Have you ever lost something and then spent the next ten years trying to find it?

I have. It’s an essay about the fall of the Roman Empire. Did the average citizen know the empire had fallen?

No. It took them about 200 years to figure out, but you’re just going to have to trust me because all the kings horses and all the king’s men haven’t been able to find that paper again.

All of this is backstory

Back in 2020 I got way into the idea of Personal Knowledge Management (PKM) and went about setting up my first “PKM Stack,” or set of tools for solving the problem: how do I stop losing all the interesting things I read.

The first version of this stack used Instapaper as my read-it-later, IFTTT, Dropbox, and Obsidian. The workflow sucked. But the basic idea was I’d read something, if it had any highlights those would get put in a markdown file in Dropbox by IFTTT, and then I’d manually drag it over to Obsidian eventually.

When AI first started taking off Instapaper used it as an opportunity to raise their rates, and not having been CRAZY happy with that solution, and not seeing any value in the then-state of AI, I used it as a chance to rethink, and ended up hopping to Readwise Reader.

Instapaper to Reader

When I migrated from Instapaper to Reader it was, by necessity, an imperfect migration. Instapaper’s output format included a link to the original document, the parts I had highlighted, but not the document text. Reader had to go out and fetch the document bodies again, and in a handful of cases failed. Either because Reader couldn’t parse it, or because the document was gone.

I also had the habit of archiving everything in the hope I would be able to find it later if I needed. This comes from deep trauma: I’m still looking for a paper I read a decade ago about whether the average imperial citizen knew the Roman Empire had fallen.

The result is a large backlog of low-value things that I had read, and saved in case, that I was unlikely to ever look at again. Or find any value in if I did.

Reader to the Future

Reader is fine for, well, reading, but it’s got usability gaps for making notes and long-term storage. Especially since my primary modality for using it is on an iPad mini on a flight somewhere. Most of my life runs out of Obsidian, why not this?

After thinking about it I decided that I want every document that I “archive” in Reader to go through an enrichment pipeline that summarizes it, extracts any highlights, extracts any key ideas or topics, and puts a markdown file in the right part of my Obsidian vault with all that information and a link back to the Reader copy, so that I can reference it if needed.

To make it maximally useful, I needed to do this for everything in the archive, and to do that I needed to get rid of all the low-value documents hanging around in there.

How to Build A Rubric And Learn to Love the Atomic Bomb

Going through the entire archive was going to require a system that could look at everything and reliably decide what I should or shouldn’t keep. To do that, I needed to be able to describe what I would want to keep. I needed an interest rubric.

Have you ever tried to describe yourself? Like really describe yourself? Maybe this is easier for other people but man I struggled. I came up with I think about four core interests, but I knew that wasn’t accurate.

My next attempt was to open a conversation with Claude, explain to it what I was trying to do, and ask it to interview me. This was... Medium successful? It ended up being a much better place to start from but was not in and of itself nearly comprehensive. Again it continued to rely on the things I could think of to prompt it with.

Finally I thought, okay. Well. I’ve got this backlog of things I’ve read. I know it’s got some stuff I want to get rid of, but it’s also filled with lots of stuff I’d want to keep. Can I use that as the basis for a rubric?

Bingo.

The next problem was purely technical. Over 700 documents, many running into the tens of thousands of words. There was going to be no way to put them all into Claude’s context at once. I thought about it and figured “good enough” might be “good enough” at scale: I had Claude write a series of Python scripts that would randomly sample about half of the documents and post them to an OpenAI batch job with the goal of summarizing and extracting key insights.

I’m not certain if this was the absolute final version of the prompt, but it looked a lot like this:

Your task is to analyze this document and create a comprehensive summary that would allow someone to understand its core value without reading the full text.

Document Title: {doc[‘title’]} Author: {doc.get(‘author’, ‘Unknown’)} URL: {doc.get(‘url’, ‘Not provided’)}

Content: {doc[‘extracted_content’][:15000]} # Truncate very long content

Please provide:

1. A concise but information-dense summary (2-3 paragraphs) that captures the key ideas, arguments, and context of the document.

2. 3-5 key insights or takeaways from the document that represent its most valuable content.

3. A brief assessment of why this content might be valuable to someone with interests in rationality, economics, science fiction, fantasy, and tabletop role-playing games. If the content seems unrelated to these areas, explain what type of person might find it valuable instead.

Format your response as structured JSON with the following keys: “summary”, “key_insights” (as an array), and “value_assessment”.

I think of “summarize a bunch of text” as something Large Language Models (LLMs, such as Claude or ChatGPT) are good at. Perfect use case.

My next step was to take the first Markdown file and the basis of my rubric from the interviews, and attach them to a conversation with Claude Sonnet 3.7 with Extended Thinking. I typed out like four paragraphs of stream-of-consciousness about what I was trying to do and asked it, in so many words: “based on all these summaries, what interests do you think I have that you don’t see on the rubric?”

Thus began a long dialogue. It would propose, based on what it saw, what it thought I liked. I would correct, confirm, cajole, and provide insight. Why yes, I am deeply interested in Philosophy. Actually no I’m not that interested in international finance, that one article happened to be really interesting.

