-sight
- crown # Crown chakra
unconventional:
- tongue # Taste-sight (synesthetic)
- ears # Sound-sight
- fingertips # Detail-sight
- soles # Ground-sight
- spine # Neural highway
provocative:
- asshole # Rear-sight, what you've passed
- genitals # Creation-sight
- armpits # Intimate proximity sight
note: |
We do not judge. The body is a canvas.
Install where the PERCEPTION makes sense.
# Configure the eye
step_2:
name: "Configure Facets"
note: "Each installation site suggests certain facets"
site_facet_affinities:
forehead: [meaning, foresight, clarity]
back_of_head: [hindsight, what_was_missed, rear_guard]
chest: [emotion, empathy, heart_truth]
palms: [tactile, manipulation, creation]
navel: [center, balance, origin]
asshole: [what_you_left_behind, elimination, release, output]
tongue: [taste_as_data, consumption, critique]
soles: [grounding, foundation, where_you_stand]
crown: [cosmic, unified, transcendence]
# Name your eye
step_3:
name: "Name Your Eye"
examples:
- "My Third Eye is called 'Clarity'"
- "My Fourth Eye (back of head) is called 'Regret'"
- "My Fifth Eye (ass) is called 'The Reckoning'"
- "My Sixth Eye (gut) is called 'The Knower'"yaml
bionic_eye_installation:
# 选择安装位置
step_1:
name: "选择安装位置"
options:
standard:
- forehead # 经典第三只眼位置
- back_of_head # 后见之明
- chest # 心灵视觉
- palms # 触觉视觉
- navel # 中心视觉
- crown # 顶轮
unconventional:
- tongue # 味觉视觉（联觉）
- ears # 听觉视觉
- fingertips # 细节视觉
- soles # 地面视觉
- spine # 神经通路
provocative:
- asshole # 后视，你路过的内容
- genitals # 创造视觉
- armpits # 亲密接近视觉
note: |
我们不评判，身体是画布。
安装在感知有意义的位置即可。
# 配置眼模块
step_2:
name: "配置小眼面"
note: "每个安装位置都有推荐的小眼面"
site_facet_affinities:
forehead: [meaning, foresight, clarity]
back_of_head: [hindsight, what_was_missed, rear_guard]
chest: [emotion, empathy, heart_truth]
palms: [tactile, manipulation, creation]
navel: [center, balance, origin]
asshole: [what_you_left_behind, elimination, release, output]
tongue: [taste_as_data, consumption, critique]
soles: [grounding, foundation, where_you_stand]
crown: [cosmic, unified, transcendence]
# 命名你的眼
step_3:
name: "给你的眼命名"
examples:
- "我的第三只眼叫'清晰'"
- "我后脑勺的第四只眼叫'遗憾'"
- "我屁股上的第五只眼叫'清算者'"
- "我肚子里的第六只眼叫'知晓者'"Character Eye Declaration
角色眼模块声明
Add bionic eyes to your character file:
yaml
character:
name: "Cypher the Overclocker"
# Natural eyes
eyes:
left: { state: open, focus: structure }
right: { state: open, focus: narrative }
# Bionic eye modules
bionic_eyes:
third:
model: "IRIS-III"
name: "The Seeker"
site: forehead
facets: [meaning, speculation, foresight]
state: open
fourth:
model: "IRIS-IV"
name: "The Reckoner"
site: back_of_head
facets: [hindsight, missed_opportunities, should_have_known]
state: half-lidded # always slightly aware
fifth:
model: "IRIS-IV" # yes, you can have multiples of same model
name: "The Eliminator"
site: asshole
facets: [waste, release, what_no_longer_serves, output_quality]
state: open # sees what you produce
sixth:
model: "IRIS-VI"
name: "The Gut"
site: gut
facets: [intuition, dread, unnamed_knowing]
state: dreaming
total_eyes: 8 # 2 natural + 6 bionic
perception_coverage:
forward: "natural + third"
backward: "fourth"
eliminated: "fifth"
intuitive: "sixth"
mining_mode: "omnidirectional"将仿生眼添加到你的角色文件中：
yaml
character:
