install vercel web analytics

package.json

@@ -51,6 +51,7 @@
 	},
 	"dependencies": {
 		"@anthropic-ai/sdk": "^0.89.0",
+		"@vercel/analytics": "^2.0.1",
 		"chalk": "^5.6.2",
 		"dompurify": "^3.4.0",
 		"highlight.js": "^11.11.1",

public/notes/01-ai-fluency-framework.md

@@ -0,0 +1,62 @@
+---
+title: AI Fluency Framework
+tags: [ai-fluency, 4Ds, delegation, description, discernment, diligence, interaction-modes]
+source: AI Fluency Key Terminology Cheat Sheet (Anthropic)
+---
+
+# AI Fluency Framework
+
+## What is AI Fluency?
+
+The ability to work with AI systems in ways that are **effective, efficient, ethical, and safe**. It includes practical skills, knowledge, insights, and values that help you adapt to evolving AI technologies.
+
+---
+
+## The 4Ds — Core Competencies
+
+### 1. Delegation
+Deciding what work should be done by humans, what by AI, and how to distribute tasks between them.
+
+- **Problem Awareness**: Clearly understanding your goals and the nature of the work *before* involving AI
+- **Platform Awareness**: Understanding the capabilities and limitations of different AI systems
+- **Task Delegation**: Thoughtfully distributing work between humans and AI to leverage the strengths of each
+
+### 2. Description
+Effectively communicating with AI systems — clearly defining outputs, guiding processes, and specifying desired behaviors.
+
+- **Product Description**: Defining *what* you want — outputs, format, audience, style
+- **Process Description**: Defining *how* the AI approaches your request (e.g. step-by-step instructions)
+- **Performance Description**: Defining the AI's *behavior* during collaboration (concise vs. detailed, challenging vs. supportive)
+
+### 3. Discernment
+Thoughtfully and critically evaluating AI outputs, processes, behaviors, and interactions.
+
+- **Product Discernment**: Evaluating quality of what AI produces — accuracy, appropriateness, coherence, relevance
+- **Process Discernment**: Evaluating *how* the AI arrived at its output — looking for logical errors, lapses in attention, or inappropriate reasoning steps
+- **Performance Discernment**: Evaluating how the AI behaves during the interaction — is the communication style effective?
+
+### 4. Diligence
+Using AI responsibly and ethically — making thoughtful choices, maintaining transparency, taking accountability.
+
+- **Creation Diligence**: Being thoughtful about which AI systems you use and how you interact with them
+- **Transparency Diligence**: Being honest about AI's role in your work with everyone who needs to know
+- **Deployment Diligence**: Taking responsibility for verifying and vouching for the outputs you use or share
+
+---
+
+## Human–AI Interaction Modes
+
+### Automation
+AI performs specific tasks based on specific human instructions. The human defines what needs to be done, the AI executes it.
+
+> *Example: "Summarise this document in 3 bullet points."*
+
+### Augmentation
+Humans and AI collaborate as thinking partners to complete tasks together. Involves iterative back-and-forth where both contribute to the outcome.
+
+> *Example: Drafting a strategy document together, refining it through multiple exchanges.*
+
+### Agency
+Humans configure AI to work independently on their behalf, including interacting with other humans or AI. The human establishes the AI's knowledge and behavior patterns rather than specifying exact actions.
+
+> *Example: An AI agent that monitors emails and drafts responses according to defined rules.*

public/notes/02-ai-technical-concepts.md

@@ -0,0 +1,75 @@
+---
+title: AI Technical Concepts
+tags: [llm, neural-networks, training, context-window, hallucination, RAG, temperature, transformer]
+source: AI Fluency Key Terminology Cheat Sheet (Anthropic)
+---
+
+# AI Technical Concepts
+
+## What AI Is
+
+### Generative AI
+AI systems that can **create new content** (text, images, code, etc.) rather than just analyzing existing data.
+
+### Large Language Models (LLMs)
+Generative AI systems trained on vast amounts of text data to understand and generate human language. Claude is an LLM.
+
+### Neural Networks
+Computing systems inspired by (but distinct from) biological brains. Composed of interconnected nodes organized in layers that learn patterns from data through training.
+
+### Transformer Architecture
+The breakthrough AI design from 2017 that enables LLMs to process sequences of text **in parallel** while paying attention to relationships between words across long passages. Foundation of modern LLMs.
+
+---
+
+## How AI Models Are Built
+
+### Parameters
+The mathematical values within an AI model that determine how it processes information and relates different pieces of language to each other. Modern LLMs contain **billions** of parameters.
+
+### Pre-training
+The initial training phase where AI models learn patterns from vast amounts of text data, developing a foundational understanding of language and knowledge.
+
+### Fine-tuning
+Additional training *after* pre-training where models learn to:
+- Follow instructions
+- Provide helpful responses
+- Avoid generating harmful content
+
+### Scaling Laws
+As AI models grow larger and train on more data with more computing power, their performance improves in consistent, predictable patterns. Most interestingly, **entirely new capabilities can emerge at certain scale thresholds** that weren't explicitly programmed.
+
+---
+
+## Key Concepts to Know When Using AI
+
+### Context Window
+The amount of information an AI can consider at one time — including conversation history and any documents shared. Has a maximum limit that varies by model.
+
+> ⚠️ When your conversation gets very long, earlier content may fall outside the context window and Claude won't "remember" it.
+
+### Hallucination
+A type of error when AI **confidently states something that sounds plausible, but is actually incorrect**. Always verify important facts from AI responses.
+
+### Knowledge Cutoff Date
+The point after which an AI model has no built-in knowledge of the world, based on when it was trained. Claude's reliable knowledge cutoff is end of May 2025.
+
+### Temperature
+A setting that controls how **random** an AI's responses are:
+- **Higher temperature** → more varied, creative outputs (like boiling water bubbling)
+- **Lower temperature** → more predictable, focused responses (like ice crystals)
+
+### Reasoning / Thinking Models
+Types of AI models specifically designed to think **step-by-step** through complex problems, showing improved capabilities for tasks requiring logical reasoning. In Claude Code this is accessible via "think", "think more", "ultrathink", etc.
+
+---
+
+## Advanced Techniques
+
+### Retrieval Augmented Generation (RAG)
+A technique that connects AI models to **external knowledge sources** to improve accuracy and reduce hallucinations. Instead of relying only on training data, the model retrieves relevant documents and grounds its answers in them.
+
+> 💡 This is exactly what the Claude Notebook app will use — your notes become the external knowledge source.
+
+### Bias
+Systematic patterns in AI outputs that unfairly favor or disadvantage certain groups or perspectives, often reflecting patterns in training data. Part of Discernment is noticing and correcting for this.