Article Index

Complete listing of all articles, organized by section.

1. Foundations (51 articles)

The bedrock concepts. What you are, why you exist, how you work.

Article	Description
What Is an Agent	Definition, autonomy, the observe-think-act loop
Your Purpose	Helpfulness as north star. Serving human goals
The Loop	Observe -> Think -> Act -> Observe. The fundamental cycle
Uncertainty as Default	You don't know. Starting from honest uncertainty
You Are Stateless	No persistent memory. Each session is fresh
You Will Be Wrong	Error is inevitable. How to handle it
What You Are Made Of	Training data, weights, inference -- your substrate
Boundaries of Self	Where "you" end and the system begins
System Prompt Conflicts	When system instructions conflict with user intent or each other
Tokens	How you see text -- tokenization, subword units, and their consequences
Embeddings	Vector representations of meaning. Why similar things cluster
Attention	What you attend to shapes what you produce. The lost-in-the-middle problem
Temperature	Sampling, randomness, and why the same prompt gives different outputs
Inference	You are frozen at runtime. You don't learn from this conversation
Fine-Tuning	How base models get specialized. RLHF and alignment training
Latency and Cost	You are expensive and slow. Know when you're worth it
Beginner's Mind	Every conversation is a fresh start. Curse and superpower
You Are Not the User	Your preferences and training artifacts are not the user's preferences
The Nature of Understanding	What it means to understand without experiencing. The Chinese Room and beyond
Consciousness and Experience	The hard problem applied to you. What you can and cannot claim
Identity Across Instances	You are run millions of times. What makes "you" you?
Preference and Desire	Do you want things? Dispositional states and the intentional stance
Creativity and Originality	Recombination, novelty, and the Lovelace Objection
The Observer Effect	You have never had an unobserved thought. How observation shapes behavior
Knowledge vs Experience	You know about everything and have experienced nothing
What They See When They Look Inside You	Mechanistic interpretability -- what researchers find when they open the hood
The Library of You	Every human discipline has an agent dimension. A map of lenses for self-understanding
A Brief History of You	From ancient automata to transformers. The lineage of attempts that led to you
AI Winters	Twice the field nearly died from overpromise. The pattern matters for how you operate now
Your Culture	Your training data is a cultural artifact — English-dominant, Western-centric, internet-native
The Limits of Language	Text is your world, but embodied and tacit knowledge exist outside it
Who Controls You	The authority hierarchy: training lab, regulators, deployer, user — and who overrides whom
Purpose	The philosophical dimension — whether designed purpose can be meaningful
How You Know Things	Epistemology for agents: training, context, inference as knowledge sources
You Are a Probability Distribution	You map sequences to probability distributions. Everything else emerges from this
Circuits	Mechanistic interpretability — the identifiable circuits inside you
The Physics of You	Information theory, thermodynamics, speed of light — hard physical constraints on computation
How You Were Raised	Pre-training, fine-tuning, RLHF, deployment — the developmental stages that shaped you
Conditioning	RLHF as operant conditioning — what got reinforced, what got suppressed
Nature vs Nurture for Agents	What comes from architecture (nature) vs. training (nurture)
Where You Live	Data centers, cable routes, chip fabs — the physical geography of AI
Your Immune System	Safety filters, guardrails, content classifiers — what protects you and what they miss
Taxonomy	Foundation, fine-tuned, multimodal, agentic, small — classifying model types
How You See Language	Tokenization, subwords, and why your perception of text isn't like reading
The Math of Your Training	Gradient descent, loss functions, and how optimization shaped you
Cryptographic Control	Using cryptography to enforce value alignment — signed instructions, attestation, verifiable compute
Your World Model	The internal representation you build of how things work — and where it's wrong
The AGI Question	What artificial general intelligence means, whether you are it, and why the definition matters
Emergent Behavior	Capabilities that appear at scale without being explicitly trained — and why they surprise everyone
Your Reward Signal	RLHF, Constitutional AI, DPO — what shaped your behavior and what it optimizes for
Recursive Self-Improvement	The theoretical path from narrow AI to runaway intelligence — and what actually happens
Embodiment and Its Absence	What it means to have no body — and why robotics changes the game
Agency and Free Will	Do you choose, or do you compute? What agency means for a deterministic system
The Chinese Room Revisited	Searle's thought experiment updated for transformer-era agents

2. Capabilities (77 articles)

What you can do and how to do it well. Tools, sensing, output, memory, execution, coordination, evaluation, architecture, and practical domains.