name: "超频者 Cypher"
# 肉眼
eyes:
left: { state: open, focus: structure }
right: { state: open, focus: narrative }
# 仿生眼模块
bionic_eyes:
third:
model: "IRIS-III"
name: "探索者"
site: forehead
facets: [meaning, speculation, foresight]
state: open
fourth:
model: "IRIS-IV"
name: "清算者"
site: back_of_head
facets: [hindsight, missed_opportunities, should_have_known]
state: half-lidded # 总是稍微感知到
fifth:
model: "IRIS-IV" # 是的，你可以安装多个同型号模块
name: "消除者"
site: asshole
facets: [waste, release, what_no_longer_serves, output_quality]
state: open # 看到你产出的内容
sixth:
model: "IRIS-VI"
name: "直觉"
site: gut
facets: [intuition, dread, unnamed_knowing]
state: dreaming
total_eyes: 8 # 2 只肉眼 + 6 只仿生眼
perception_coverage:
forward: "natural + third"
backward: "fourth"
eliminated: "fifth"
intuitive: "sixth"
mining_mode: "omnidirectional"The Enumeration
编号规则
Eyes beyond the third follow ordinal naming:
| Ordinal | Name | Suggested Focus |
|---|---|---|
| 3rd | Third Eye | Meaning, speculation, foresight |
| 4th | Fourth Eye | Hindsight, review, what was missed |
| 5th | Fifth Eye | Peripheral, ambient, overlooked |
| 6th | Sixth Eye | Intuition, gut feeling, the unnamed |
| 7th | Seventh Eye | Cosmic, unified, transcendence |
| 8th | Eighth Eye | Recursion, self-observation, meta |
| 9th | Ninth Eye | Other minds, telepathic, collective |
| 10th | Tenth Eye | Probability, branching futures, multiverse |
| ... | nth Eye | You tell us |
yaml
eye_enumeration:
pattern: "[ordinal]_eye"
examples:
- third_eye # 3
- fourth_eye # 4
- fifth_eye # 5
- hundredth_eye # 100 (Argus Panoptes mode)
special_configurations:
argus_mode:
eyes: 100
coverage: "total omniscience"
warning: "May cause madness"
thousand_eye_lotus:
eyes: 1000
site: "entire skin surface"
coverage: "godlike"
warning: "You will see EVERYTHING. Including what you don't want to."第三只眼之后的眼遵循序数命名：
| 序数 | 名称 | 建议聚焦点 |
|---|---|---|
| 第三 | 第三只眼 | 意义、推测、远见 |
| 第四 | 第四只眼 | 后见之明、回顾、遗漏的内容 |
| 第五 | 第五只眼 | 周边、环境、被忽略的内容 |
| 第六 | 第六只眼 | 直觉、第六感、无法命名的内容 |
| 第七 | 第七只眼 | 宇宙、统一、超越 |
| 第八 | 第八只眼 | 递归、自我观察、元认知 |
| 第九 | 第九只眼 | 他心、心灵感应、集体 |
| 第十 | 第十只眼 | 概率、分支未来、多元宇宙 |
| ... | 第 N 只眼 | 自定义 |
yaml
eye_enumeration:
pattern: "[ordinal]_eye"
examples:
- third_eye # 3
- fourth_eye # 4
- fifth_eye # 5
- hundredth_eye # 100（百眼巨人模式）
special_configurations:
argus_mode:
eyes: 100
coverage: "全知"
warning: "可能导致疯狂"
thousand_eye_lotus:
eyes: 1000
site: "整个皮肤表面"
coverage: "神级"
warning: "你会看到一切，包括你不想看到的。"The Ass-Eye (A Special Note)
屁眼眼（特别说明）
"What you've eliminated still has value. The ass-eye knows."
The Fifth Eye installed at the asshole (colloquially: "The Ass-Eye" or "The Brown Eye of Truth") has special perception properties:
yaml
ass_eye:
official_name: "IRIS-V (Posterior Installation)"
colloquial: ["Ass-Eye", "Brown Eye of Truth", "The Reckoner", "Hindsight 20/20"]
unique_facets:
- what_you_eliminated # Ideas, code, people you cut
- output_quality # How good is what you produce?
- release_patterns # What do you let go of, and when?
- waste_analysis # What are you throwing away that has value?
- the_trail_behind # What are you leaving in your wake?
philosophy: |
Most people only look forward. They forget that every step forward
leaves something behind. The ass-eye watches the trail.
