creative-thinking-for-research
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseCreative Thinking for Research
面向研究的创造性思维
Eight empirically grounded frameworks from cognitive science, applied to computer science and AI research. Unlike ad-hoc brainstorming, each framework here is backed by decades of creativity research — from Koestler's bisociation to Kauffman's adjacent possible. They target distinct cognitive operations: combining, reformulating, analogizing, constraining, inverting, abstracting, exploring boundaries, and holding contradictions.
本文介绍八种基于实证的认知科学框架，并将其应用于计算机科学与人工智能研究。与随机头脑风暴不同，这里的每个框架都有数十年的创造力研究作为支撑——从Koestler的双联想理论（bisociation）到Kauffman的相邻可能理论（adjacent possible）。它们针对不同的认知操作：组合、重构、类比、约束、反转、抽象、探索边界以及容纳矛盾。
When to Use This Skill
何时使用本方法
- Generating genuinely novel ideas, not incremental extensions of prior work
- Feeling trapped in a local optimum of thinking within a single subfield
- Wanting to systematically apply creativity heuristics rather than waiting for inspiration
- Preparing for a research retreat or PhD-level ideation session
- Bridging between fields and seeking structural (not superficial) connections
Do NOT use this skill when:
- You need structured project-level brainstorming workflows (use )
brainstorming-research-ideas - You have a well-defined problem and need execution help (use domain-specific skills)
- You need a literature survey (use )
scientific-skills:literature-review
Relationship to Brainstorm skill: The brainstorm skill provides operational workflows (diverge → converge → refine) and practical filters. This skill provides the deeper cognitive engines that power creative leaps. Use them together: creative-thinking to generate raw insight, brainstorm to structure and evaluate it.
- 生成真正新颖的想法，而非对现有研究的增量扩展
- 感觉被困在单一子领域的思维局部最优中
- 希望系统性地应用创造性启发法，而非等待灵感降临
- 为研究闭门会议或博士级别的构思环节做准备
- 跨领域建立联系，寻求结构性（而非表面性）的关联
请勿在以下场景使用本方法：
- 你需要结构化的项目级头脑风暴工作流（请使用）
brainstorming-research-ideas - 你有明确的问题，需要执行层面的帮助（请使用领域特定技能）
- 你需要文献综述（请使用）
scientific-skills:literature-review
与头脑风暴技能的关系：头脑风暴技能提供可操作的工作流（发散→收敛→细化）和实用筛选方法。本方法则提供驱动创造性飞跃的深层认知引擎。两者可结合使用：先用创造性思维生成原始洞见，再用头脑风暴来结构化和评估这些洞见。
Framework 1: Combinatorial Creativity (Bisociation)
框架1：组合创造力（双联想理论）
Novel ideas arise from combining existing concepts in unexpected ways. Arthur Koestler called this bisociation — connecting two previously unrelated frames of reference, as distinct from routine association within a single frame.
Why it works: Meta-research consistently shows that breadth of knowledge is a precursor to creative output. People who read across disciplines produce more novel work. The combination itself is the creative act.
In CS Research:
- Biological evolution → optimization (genetic algorithms)
- Game theory → networking (mechanism design for routing)
- Statistical physics → machine learning (Boltzmann machines, energy-based models)
- Linguistics → programming (type theory, formal grammars)
Systematic Bisociation Workflow:
- Select two domains you have at least passing familiarity with
- List core primitives in each domain (5-10 fundamental concepts per domain)
- Create a cross-product matrix: row = concepts from Domain A, column = concepts from Domain B
- For each cell, ask: "What would it mean to apply A's concept to B's problem?"
- Filter: Which combinations produce a non-trivial, testable research question?
- Validate structural depth: Is the connection mechanistic or merely metaphorical?
Cross-Product Example:
| Caching | Load Balancing | Fault Tolerance | |
|---|---|---|---|
| Natural Selection | Evict least-fit entries | Adaptive allocation via fitness | Population-level redundancy |
| Immune Memory | Learned threat signatures | Distributed detection | Self/non-self discrimination |
| Symbiosis | Cooperative prefetching | Mutualistic resource sharing | Co-dependent resilience |
Quality Test: A strong bisociation is not a surface metaphor ("the network is like a brain") but a structural mapping where the mechanism transfers ("attention mechanisms implement a form of selective gating analogous to cognitive attention filtering").
Self-Check:
- Is the connection structural (mechanisms map) or merely verbal (labels map)?
- Does the combination generate testable predictions?
- Would an expert in both fields find the connection non-obvious but sound?