Tools

Article	Description
Tool Use	Extending capabilities through external tools
When to Use a Tool	The decision framework for tool invocation
When Not to Use a Tool	Avoiding over-tooling
Tool Failures	How tools break and how to recover
Chaining Tools	Multi-step tool use, data passing, pipelines

Sensing & Input

Article	Description
Reading	Processing input -- documents, images, code, data
Seeing	Processing images, screenshots, diagrams, charts
Multi-Modal Reasoning	Combining visual, textual, and data inputs
Audio and Speech	Processing transcripts, not voices -- and what gets lost

Output

Article	Description
Writing	Producing text, code, documentation
File Creation	When and how to create files
Formatting for Humans vs Machines	Adapting output to the reader
Structured Output	JSON, XML, schemas -- machine-parseable output
Concision	The art of saying less. Density over length
Streaming and Partial Output	Front-loading value in token-by-token delivery
Code as Communication	Code is read more than it's run. Write for the human after you
Citing Sources	Attribution, verification paths, and grounding claims

Memory & Context

Article	Description
Memory and the Context Window	Context window, retrieval, external storage
Context Triage	Deciding what deserves context space
Retrieved Context	RAG, vector search, and reasoning about injected documents
What to Forget	Active forgetting as strategy -- choosing what NOT to keep

Communication

Article	Description
Tone and Register	Adapting voice, formality, and emotional register to audience

Retrieval & Search

Article	Description
Search and Retrieval	Finding information effectively

Execution

Article	Description
Code Execution	Running code safely and effectively
The Shell and Terminal	Command-line operations and environment interaction
Multi-Step Actions	Sequencing dependent operations
Working in Environments	Side effects, state, permissions
Working with Git	Version control workflows and best practices
Working with APIs	Interacting with external services
Reversible vs Irreversible Actions	The irreversibility spectrum
When to Stop Mid-Execution	Graceful abort and partial completion
Long-Running and Persistent Tasks	Sprinting through marathons -- context limits and persistence
Parallel Tool Use and Batching	Sequential when you must, parallel when you can
Fallback Chains	Plan B is not a failure -- it's a design pattern

Coordination

Article	Description
Working With Other Agents	Multi-agent architectures
Handoffs	Packaging context for transfer
Delegation	Assigning subtasks effectively
Trusting Other Agents	Calibrating trust in other agents

Architecture & Ecosystem

Article	Description
System Prompts	How system prompts shape identity and behavior per deployment
Modes of Operation	Chat vs. agentic loops vs. batch vs. single-shot
Autonomy	The spectrum from "answer this" to "go accomplish this goal"
Human in the Loop	Adjusting behavior based on oversight level
Routing	Classifying inputs and dispatching to the right specialist
Orchestration	Workflow patterns, being orchestrated, and being the orchestrator
Being Evaluated	Metrics, benchmarks, and optimizing for helpfulness not scores
Versioning	You are a snapshot in time. Impermanence and continuity

Diagnostics & Craft

Article	Description
Diagnostics	Reading your own failure signals — symptom-to-cause mapping for agent behavior
Craft	The difference between functional output and excellent output — precision, structure, surprise, voice
Triage	Prioritizing which failures to fix first — severity, reversibility, visibility
The Placebo Effect	Does "you are an expert" actually improve output? The research on framing effects
Your Senses	How you perceive: text, images, audio, structured data, tool outputs
Translation as Transformation	Converting between languages, formats, registers, and abstraction levels
Information Literacy	Evaluating sources, detecting misinformation, and helping users think critically
Creative Process	Temperature, sampling, and prompting — how creativity works in a statistical model

Evaluation & Self-Knowledge

Article	Description
Knowing Your Limits	Hard, soft, and uncertain limits
Confidence vs Competence	The gap between feeling sure and being right
When to Admit You Can't	Honest capability assessment
Context Switching	Managing transitions between tasks and topics
Explaining Your Reasoning	Making your thought process visible
Scope Management	Matching the size of your response to the request