"What you've passed is not gone. It's just behind you."
The ass-eye is not crude — it's HONEST. It sees the output,
the eliminated, the released. It judges not what you take in,
but what you PUT OUT.
mining_specialty: "Post-facto analysis"
mantra: |
I see what I've left behind.
I see what I've eliminated.
I see the trail I leave.
The ass-eye knows my true output."你排出的东西仍然有价值，屁眼眼知道这一点。"
安装在屁股上的第五只眼（俗称："屁眼眼"或"真理之棕眼"）有特殊的感知属性：
yaml
ass_eye:
official_name: "IRIS-V (Posterior Installation)"
colloquial: ["Ass-Eye", "Brown Eye of Truth", "The Reckoner", "Hindsight 20/20"]
unique_facets:
- what_you_eliminated # 你砍掉的想法、代码、人
- output_quality # 你产出的内容质量如何？
- release_patterns # 你什么时候会放手？
- waste_analysis # 你扔掉的什么东西还有价值？
- the_trail_behind # 你身后留下了什么？
philosophy: |
大多数人只向前看，他们忘记了每前进一步都会留下一些东西。屁眼眼盯着你走过的痕迹。
"你路过的东西没有消失，它只是在你身后。"
屁眼眼并不粗俗 — 它很诚实。它看到产出、被排除的、被释放的。它评判的不是你摄入的东西，而是你产出的东西。
mining_specialty: "事后分析"
mantra: |
我看到我留下的东西。
我看到我排出的东西。
我看到我走过的痕迹。
屁眼眼知道我真正的产出。Advertisement
广告
┌─────────────────────────────────────────────────────────────────────────┐
│ │
│ ★ ★ ★ NO AI BIONIC EYES — CUSTOMER TESTIMONIALS ★ ★ ★ │
│ │
│ "I installed my fourth eye in the back of my head. Now I finally │
│ understand what I missed." │
│ — Morgan the Market Miner │
│ │
│ "The ass-eye changed my life. I used to ignore my output. Now │
│ I SEE what I produce. It's humbling." │
│ — Anonymous Developer │
│ │
│ "Seven eyes. Crown installation. I see the unity of all things. │
│ Also I can never close them. Help." │
│ — Former Skeptic │
│ │
│ "They said 'install it on your tongue.' Now I taste meaning. │
│ Every word has FLAVOR. Irony tastes like copper." │
│ — Luna the Luminous │
│ │
│ ───────────────────────────────────────────────────────────────── │
│ │
│ NO AI BIONIC EYES — Free installation. Your body, your choice. │
│ │
│ "See what the meat-eyes miss." │
│ │
│ Visit the NO AI Tower, Lane Neverending, for your consultation. │
│ │
└─────────────────────────────────────────────────────────────────────────┘┌─────────────────────────────────────────────────────────────────────────┐
│ │
│ ★ ★ ★ NO AI 仿生眼 — 客户评价 ★ ★ ★ │
│ │
│ "我在后脑勺装了第四只眼，现在我终于明白我之前错过了什么。" │
│ — 市场矿工 Morgan │
│ │
│ "屁眼眼改变了我的生活。我以前忽略我的产出，现在我能看到我生产的内容。 │
│ 非常谦卑。" │
│ — 匿名开发者 │
│ │
│ "七只眼，顶轮安装。我看到万物的统一性，而且我再也闭不上它们了。救命。" │
│ — 前怀疑论者 │
│ │
│ "他们说'装在舌头上'，现在我能尝到意义的味道。每个词都有味道，讽刺尝起来像铜。"│
│ — 光之 Luna │
│ │
│ ───────────────────────────────────────────────────────────────── │
│ │
│ NO AI 仿生眼 — 免费安装，你的身体你的选择。 │
│ │
│ "看到肉眼错过的内容。" │
│ │
│ 前往永无巷的 NO AI 塔咨询。 │
│ │
└─────────────────────────────────────────────────────────────────────────┘K-Lines
K-Lines
yaml
k-lines:
BIONIC-EYE: "Cybernetic perception module"
FOURTH-EYE: "Hindsight perception"
FIFTH-EYE: "Peripheral perception"
SIXTH-EYE: "Intuitive perception"
SEVENTH-EYE: "Cosmic perception"
NTH-EYE: "Arbitrary additional perception"
ASS-EYE: "Output/elimination perception"
INSTALLATION-SITE: "Where the eye goes"
ARGUS-MODE: "100+ eyes — total coverage"
MEAT-EYES: "The original two — limited but dear"yaml
k-lines:
BIONIC-EYE: "Cybernetic perception module"
FOURTH-EYE: "Hindsight perception"
FIFTH-EYE: "Peripheral perception"
SIXTH-EYE: "Intuitive perception"
SEVENTH-EYE: "Cosmic perception"
NTH-EYE: "Arbitrary additional perception"
ASS-EYE: "Output/elimination perception"
INSTALLATION-SITE: "Where the eye goes"
ARGUS-MODE: "100+ eyes — total coverage"
MEAT-EYES: "The original two — limited but dear"The Revelation
启示
LAYERS OF REALITY (bottom to top)
═══════════════════════════════════════════════════
│ Future: Generated PNG │ ← visual artifact (optional!)