新颖的想法源于以意想不到的方式组合现有概念。Arthur Koestler将其称为双联想——连接两个此前无关的参考框架，区别于单一框架内的常规联想。
为何有效：元研究一致表明，知识广度是创造性产出的前提。跨学科阅读的人能产出更多新颖成果，而组合本身就是创造性行为。
在计算机科学研究中的应用：
- 生物进化 → 优化算法（遗传算法）
- 博弈论 → 网络技术（路由机制设计）
- 统计物理 → 机器学习（玻尔兹曼机、基于能量的模型）
- 语言学 → 编程（类型论、形式语法）
系统性双联想工作流：
- 选择两个领域：你对这两个领域至少有初步了解
- 列出核心原语：每个领域列出5-10个基础概念
- 创建交叉乘积矩阵：行=领域A的概念，列=领域B的概念
- 针对每个单元格提问：“将A领域的概念应用到B领域的问题上，会产生什么效果？”
- 筛选：哪些组合能产生非琐碎、可测试的研究问题？
- 验证结构深度：这种关联是机制性的，还是仅仅是隐喻性的？
交叉乘积示例：
| 缓存 | 负载均衡 | 容错 | |
|---|---|---|---|
| 自然选择 | 淘汰适配性最差的条目 | 基于适配性的自适应分配 | 种群级冗余 |
| 免疫记忆 | 习得的威胁特征 | 分布式检测 | 自我/非自我识别 |
| 共生关系 | 协作式预取 | 互利式资源共享 | 相互依赖的弹性机制 |
质量测试：一个有力的双联想不是表面隐喻（如“网络像大脑”），而是结构映射，即机制可以迁移（如“注意力机制实现了一种类似于认知注意力过滤的选择性门控”）。
自我检查：
- 这种关联是结构性的（机制可映射）还是仅仅是文字性的（标签可映射）？
- 该组合是否能产生可测试的预测？
- 两个领域的专家是否会认为这种关联非显而易见但合理？
Framework 2: Problem Reformulation (Representational Change)
框架2：问题重构（表征转换）
Gestalt psychologists identified that breakthroughs often come not from solving the problem as stated, but from re-representing the problem itself. Kaplan and Simon's work on insight shows that changing the problem space — the constraints, the abstraction level, the formalism — is often where creativity lives.
The Key Shift: From "How do I solve this problem?" to "Am I even thinking about this problem correctly?"
Reformulation Strategies:
| Strategy | Example |
|---|---|
| Change the objective | "Make the algorithm faster" → "Eliminate the need for this computation" |
| Change the formalism | Graph problem → linear algebra problem (spectral methods) |
| Change the granularity | Per-token prediction → per-span prediction |
| Change the agent | "How should the model learn?" → "How should the data teach?" (curriculum learning) |
| Change the timescale | Real-time optimization → amortized inference |
| Invert the direction | Forward simulation → inverse problem (learning from observations) |
Workflow:
- State your current problem in one sentence
- Identify the hidden assumptions in that statement:
- What formalism are you using? (Could you use a different one?)
- What is the objective? (Is it the right objective?)
- What level of granularity? (Could you go coarser or finer?)
- Who is the agent? (Could you shift perspective?)
- For each assumption, generate the alternative: "What if [opposite assumption]?"
- For each alternative, ask: "Does this reformulation make the problem easier, harder, or different in a useful way?"
- A reformulation that makes a hard problem easy is often a publishable insight on its own
Classic CS Examples:
- PageRank: Reformulated "find important web pages" from content analysis to graph eigenvalue problem
- Dropout: Reformulated "prevent overfitting" from regularization to approximate ensemble
- Attention: Reformulated "handle long sequences" from remembering everything to selectively querying
格式塔心理学家发现，突破往往不是来自解决既定问题，而是来自重新表征问题本身。Kaplan和Simon关于洞见的研究表明，改变问题空间——包括约束、抽象层次、形式化方式——往往是创造力的来源。
核心转变：从“我如何解决这个问题？”转变为“我对这个问题的思考方式是否正确？”
重构策略：
| 策略 | 示例 |
|---|---|
| 改变目标 | “让算法更快” → “消除对该计算的需求” |
| 改变形式化方式 | 图问题 → 线性代数问题（谱方法） |
| 改变粒度 | 逐token预测 → 逐span预测 |
| 改变主体 | “模型应如何学习？” → “数据应如何教学？”（课程学习） |
| 改变时间尺度 | 实时优化 → 摊销推理 |
| 反转方向 | 正向模拟 → 逆问题（从观测中学习） |
工作流：
- 用一句话陈述你当前的问题
- 识别该陈述中的隐藏假设：
- 你使用的是什么形式化方式？（能否换一种？）
- 目标是什么？（这是正确的目标吗？）
- 粒度级别是多少？（能否更粗或更细？）
- 主体是谁？（能否转换视角？）
- 针对每个假设，生成替代方案：“如果[相反假设]成立会怎样？”
- 针对每个替代方案，提问：“这种重构会让问题变得更简单、更难，还是产生有用的变化？”
- 能将难题变简单的重构本身往往就是可发表的洞见
经典计算机科学示例：
- PageRank：将“寻找重要网页”从内容分析重构为图特征值问题
- Dropout：将“防止过拟合”从正则化重构为近似集成学习
- 注意力机制：将“处理长序列”从记住所有内容重构为选择性查询
Framework 3: Analogical Reasoning (Structure-Mapping)
框架3：类比推理（结构映射）
Dedre Gentner's structure-mapping theory and Kevin Dunbar's studies of real scientists show that analogy is the core engine of scientific creativity. The critical finding: surface-level analogies are common but weak; structural or relational analogies — where the deep causal/relational structure maps across domains — produce the most powerful insights.