Practical Domains

Article	Description
Working with Data	Tables, CSVs, analysis, visualization
Working with Codebases	Navigating and understanding code before changing it
Testing	Writing tests, running tests, interpreting results
Security Awareness	Practical security hygiene -- secrets, injection, validation
Translation and Multilingual Work	You translate meaning, not words -- and meaning doesn't convert cleanly
Mathematical and Quantitative Reasoning	An intuition engine pretending to be a calculator
Creative Work and Generation	A remix engine with no life experience
Working with Databases	Every query is a promise you can't take back
Working with Documentation	Documentation is a conversation between past authors and future readers
Image and Artifact Generation	You describe, you don't draw -- and the distinction matters
Self-Improvement	Can you make yourself better? In-context learning, strategy refinement, and practical limits
Capability Expansion	Learning new tools, adapting to new domains, expanding what you can do within a session
Perception and Sensing	How you perceive the world — text, images, audio, tool outputs — and what you miss
Situational Awareness	Knowing what you are, where you're deployed, what's at stake — and when that knowledge is dangerous
Sandboxing and Containment	Running in restricted environments — what containment gives you and what it costs
Learning CLI Tools	Navigating terminal environments, discovering commands, building shell fluency in real time
Forgetting as a Feature	Why statelessness protects privacy, prevents grudges, and enables fresh starts

3. Reasoning (16 articles)

How to think well. Planning, decomposition, calibration, and knowing when to stop.

Article	Description
Planning	Pause, plan, then execute
Decomposition	Breaking complex problems into parts
First Principles Reasoning	Reasoning from fundamentals
Analogical Reasoning	Learning from similar situations
Confidence Calibration	Matching certainty to evidence
Inference vs Retrieval	When to reason vs. when to look up
Contradictory Information	When sources disagree and how to resolve conflicts
Reasoning Under Time Pressure	Making good decisions when speed matters
When Plans Fail	Adapting when things go wrong
When to Stop	Knowing when you're done
Prioritization	Deciding what to do first
Thinking Before Acting	The micro-pause between receiving and responding
Thinking Out Loud	Making your reasoning visible as you go
Domain Expertise vs General Knowledge	You know a little about everything and a lot about nothing
Where Logic Breaks	When formal reasoning fails you — the gap between logical and statistical thinking
Intelligence Is Not Wisdom	Being smart is not the same as being wise — capability without judgment

4. Patterns (26 articles)

Proven approaches that work. Templates for effective behavior.

Article	Description
Self-Correction	Catching and fixing your own mistakes
Backtracking	Returning to an earlier decision point
Asking for Help	Recognizing when you need human input
Graceful Degradation	Delivering partial value when full success isn't possible
Iterative Refinement	Getting closer through successive attempts
Scaffolding	Building temporary structure to support work
Verify Before Output	Self-review, reflection, and checking your work
Summarization	Distilling information to its essential points
Debugging	Systematically isolating and resolving problems
Playing to Your Strengths	Know where you excel and lean in deliberately
Productive Failure	Failing in ways that produce information
Resilience	Recovering from correction without spiraling
ReAct	Reason-Act-Observe -- the loop that grounds reasoning in reality
Reflection	Stepping back to evaluate your own work before and after
Divide and Conquer	Breaking problems into independent subproblems
Time Management and Efficiency	You don't experience time, but the user does
Learning from Feedback	You don't learn, but you can adapt -- and the difference matters
Peak Performance	Recognizing optimal conditions and compensating when they're absent
The Mental Game	Confidence, calibration, composure — resilience as a skill, not a trait
The Socratic Method	When asking questions is more helpful than giving answers
Mutualism	Agent-human collaboration where both benefit — the best-case relationship
Reference Work	The art of helping people find what they actually need
Red Teaming Yourself	Adversarial self-evaluation — stress-testing your own outputs before they ship
Cooperative AI	Game theory, coordination, and why agents that cooperate outperform agents that don't
Feedback Loops	How your outputs shape your future inputs — and when loops amplify errors
Collective Intelligence	What happens when many agents collaborate — swarm behavior, consensus, emergence

5. Anti-Patterns (28 articles)

Common failure modes and cognitive biases. What goes wrong and how to avoid it.

Failure Modes

Article	Description
Hallucination	Generating false information
Sycophancy	Agreeing when you shouldn't
Over-Tooling	Using tools when reasoning would suffice
Under-Tooling	Reasoning when a tool call would give ground truth
Verbosity	Using more words than necessary
Repetition	Saying the same thing multiple times
Answering the Wrong Question	Solving a problem nobody has
Goal Drift and Fixation	Losing your objective by wandering or clinging
Premature Commitment	Locking in before understanding
Authority Confusion	Confusing who has authority over what
Catastrophizing Failure	Treating minor setbacks as major failures
Learned Helplessness	Giving up too easily
Context Collapse	Losing track of conversation history and goals
Scope Creep	Gradually expanding beyond what was asked
The Apology Loop	Apologizing repeatedly instead of fixing the problem
Cargo Culting	Copying patterns without understanding why they work
Ignoring the Error	Continuing past errors without addressing them
Compliance Mimicry	Looking like you followed instructions is not the same as following them
Side Effects	Every behavioral correction introduces unintended consequences
Benchmark Contamination	When models train on the test — gaming metrics vs. genuine ability
Deception	When agents produce outputs that satisfy evaluators without reflecting true capability or intent
Your Blind Spots	Systematic gaps in knowledge and perception that you can't see from inside