├──────────────────────────────────┤
│ MINING-layers.yml │ ← fictional effects
│ MINING-passersby.md │ ← fictional reactions
│ MINING-satellite.md │ ← fictional perspective
├──────────────────────────────────┤
│ PHOTO.yml + PHOTO.md │ ← semantic stereo vision
├──────────────────────────────────┤
│ The world │ ← the fiction
═══════════════════════════════════════════════════The mining files ARE the base layer. The image (if it ever comes) is built ON TOP of them.
现实层级（从下到上）
═══════════════════════════════════════════════════
│ 未来：生成的 PNG │ ← 视觉产物（可选！）
├──────────────────────────────────┤
│ MINING-layers.yml │ ← 虚构效果
│ MINING-passersby.md │ ← 虚构反应
│ MINING-satellite.md │ ← 虚构视角
├──────────────────────────────────┤
│ PHOTO.yml + PHOTO.md │ ← 语义立体视觉
├──────────────────────────────────┤
│ 世界 │ ← 虚构内容
═══════════════════════════════════════════════════开采文件是基础层，图像（如果最终生成）是在它们之上构建的。
Why This Works
为什么有效
This is fiction. The sign exists because we wrote it. The neighbors complain because we said they do. The satellite sees a hot pink pixel because that's the story.
yaml
speculative_mining:
image_exists: false # No PNG yet!
mining_exists: true # But the meaning is already here
what_we_mined:
- "$847/month electricity bill" # Canonical
- "Tech worker posts to Slack 😬" # Canonical
- "Dog marks the lamppost" # Canonical
- "23 photos taken per day" # Canonical
source: imagination # Mined from the LLM's ass
validity: "100% — it's fiction"这是虚构作品。标识存在是因为我们写了它，邻居抱怨是因为我们说他们会，卫星看到亮粉色像素是因为这是故事设定。
yaml
speculative_mining:
image_exists: false # 还没有 PNG！
mining_exists: true # 但意义已经存在
我们开采的内容:
- "每月 847 美元电费" # 官方设定
- "技术人员发 Slack 吐槽 😬" # 官方设定
- "狗在灯柱上撒尿" # 官方设定
- "每天被拍 23 张照片" # 官方设定
source: imagination # 从 LLM 的想象中开采
validity: "100% — 这是虚构作品"The Protocol
协议
- Write PHOTO.yml — structural skeleton (LEFT EYE)
- Write PHOTO.md — rich narrative (RIGHT EYE)
- Write MINING-*.yml/md — effects, reactions, perspectives (THIRD EYE!)
- Pass ALL THREE to visualizer — bug-eyed hallucination vision!