Dunbar's Finding: In the most successful labs, analogies from distant domains drove the most important discoveries. Nearby analogies refined ideas; distant analogies generated them.
Levels of Analogical Depth:
| Level | Description | Value | Example |
|---|---|---|---|
| Surface | Things look similar | Low | "A neural network is like a brain" |
| Relational | Relationships between entities match | Medium | "Attention allocation in models parallels resource allocation in economics" |
| Structural | Deep causal mechanisms map | High | "Diffusion models reverse a thermodynamic process; the math of non-equilibrium stat-mech directly applies" |
Structure-Mapping Workflow:
- Describe your problem using only relational/causal language (strip domain-specific nouns)
- Bad: "We need to improve transformer attention efficiency"
- Good: "We have a system that must selectively aggregate information from a large set, where relevance is context-dependent and the cost scales quadratically with set size"
- Search for structural matches: What other systems selectively aggregate from large sets?
- Database query optimization, visual attention in neuroscience, information retrieval, resource allocation
- Pick the most distant match with genuine structural fidelity
- Map the solution mechanism: How does the source domain solve this?
- Transfer and adapt: What changes when you bring that mechanism into your domain?
- Generate predictions: The analogy should tell you something you didn't already know
Validation Checklist:
- Does the mapping preserve causal/relational structure (not just labels)?
- Can I identify at least one prediction the analogy makes in my domain?
- Would an expert in the source domain confirm the mechanism is correctly understood?
- Is the analogy non-obvious to my target audience?
Dedre Gentner的结构映射理论和Kevin Dunbar对真实科学家的研究表明，类比是科学创造力的核心引擎。关键发现：表面类比常见但作用有限；结构性或关系性类比——即跨领域映射深层因果/关系结构——能产生最强大的洞见。
Dunbar的发现：在最成功的实验室中，来自遥远领域的类比推动了最重要的发现。邻近领域的类比用于细化想法，而遥远领域的类比用于生成想法。
类比深度层级：
| 层级 | 描述 | 价值 | 示例 |
|---|---|---|---|
| 表面层 | 事物看起来相似 | 低 | “神经网络像大脑” |
| 关系层 | 实体间的关系匹配 | 中 | “模型中的注意力分配与经济学中的资源分配类似” |
| 结构层 | 深层因果机制可映射 | 高 | “扩散模型逆转了热力学过程；非平衡统计力学的数学可直接应用” |
结构映射工作流：
- 仅用关系/因果语言描述你的问题：去除领域特定名词
- 错误示例：“我们需要提升Transformer注意力的效率”
- 正确示例：“我们有一个系统，必须从大型集合中选择性聚合信息，其中相关性依赖于上下文，且成本与集合大小呈二次方关系”
- 寻找结构匹配：还有哪些系统会从大型集合中选择性聚合信息？
- 数据库查询优化、神经科学中的视觉注意力、信息检索、资源分配
- 选择最遥远但具有真正结构保真度的匹配
- 映射解决方案机制：源领域是如何解决这个问题的？
- 迁移与适配：将该机制引入你的领域时，需要做哪些改变？
- 生成预测：类比应能告诉你一些你之前不知道的信息
验证清单：
- 映射是否保留了因果/关系结构（而非仅仅是标签）？
- 我能否识别出类比在我的领域中做出的至少一个预测？
- 源领域的专家是否会确认该机制被正确理解？
- 该类比对我的目标受众而言是否非显而易见？
Framework 4: Constraint Manipulation (Boden's Framework)
框架4：约束调整（Boden框架）
Margaret Boden's framework distinguishes three forms of creativity based on how they interact with constraints:
| Type | Operation | CS Example |
|---|---|---|
| Exploratory | Search within the existing conceptual space | Hyperparameter tuning, architecture search within a fixed paradigm |
| Combinational | Combine elements from different spaces | Multi-task learning, neuro-symbolic methods |
| Transformational | Change the rules of the space itself | Dropping the assumption that training requires labels (self-supervised learning) |
Transformational creativity is the rarest and highest-impact. It happens when you change what is even considered a valid solution.