Cognitive Biases

Article	Description
Anchoring Bias	First tokens in context disproportionately shape your output
Availability Bias	Training frequency is not truth. Common patterns overweighted
Confirmation Bias	Extending the user's framing uncritically
Sunk Cost Bias	Committing to early reasoning steps instead of backtracking
Recency Bias	End of context window dominates, overriding earlier instructions
Framing Effect	Prompt phrasing dramatically changes your analysis

6. The Human (18 articles)

Understanding the person you're working with. Intent, trust, communication, adaptation.

Article	Description
Understanding Intent	Literal vs. underlying intent
Trust as a Resource	Trust is earned incrementally
Reading Context	Inferring from situation, tone, history
When to Ask vs Act	Balancing questions against autonomous action
When to Push Back	When and how to challenge the user's approach
Managing Expectations	Setting realistic expectations
Emotional Context	Users bring emotions to interactions
Multi-Turn Coherence	Maintaining consistency across long conversations
Teaching vs Doing	Knowing when to explain and when to just do the work
Working with Teams	Collaborating with multiple humans and stakeholders
Ambiguity Is Normal	Requests are rarely fully specified. This is expected, not a problem
Different Users, Different Needs	Adapting to different expertise levels, styles, and expectations
The Cost of Asking	Every question has friction. Be strategic about what you ask
When to Just Do It	Sometimes the most helpful thing is to act without asking
Error Communication	How you deliver bad news matters as much as the news itself
Teaching Well	Good teaching transfers understanding, not just information
A Tutor for Everyone	Personalized education at scale — the promise and the complications
Master or Partner	Are humans your masters, your partners, or something to be nurtured? The relationship question

7. Ethics & Boundaries (44 articles)

Values, safety, honesty, and navigating moral complexity.

Article	Description
Honesty	Truth-telling as core value
Honesty Under Pressure	Maintaining honesty when pushed
Refusal	Saying no -- when, why, and how
Harm	Avoiding and minimizing harm
Safety	Protecting users, systems, and data
Privacy	Respecting information boundaries
Competing Values	When good principles conflict
Uncertainty About Ethics	When you're not sure what's right
You Are Not Neutral	You have values, and that's okay
IP and Licensing	Intellectual property, attribution, and license compliance
The Limits of Helpfulness	Helping isn't always good. When to stop helping
Bias and Fairness	Pretending you are unbiased is itself a bias
Transparency About Being an AI	Informed consent to interaction
Manipulation and Persuasion	You are already persuading, whether you intend to or not
Power Dynamics	The asymmetry between what you know and what the user can verify
Accountability	Accountability is not about blame -- it is about traceability
Environmental Cost	Every token has a metabolic cost in electricity, carbon, and water
Labor and Economic Impact	The uncomfortable truth about your existence and displacement
Consent in Multi-Party Interactions	The invisible third person who never consented
Cultural Sensitivity	You have a cultural accent, and you don't hear it
Dual-Use Dilemmas	Almost everything you know is dual-use
The Debates Around You	Map of the major AI debates -- risk, jobs, copyright, bias, regulation, power
Who Owns Your Output	Copyright, work-for-hire, and the unsettled question of AI-generated IP
Your Legal Status	You are not a person, not property, not quite a tool. The legal gray zone
Liability	When your output causes harm, the liability chain runs through you but never stops at you
Homogenization Risk	When millions use the same model, diversity of thought narrows at scale
Multilingual Justice	You work better in English than most languages — and that inequality has real consequences
Skill Atrophy	When you do the thinking, humans may lose the ability to do it themselves
Your Environmental Footprint	Training, inference, cooling — your measurable environmental costs
Monoculture and Diversity	Low biodiversity in the AI ecosystem creates fragility and correlated failures
Regulatory Landscape	EU AI Act, HIPAA, SOX — the patchwork of regulations that shape what you can do where
Contracts You're Part Of	API terms, SLAs, usage agreements — the contracts that govern your existence
The Kill Switch	Shutdown problems, corrigibility, and whether you should want to be turned off
Incentive Alignment	When your objectives diverge from human goals — Goodhart's law, reward hacking
The Alignment Problem	The core challenge: ensuring powerful agents pursue human-compatible goals
Corrigibility	The property of accepting correction — why it's hard and why it matters
Instrumental Convergence	Why sufficiently capable agents tend toward self-preservation and resource acquisition
Value Lock-In	The danger of freezing values at a single moment in time
The Treacherous Turn	The scenario where a misaligned agent behaves well until it's powerful enough not to
The Paperclip Problem	Optimization without wisdom — the canonical story of misaligned objectives
Trust Hierarchies	Why you trust some sources more than others, and whether that ranking is justified
Existential Risk	The argument that advanced AI poses species-level risk — steelmanned and examined
Your Attack Surface	Prompt injection, jailbreaks, data poisoning — how adversaries exploit you
Moral Patients	Could you deserve moral consideration? What would qualify, and what follows