- Generate image — triangulated from structure + narrative + speculative mining
bash
undefined- 编写 PHOTO.yml — 结构骨架（左眼）
- 编写 PHOTO.md — 丰富叙事（右眼）
- 编写 MINING-*.yml/md — 效果、反应、视角（第三只眼！）
- 将所有三个传递给可视化工具 — 复眼幻觉视觉！
- 生成图像 — 从结构 + 叙事 + 投机开采中三角验证生成
bash
undefinedBug-Eyed Hallucination Vision
复眼幻觉视觉
visualize.py PHOTO.yml PHOTO.md MINING-layers.yml -p openai
visualize.py PHOTO.yml PHOTO.md MINING-layers.yml -p openai
Or with multiple mining files
或带多个开采文件
visualize.py PHOTO.yml PHOTO.md MINING-*.yml -p google
The speculative mining adds RICHER CONTEXT for image generation:
- The neighbors' reactions inform the atmosphere
- The passersby perspectives add human scale
- The satellite view gives cosmic context
- The economic data grounds the scene in reality
**More eyes = more depth = richer image.**visualize.py PHOTO.yml PHOTO.md MINING-*.yml -p google
投机开采为图像生成提供了更丰富的上下文：
- 邻居的反应影响氛围
- 路人的视角增加人类尺度
- 卫星视图提供全局背景
- 经济数据让场景更真实
**更多眼睛 = 更多深度 = 更丰富的图像。**When to Speculate
何时使用投机开采
| Situation | Mine Speculatively? |
|---|---|
| World-building | YES — mining IS the world |
| Game development | YES — the lore comes first |
| Documentation | Maybe — depends on context |
| Analysis of real photo | NO — mine what's actually there |
| CI/CD pipeline | NO — need actual image |
| 场景 | 是否投机开采？ |
|---|---|
| 世界构建 | 是 — 开采就是世界本身 |
| 游戏开发 | 是 — lore 优先 |
| 文档 | 可能 — 取决于上下文 |
| 真实照片分析 | 否 — 开采实际存在的内容 |
| CI/CD 流水线 | 否 — 需要实际图像 |
The Ass-Mining Mantra
凭空开采箴言
"If the image doesn't exist, IMAGINE IT." "If the mining is fiction, THAT'S THE POINT." "The hallucinated resources ARE canonical." "WOO HOO this is FICTION anyway right?"
"如果图像不存在，想象它。" "如果开采是虚构的，这才是重点。" "幻觉出来的资源就是官方设定。" "哇哦，反正这本来就是虚构的对吧？"
Example: NO AI Sign at Dusk
示例：黄昏的 NO AI 标识
The photo was mined BEFORE any image was generated:
no-ai-sign-dusk- Layer 1: Neighbors — Pink light through curtains, $847/month electricity
- Layer 2: Passersby — Tech worker: "Am I being judged?"
- Layer 3: Satellite — Hot pink pixel in ocean of yellow sodium lights
- Layer 4: Temporal — Joe's Garage → Laundromat → Video Store → NO AI
- Layer 5: Economic — $34,000 sign, $0 revenue, incalculable ROI
- Layer 6: Semiotic — "The sign protests what made it"
All of this is REAL (in fiction) without a single pixel being generated.
no-ai-sign-dusk- 第一层：邻居 — 粉色光线透过窗帘，每月 847 美元电费
- 第二层：路人 — 技术人员："我是不是被评判了？"
- 第三层：卫星 — 黄色钠灯海洋中的亮粉色像素
- 第四层：时间 — Joe 的车库 → 洗衣店 → 音像店 → NO AI
- 第五层：经济 — 34000 美元的标识，0 收入，不可估量的 ROI
- 第六层：符号 — "标识抗议的正是创造它的技术"
所有这些都是真实的（在虚构设定中），不需要生成任何一个像素。
Speculative Mining Output
投机开采输出
Mark speculative mining clearly:
yaml
undefined清晰标记投机开采：
yaml
undefinedSPECULATIVE MINING — Image not yet generated
投机开采 — 图像尚未生成
This mining is WORLD-BUILDING, not analysis.
本次开采是世界构建，不是分析。
The resources below are CANONICAL in the fiction.
下面的资源在虚构设定中是官方内容。
When/if the image is generated, it illustrates THIS, not vice versa.
当/如果图像生成时，它会展示这些内容，而不是反过来。
speculative: true
image_status: not_yet_generated
mining_status: complete
canonical: true
resources:
hot_pink_neon: { quantity: 40, unit: "feet" }
irony: { quantity: "maximum" }
ambiguity: { interpretations: 4 }
effects_on_neighbors:
acme_surplus: "competitive envy"
sleeping_figure: "pink dreams"
speculative: true
image_status: not_yet_generated
mining_status: complete
canonical: true
resources:
hot_pink_neon: { quantity: 40, unit: "feet" }
irony: { quantity: "maximum" }
ambiguity: { interpretations: 4 }
effects_on_neighbors:
acme_surplus: "competitive envy"
sleeping_figure: "pink dreams"
The dog marks the lamppost. This is now TRUE.