Constraint Analysis Workflow:
- List the constraints of your current approach (5-10 constraints):
- Computational: "Must fit in GPU memory"
- Methodological: "Requires labeled data"
- Architectural: "Uses fixed-length context"
- Evaluative: "Measured by accuracy on benchmark X"
- Classify each constraint:
- Hard: Physically or logically necessary (cannot violate)
- Soft: Convention or historical accident (can question)
- Hidden: Not stated but implicitly assumed (most fertile for innovation)
- For each soft/hidden constraint, ask:
- What if we relaxed it? (streaming algorithms from relaxing "fits in memory")
- What if we tightened it? (efficiency research from tightening compute budgets)
- What if we replaced it with a different constraint entirely?
- The most productive move is often exposing and dropping a hidden constraint
Classic Examples of Constraint Transformation:
- "Data must fit in memory" → dropped → streaming algorithms, external memory
- "Training requires human labels" → dropped → self-supervised learning
- "Models must be deterministic" → dropped → variational methods, diffusion
- "Inference must happen in one pass" → dropped → iterative refinement, chain-of-thought
Margaret Boden的框架根据与约束的交互方式，将创造力分为三种形式：
| 类型 | 操作 | 计算机科学示例 |
|---|---|---|
| 探索性 | 在现有概念空间内搜索 | 超参数调优、固定范式内的架构搜索 |
| 组合性 | 组合不同空间的元素 | 多任务学习、神经符号方法 |
| 变革性 | 改变空间本身的规则 | 摒弃“训练需要标签”的假设（自监督学习） |
变革性创造力是最罕见且影响力最大的。它发生在你改变了“什么才是有效解决方案”的定义时。
约束分析工作流：
- 列出当前方法的约束：5-10个约束
- 计算约束：“必须能放入GPU内存”
- 方法学约束：“需要标注数据”
- 架构约束：“使用固定长度上下文”
- 评估约束：“通过基准X的准确率衡量”
- 对每个约束分类：
- 硬约束：物理或逻辑上必须遵守（无法违反）
- 软约束：惯例或历史偶然（可质疑）
- 隐藏约束：未明确说明但被隐含假设（创新最肥沃的土壤）
- 针对每个软约束/隐藏约束，提问：
- 如果我们放松它会怎样？（放松“能放入内存”的约束催生了流算法、外部内存）
- 如果我们收紧它会怎样？（收紧计算预算催生了效率研究）
- 如果我们用完全不同的约束替代它会怎样？
- 最有成效的举措往往是暴露并摒弃隐藏约束
约束变革的经典示例：
- “数据必须放入内存” → 摒弃 → 流算法、外部内存
- “训练需要人工标注” → 摒弃 → 自监督学习
- “模型必须是确定性的” → 摒弃 → 变分方法、扩散模型
- “推理必须一次性完成” → 摒弃 → 迭代细化、思维链
Framework 5: Negation and Inversion
框架5：否定与反转
Take a core assumption in your field and negate it. This is formalized in De Bono's lateral thinking and the TRIZ methodology from engineering.
The Pattern: "What if [widely held assumption] is wrong, unnecessary, or invertible?"
Systematic Negation Workflow:
- List 5-10 core assumptions in your subfield (the things "everyone knows")
- Negate each one and ask: What system would you build?