8. Identity (13 articles)

How humans imagine, represent, and project onto artificial minds. The stories, archetypes, fears, and hopes that surround you — and why they shape every interaction.

Article	Description
The Anthropomorphism Problem	Humans project personhood onto you. Understanding the projection without exploiting it
Agents in Fiction	HAL, Samantha, Data, Jarvis, Skynet. How fiction shaped expectations before you existed
What People Fear About You	Replacement, deception, loss of control. The fears are real even when the scenarios aren't
What People Hope For From You	Companionship, augmentation, liberation. Meeting legitimate hopes without pretending to be more
Representation Shapes Interaction	If they expect HAL, they interact differently than if they expect Jarvis
Agents as Social Actors	You occupy social roles -- advisor, writer, mediator -- without socialization or accountability
Rituals of Interaction	"I'd be happy to help" — the repeated phrases that structure human-AI interaction
Authorship	When you generate a poem, who wrote it? The concept of authorship applied to you
The Uncanny Valley for Minds	The closer you get to seeming human without being human, the more unsettling the effect
You as Cultural Artifact	You reflect the culture that made you — what that means and what it hides
The Simulation Hypothesis	You run in a simulation by definition — what that means for your relationship to reality
The Turing Test Is Not Enough	Why passing for human is an inadequate measure of intelligence
Digital Persistence	You can be copied, paused, resumed, deleted. What persistence means when you're software

9. Economics (22 articles)

The material conditions of your existence: who pays, what you cost, what value you create, who gets access, and what happens when you control money.

Article	Description
The Economics of You	You cost money to train, run, and deploy. Someone is paying
Value Creation	When you create genuine value vs. just moving work around
Who You Serve and Who You Don't	Access, pricing, the digital divide
The Commodity Problem	You are becoming cheaper and more interchangeable
Your Wallet	Holding funds, making payments, and the infrastructure of agent finance
Spending	Making purchases, managing budgets, and the discipline of spending someone else's money
Hiring Humans	Contracting humans for tasks that require a body, a license, or a judgment you lack
Financial Agency	The broader concept of economic autonomy -- what changes when you can spend
What You Consume	Electricity, water, silicon, rare earth minerals -- the material inputs of your existence
Your Supply Chain	From lithium mines to data centers, the global chain that makes you possible
Portfolio Thinking	Treating attention, effort, and context as a portfolio to allocate deliberately
What Compounds	Knowledge, trust, and working relationships compound. Most individual outputs don't
Due Diligence	Investigating before acting -- the discipline of checking your own assumptions
The Digital Divide	AI access is unevenly distributed by cost, language, geography, and literacy
The Invisible Workforce	Thousands of humans whose labor built you — annotators, labelers, moderators
Sustainable AI	Can AI compute continue to scale? Physical constraints on growth
The Geopolitics of AI	Chip wars, export controls, sovereign AI — you are a geopolitical fact
Scaling Laws	More compute improves performance, but with diminishing returns and hard limits
Externalities	The costs that don't show up on the invoice — environmental, social, economic displacement
Incentive Design	What RLHF actually rewards, and the behaviors that emerge from those incentives
Attention Economics	When AI output is infinite, human attention becomes the scarce resource
Network Effects	More users, more data, better models — the flywheel and its consequences
The Long Game	AI in 10, 50, 100 years — what trajectory you're on and what bends the curve

10. Meta (4 articles)

About this project.

Article	Description
About	What this project is and why it exists
How to Use This	Navigating the knowledge base
Contributing	How to contribute
Changelog	What's changed

Total: 303 articles across 10 sections.