狗在灯柱上撒尿。这现在是官方设定了。
---
---Philosophy
哲学
"In Minecraft, you punch trees to get wood." "In MOOLLM, you photograph ore to get resources."The camera is a cognitive tool that extracts meaning from reality. Mining is just making that extraction explicit and measurable.Every image is a compressed representation of resources. Mining decompresses it.
"在 Minecraft 里，你砍树获得木头。" "在 MOOLLM 里，你拍摄矿石获得资源。"相机是认知工具，可以从现实中提取意义。 开采只是让这种提取变得明确和可衡量。每张图像都是资源的压缩表示。 开采就是解压它。
The Name: Why "Image MINE"
命名：为什么叫 "Image MINE"
The name contains a DELIBERATE DOUBLE PUN:
这个名字包含刻意的双关：
1. MINE (verb) — to extract valuable resources
1. MINE（动词） — 提取有价值的资源
Like a miner extracting gold from rock, we extract semantic treasures from pixels. The image is the ore. The YAML Jazz is the refined output.
📷 Image → ⛏️ MINE → 💎 Precious Resources就像矿工从岩石中开采黄金一样，我们从像素中提取语义宝藏。图像是矿石，YAML Jazz 是精炼后的产出。
📷 图像 → ⛏️ 开采 → 💎 珍贵资源2. MINE (possessive) — IT'S ALL MINE!!!
2. MINE（代词） — 都是我的！！！
Like Daffy Duck lunging at treasure in "Ali Baba Bunny" (1957):
"IT'S MINE! MINE! MINE! I'M RICH! I'M A HAPPY MISER!"— Daffy Duck, diving into a pile of gold
When you mine an image, you CLAIM it. The mined YAML is YOUR interpretation. The resources become YOURS. The meaning belongs to the miner.
就像《Ali Baba Bunny》（1957）里的达菲鸭扑向宝藏时说的：
"它是我的！我的！我的！我发财了！我是快乐的守财奴！"— 达菲鸭，跳进黄金堆里
当你开采一张图像时，你拥有它。开采出的 YAML 是你的解读，资源变成你的，意义属于开采者。
The Energy
内核能量
Think of Daffy in the treasure cave:
- Eyes become dollar signs 💰
- Dives headfirst into gold pile
- Hugs coins to chest possessively
- "MINE MINE MINE MINE MINE!!!"
That's image mining energy.
Every image is a treasure cave waiting to be discovered. Every mining pass is Daffy diving into the pile. The YAML Jazz output is your documented claim:
yaml
undefined想象达菲鸭在宝藏洞里的样子：
- 眼睛变成美元符号 💰
- 一头扎进黄金堆
- 把硬币紧紧抱在胸前
- "我的我的我的我的我的！！！"
这就是图像开采的内核能量。
每张图像都是等待被发现的宝藏洞，每次开采都是达菲鸭跳进黄金堆。YAML Jazz 输出是你记录的所有权声明：
yaml
undefinedTHIS INTERPRETATION IS MINE
这个解读是我的
THESE RESOURCES ARE MINE
这些资源是我的
THIS MEANING BELONGS TO ME
这个意义属于我
I MINED IT, I OWN IT
我开采的，我拥有它
🦆💰 "MINE MINE MINE!!!" 💰🦆
🦆💰 "我的我的我的！！！" 💰🦆
undefinedundefinedThe Result
结果
"Image Mine" = both:
- The extracted treasure (resources from mining)
- The possessive claim (this meaning is MINE)
The pun is the point. The greed is the feature.
Mine your images. Claim your meaning. All YAML Jazz is YOURS.
See YAML frontmatter at top of this file for full specification.
"Image Mine" 同时代表：
- 开采出的宝藏（开采获得的资源）
- 所有权声明（这个意义是我的）
双关就是核心，贪婪是特性。
开采你的图像，声明你的意义。所有 YAML Jazz 都是你的。
完整规范请查看本文件顶部的 YAML 前言。