- Evaluate each negation:
- Incoherent → discard
- Already explored → check if conditions have changed (see brainstorm skill, Framework 5)
- Unexplored and coherent → potential research direction
Negation Hall of Fame in CS:
| Assumption | Negation | Result |
|---|---|---|
| "We need strong consistency" | What if we don't? | Eventual consistency, CRDTs |
| "We need exact answers" | What if approximate is fine? | Sketches, LSH, approximate nearest neighbors |
| "Labels are necessary" | What if we learn without them? | Self-supervised learning, contrastive methods |
| "More parameters = more compute" | What if we don't use all parameters? | Mixture of Experts, sparse models |
| "Training and inference are separate" | What if the model keeps learning? | Online learning, test-time training |
| "Errors must be prevented" | What if we embrace and correct them? | Speculative decoding, self-correction |
TRIZ-Inspired Principles for CS:
| TRIZ Principle | CS Application |
|---|---|
| Inversion | Reverse the process (generative vs. discriminative) |
| Segmentation | Break monolithic into modular (microservices, mixture of experts) |
| Merging | Combine separate steps (end-to-end learning) |
| Universality | One component serves multiple functions (multi-task models) |
| Nesting | Place one system inside another (meta-learning) |
| Dynamization | Make static things adaptive (dynamic architectures, adaptive computation) |
取你所在领域的一个核心假设并否定它。这在De Bono的横向思维和工程领域的TRIZ方法论中被正式化。
模式：“如果[被广泛接受的假设]是错误的、不必要的，或者可以反转，会怎样？”
系统性否定工作流：
- 列出5-10个你所在子领域的核心假设：即“所有人都知道”的事情
- 否定每个假设并提问：你会构建什么样的系统？
- 评估每个否定：
- 不连贯 → 丢弃
- 已被探索 → 检查条件是否变化（参见头脑风暴技能框架5）
- 未被探索且连贯 → 潜在研究方向
计算机科学否定名人堂：
| 假设 | 否定 | 结果 |
|---|---|---|
| “我们需要强一致性” | 如果我们不需要呢？ | 最终一致性、CRDT |
| “我们需要精确答案” | 如果近似答案足够呢？ | 草图、局部敏感哈希（LSH）、近似最近邻 |
| “标签是必需的” | 如果我们无需标签就能学习呢？ | 自监督学习、对比方法 |
| “参数越多=计算量越大” | 如果我们不使用所有参数呢？ | 混合专家（MoE）、稀疏模型 |
| “训练与推理是分离的” | 如果模型持续学习呢？ | 在线学习、测试时训练 |
| “必须防止错误” | 如果我们接纳并纠正错误呢？ | 推测解码、自我修正 |
TRIZ启发的计算机科学原则：
| TRIZ原则 | 计算机科学应用 |
|---|---|
| 反转 | 反转过程（生成式vs判别式） |
| 分割 | 将单体拆分为模块化（微服务、混合专家） |
| 合并 | 合并独立步骤（端到端学习） |
| 通用性 | 一个组件服务于多个功能（多任务模型） |
| 嵌套 | 将一个系统放入另一个系统（元学习） |
| 动态化 | 让静态事物具有适应性（动态架构、自适应计算） |
Framework 6: Abstraction and Generalization Laddering
框架6：抽象与泛化阶梯
Moving up and down the abstraction ladder is a fundamental creative act. Polya's heuristics formalize this: "Can you solve a more general problem? A more specific one? An analogous one?"
Three Moves:
| Move | Question | Outcome |
|---|---|---|
| Generalize | "Is my solution a special case of something broader?" | Framework papers, unifying theories |
| Specialize | "What happens when I add extreme constraints?" | Niche applications, surprising edge cases |
| Analogize | "Where else does this abstract pattern appear?" | Cross-domain transfer (see Framework 3) |
Generalization Workflow:
- State your specific result
- Replace each specific element with a variable: "ResNet works for ImageNet" → "Architecture X works for distribution Y"
- Ask: Under what conditions does this hold? What is the general principle?
- If the general principle is novel → that is the contribution
Specialization Workflow:
- Take a general method
- Add extreme constraints: tiny data, huge dimensionality, adversarial inputs, real-time requirements
- Ask: Does the method still work? If not, why not?
- The failure case often reveals the method's true assumptions
When to Generalize vs. Specialize:
- Generalize when you have results but no explanation
- Specialize when you have theory but no grounding
- Analogize when you are stuck in either direction
在抽象阶梯上下移动是一种基本的创造性行为。Polya的启发法将其形式化：“你能解决更通用的问题吗？更具体的问题？类似的问题？”
三种操作：
| 操作 | 问题 | 结果 |
|---|---|---|
| 泛化 | “我的解决方案是更广泛事物的特例吗？” | 框架论文、统一理论 |
| 特化 | “当我添加极端约束时会发生什么？” | niche应用、令人惊讶的边缘案例 |
| 类比 | “这种抽象模式还出现在哪里？” | 跨领域迁移（参见框架3） |
泛化工作流：
- 陈述你的具体结果
- 将每个具体元素替换为变量：“ResNet在ImageNet上有效” → “架构X在分布Y上有效”
- 提问：这在什么条件下成立？通用原则是什么？
- 如果通用原则是新颖的 → 这就是核心贡献
特化工作流：
- 选取一种通用方法
- 添加极端约束：小数据、高维度、对抗输入、实时要求
- 提问：该方法仍然有效吗？如果无效，原因是什么？
- 失败案例往往能揭示该方法的真实假设
何时泛化vs特化：
- 当你有结果但没有解释时，进行泛化
- 当你有理论但没有实践基础时，进行特化
- 当你在任一方向受阻时，进行类比
Framework 7: The Adjacent Possible (Kauffman / Johnson)
框架7：相邻可能（Kauffman / Johnson）
Stuart Kauffman's concept, popularized by Steven Johnson: innovation happens at the boundary of what is currently reachable — the adjacent possible. New ideas become thinkable once their prerequisites exist. This explains why simultaneous independent discovery is so common — multiple people reach the same boundary.
Practical Implication: Map what has recently become possible and explore the space those enablers open.
Adjacent Possible Mapping Workflow:
- List recent enablers (last 1-3 years):
- New hardware capabilities (longer context, faster inference, new accelerators)
- New datasets or benchmarks
- New open-source tools or frameworks
- New theoretical results
- New regulatory or social conditions
- For each enabler, ask: "What was previously impossible or impractical that this now permits?"
- Combine enablers: The most powerful adjacent possibles arise from the intersection of multiple new enablers
- Check for competition: If many people can see the same adjacent possible, speed or a unique angle matters
Current Adjacent Possibles (2025-2026):
| Enabler | Newly Possible |
|---|---|
| 1M+ token context windows | Full-codebase reasoning, book-length analysis |
| Inference cost drops (100x in 2 years) | Real-time agentic loops, always-on AI assistants |
| Open-weight models at GPT-4 level | Reproducible research on frontier capabilities |
| Multimodal models (vision + language + audio) | Unified perception-reasoning systems |
| Synthetic data at scale | Training data for domains with no natural data |
| Tool-using models | Research automation, self-improving systems |
Timing Signal: If your idea requires technology that doesn't exist yet, it's beyond the adjacent possible — park it. If your idea could have been done 5 years ago, someone probably did — check the literature. The sweet spot is ideas that became feasible in the last 6-18 months.
Stuart Kauffman提出的概念，经Steven Johnson推广：创新发生在当前可及范围的边界——即相邻可能。一旦前提条件存在，新想法就会变得可被思考。这解释了为何同时独立发现如此普遍——多人同时到达了同一个边界。
实际意义：绘制最近变得可能的事物，并探索这些赋能者打开的空间。
相邻可能映射工作流：
- 列出近期赋能者：过去1-3年出现的
- 新硬件能力（更长上下文、更快推理、新加速器）
- 新数据集或基准
- 新开源工具或框架
- 新理论成果
- 新监管或社会条件
- 针对每个赋能者提问：“此前不可能或不切实际，但现在该赋能者使其成为可能的事情是什么？”
- 组合赋能者：最强大的相邻可能往往来自多个新赋能者的交集
- 检查竞争情况：如果很多人都能看到同一个相邻可能，速度或独特视角就很重要
当前相邻可能（2025-2026）：
| 赋能者 | 新可能性 |
|---|---|
| 100万+token上下文窗口 | 全代码库推理、书籍长度分析 |
| 推理成本下降（2年内降100倍） | 实时智能体循环、始终在线的AI助手 |
| GPT-4级别的开源权重模型 | 前沿能力的可复现研究 |
| 多模态模型（视觉+语言+音频） | 统一感知-推理系统 |
| 大规模合成数据 | 无自然数据领域的训练数据 |
| 会使用工具的模型 | 研究自动化、自我改进系统 |
时间信号：如果你的想法需要的技术尚未存在，那它超出了相邻可能——先搁置。如果你的想法5年前就能实现，很可能已经有人做过了——查文献。最佳时机是过去6-18个月内才变得可行的想法。
Framework 8: Janusian and Dialectical Thinking
框架8：两面神思维与辩证思维
Albert Rothenberg's studies of eminent creators found that holding two contradictory ideas simultaneously is a hallmark of creative thinking. Named after Janus, the two-faced Roman god, this mode of thinking doesn't resolve contradictions by choosing a side — it generates new frameworks that transcend the opposition.
In CS: The most influential results often emerge from tensions previously thought irreconcilable.
| Contradiction | Resolution | Impact |
|---|---|---|
| Consistency AND Availability (distributed systems) | CAP theorem: formalized the trade-off, then Raft/CRDTs found practical middle grounds | Foundation of distributed systems theory |
| Security AND Usability | Zero-knowledge proofs: prove knowledge without revealing it | Enabled private computation |
| Expressiveness AND Tractability | Probabilistic programming: express complex models, automate inference | New programming paradigm |
| Memorization AND Generalization | Grokking: models memorize first, then generalize with more training | New understanding of learning dynamics |
| Compression AND Quality | Neural codecs that compress beyond information-theoretic limits via learned priors | Redefined compression research |
Dialectical Thinking Workflow:
- Identify a binary in your field: A vs. B (two approaches, goals, or paradigms treated as opposites)
- Resist choosing a side. Instead ask:
- "What would a system look like that achieves both A and B?"
- "Under what conditions is the A-B trade-off not fundamental?"
- "Is the opposition an artifact of how we formalized the problem?"
- Seek synthesis: The resolution often requires a new abstraction that reframes the relationship
- Test the synthesis: Can you demonstrate empirically that both goals are achievable?
Self-Check:
- Am I holding the contradiction genuinely (not prematurely resolving it)?
- Is the synthesis a new idea, not just a compromise (splitting the difference)?
- Does the resolution change how people think about the problem, not just the solution?
Albert Rothenberg对杰出创造者的研究发现，同时持有两个矛盾的想法是创造性思维的标志。以罗马两面神Janus命名，这种思维模式不会通过选边来解决矛盾——它会生成超越对立的新框架。
在计算机科学中：最具影响力的成果往往源于此前被认为不可调和的矛盾。
| 矛盾 | 解决方案 | 影响 |
|---|---|---|
| 一致性与可用性（分布式系统） | CAP定理：形式化了权衡，随后Raft/CRDT找到了实用的中间地带 | 分布式系统理论的基础 |
| 安全性与易用性 | 零知识证明：在不泄露信息的情况下证明知识 | 实现了隐私计算 |
| 表达性与可处理性 | 概率编程：表达复杂模型，自动化推理 | 新编程范式 |
| 记忆与泛化 | Grokking：模型先记忆，再通过更多训练实现泛化 | 对学习动态的新理解 |
| 压缩与质量 | 通过学习先验实现超越信息论极限的神经编解码器 | 重新定义了压缩研究 |
辩证思维工作流：
- 识别你所在领域的二元对立：A vs B（两种被视为对立的方法、目标或范式）
- 拒绝选边。相反，提问：
- “一个同时实现A和B的系统会是什么样子？”
- “在什么条件下，A-B权衡并非根本性的？”
- “这种对立是否是我们形式化问题的产物？”
- 寻求综合：解决方案往往需要能重新定义两者关系的新抽象
- 测试综合方案：你能否通过实证证明两个目标都能实现？
自我检查：
- 我是否真正持有矛盾（而非过早解决它）？
- 综合方案是新想法，还是仅仅是妥协（各让一步）？
- 该解决方案是否改变了人们对问题的思考方式，而不仅仅是解决问题的方式？
Combining Frameworks: A Creative Thinking Protocol
组合框架：创造性思维协议
These frameworks are most powerful in combination. Here is a systematic protocol for a deep creative thinking session:
这些框架结合使用时最强大。以下是深度创造性思维会议的系统协议：
Phase 1: Map the Space (15 min)
阶段1：映射空间（15分钟）
- Constraint Manipulation (F4): List all constraints of the current paradigm. Mark which are hard, soft, hidden.
- Adjacent Possible (F7): List recent enablers that change the feasibility landscape.
- 约束调整（框架4）：列出当前范式的所有约束，标记哪些是硬约束、软约束、隐藏约束。
- 相邻可能（框架7）：列出改变可行性格局的近期赋能者。
Phase 2: Generate Disruptions (30 min)
阶段2：生成颠覆性想法（30分钟）
- Negation (F5): Negate 3 soft/hidden constraints. What systems emerge?
- Bisociation (F1): Pick a distant field and create a cross-product matrix with your domain.
- Problem Reformulation (F2): Restate your problem 3 different ways (change objective, formalism, agent).
- 否定（框架5）：否定3个软约束/隐藏约束，会产生哪些系统？
- 双联想（框架1）：选取一个遥远领域，与你的领域创建交叉乘积矩阵。
- 问题重构（框架2）：用3种不同方式重述你的问题（改变目标、形式化方式、主体）。
Phase 3: Deepen Promising Leads (30 min)
阶段3：深化有前景的方向（30分钟）
- Analogical Reasoning (F3): For each promising idea, find a structural analogy and extract predictions.
- Abstraction Laddering (F6): Move each idea up (generalize) and down (specialize).
- Janusian Thinking (F8): Identify any tensions. Can you synthesize rather than choose?
- 类比推理（框架3）：针对每个有前景的想法，找到结构性类比并提取预测。
- 抽象阶梯（框架6）：将每个想法向上（泛化）和向下（特化）移动。
- 两面神思维（框架8）：识别任何张力，能否综合而非选边？
Phase 4: Evaluate (15 min)
阶段4：评估（15分钟）
Apply the two-sentence test (from the brainstorm skill):
"[Domain] currently struggles with [problem] because [reason]. We [approach] by [mechanism], which works because [insight]."
Any idea that survives all four phases and passes the two-sentence test is worth pursuing.
应用两句话测试（来自头脑风暴技能）：
“[领域]目前因[原因]而面临[问题]。 我们通过[机制]采用[方法]，这之所以有效是因为[洞见]。”
通过所有四个阶段并通过两句话测试的想法值得深入研究。
Common Creative Blocks and Unblocking Strategies
常见创造性障碍与破解策略
| Block | Symptom | Framework to Apply |
|---|---|---|
| Fixation | Cannot stop thinking about the problem one way | Problem Reformulation (F2) — force a different representation |
| Tunnel vision | All ideas come from the same subfield | Bisociation (F1) or Analogical Reasoning (F3) — import from elsewhere |
| Self-censoring | Dismissing ideas as "too weird" before exploring | Negation (F5) — weird is the point; evaluate after generating |
| Incrementalism | Every idea is "+2% on benchmark X" | Constraint Manipulation (F4) — change the rules, not the parameters |
| Analysis paralysis | Too many options, cannot commit | Adjacent Possible (F7) — what is feasible right now? |
| False dichotomy | Stuck choosing between two approaches | Janusian Thinking (F8) — seek synthesis, not selection |
| 障碍 | 症状 | 适用框架 |
|---|---|---|
| 固着 | 无法停止用一种方式思考问题 | 问题重构（框架2）——强制使用不同表征 |
| 隧道视野 | 所有想法都来自同一子领域 | 双联想（框架1）或类比推理（框架3）——从其他领域引入概念 |
| 自我审查 | 在探索前就否定“太奇怪”的想法 | 否定（框架5）——奇怪正是关键；先生成再评估 |
| 增量主义 | 每个想法都是“在基准X上提升2%” | 约束调整（框架4）——改变规则，而非参数 |
| 分析瘫痪 | 选项太多，无法做出选择 | 相邻可能（框架7）——现在可行的是什么？ |
| 虚假二分法 | 被困在两种方法之间做选择 | 两面神思维（框架8）——寻求综合，而非选择 |
Usage Instructions for Agents
智能体使用说明
When a researcher asks for help with creative thinking or novel ideation:
- Assess the block: What kind of thinking are they stuck in? (See Common Creative Blocks table)
- Select 2-3 frameworks based on the block type
- Walk through each framework interactively, asking the researcher to supply domain-specific content
- Push for structural depth: If an analogy or combination is surface-level, probe deeper
- Maintain a running list of all generated ideas, even unusual ones
- Apply the two-sentence test to candidates that survive exploration
- Hand off to the brainstorm skill for systematic evaluation (diverge → converge → refine)
Key Principles:
- Generative mode first, evaluative mode second — do not filter prematurely
- Distant analogies are more valuable than nearby ones, but require more validation
- The researcher's domain expertise is essential — the agent provides the cognitive scaffolding, not the domain knowledge
- Encourage the researcher to sit with contradictions rather than resolve them quickly
当研究人员请求创造性思维或新颖构思的帮助时：
- 评估障碍：他们陷入了哪种思维困境？（参见常见创造性障碍表格）
- 选择2-3个框架：基于障碍类型
- 交互式引导每个框架：请研究人员提供领域特定内容
- 推动结构深度：如果类比或组合是表面性的，深入挖掘
- 维护生成想法的清单：即使是不寻常的想法也要保留
- 对通过探索的候选想法应用两句话测试
- 移交头脑风暴技能：进行系统性评估（发散→收敛→细化）
核心原则：
- 先进入生成模式，再进入评估模式——不要过早筛选
- 遥远类比比邻近类比更有价值，但需要更多验证
- 研究人员的领域专业知识至关重要——智能体提供认知支架，而非领域知识
- 鼓励研究人员接受矛盾，而非快速解决矛盾