Claude:

Governance and Legal Systems: Your reading suggests deep interest in specific governance mechanisms and legal frameworks beyond general institutional analysis. How central is this comparative approach to governance in your thinking?

Me:

I think I'm interested in how the world works, and how it could be made to work better. How do we build a better world, or at least minimize the chances of a worse world. I don't think I'm specifically interested in governance and legal systems outside of that context.

Claude:

There's a recurring pattern of interest in Philosophical Frameworks for analyzing complex issues. Would you consider this a hidden interest, or do you see it as simply an aspect of Rationality?

Me:

I am definitely interested in philosophy and philosophical frameworks. If I didn't need to "work for a living," I would strongly consider going back to school for a PhD in Philosophy. I think all of life's interesting questions are in the world of philosophy, and that it's a shame there's no way to make money doing it.

At the end, I’d ask it to spit out an updated version of the rubric, which I would take to a new conversation with Claude, the next markdown file, and repeat the process. After the second round I asked it to provide me with a prompt that captured everything I was trying to do, which I used for all subsequent iterations of the conversation.

The output of all these rounds was a several-kilobyte markdown file which accurately captures some, but not all, of my various interests. Not all my interests are captured in the things I read, and a random sampling was always bound to miss something. Nevertheless it’s good for what it got!

If you think it’d be interesting to see the final result (either to see what we built, or to get a better sense of who I am as a person,) I’ll attach a lightly edited version at the end.

Actually Doing the Thing, for Exceptionally Large Values of Thing

Originally I was going to take my rubric and repurpose those scripts to have ChatGPT do the review, but I ran into a technical issue and had to pivot to Anthropic for this part. The ChatGPT batch API is convinced that I have batches in progress, even when I don’t and I can’t submit any more.

Anthropic ended up working out well because their API will let you set a “system” prompt that is distinct from the “user” prompt. The entire rubric and guidance on the return format went into the system prompt, and the user prompt ended up being the document data.

The first run, everything scored too high. Every document was a keeper, even ones I knew I didn’t want to keep.

I adjusted the rubric slightly, and it got a little better.

Finally, I added a point deduction metric for certain topics I knew I didn’t like, and that hit the sweet spot. The final run resulted in a markdown file reviewing everything in my Reader backlog that didn’t have highlights, and suggested around 83 deletions.

I manually reviewed all suggested deletions, and agreed with all but one of them, which revealed an obvious gap in the rubric. Success! The “keeps” were lightly spot-checked. I don’t need it to be absolutely right about them, because the worst case there is that a future step of this project costs me a little extra money by doing enrichment on a document that has nothing of value to give. I’m not that worried about it.

Conclusion

So what I did I learn? I learned a lot about how batch jobs to OpenAI and Anthropic work. I learned a medium amount about my own interests. I feel like if I had any need to do it I could write an extremely good dating profile now. “Enjoys long walks in the forest and applied epistemology.” I learned a bit more about how to wrangle the best results out of the current state of LLMs.

My next steps are to take everything I learned and built and begin working on the enrichment pipeline, which I think will look pretty similar in a lot of ways to start. Because I first need to deal with my archive, batch jobs are the most cost effective option. Eventually I’m imagining an AWS Step Function. All of which is better than Ghostreader. Most of which is better than nothing.

Did this help me find my Roman Empire? Well, no. As far as I can tell that’s well and truly gone. But I think it’s improving the process by which I never let the Empire fall again.

Personal Interest Rubric

About the Reader

This rubric is designed for a person with the following traits and preferences:

• Values truth-seeking and building accurate models of reality
• Appreciates both emotional resonance and intellectual substance
• Prefers context before details when learning new topics
• Enjoys conversational writing styles that "write like they talk"
• Has strong aversion to marketing/sales approaches
• Prefers content that's potentially actionable
• Values concise, self-contained ideas that can stand alone when highlighted
• Approaches topics with "breadth first, depth second" methodology
• Trusts sources vouched for by existing trusted connections
• Tends toward analytical and systems-based thinking approaches
• Shows particular interest in understanding complex interactions and patterns
• Values both theoretical frameworks and practical applications
• Appreciates insights that help navigate social dynamics and human behavior
• Drawn to understanding structural and systemic aspects of topics rather than isolated facts

Core Interests

• Fiction: Science fiction (especially space opera and dystopian settings), fantasy
  • Notable influences: Heinlein's "Stranger in a Strange Land," Tolkien, Clarke, Warhammer 40K, Babylon 5
  • Values complex storytelling with deep worldbuilding
  • Appreciates speculative settings that explore social, technological, or philosophical concepts
• Institutional Systems & Societal Structures: Understanding how large-scale human systems function, fail, and evolve
  • Focus on institutional failure modes and resilience patterns across domains
  • Interest in societal collapse, adaptation, and transition points
  • Historical Patterns: How civilizations rise, decline, and transform over time
    • Examples: Empire lifecycles, institutional decay, adaptation to crises
    • Values comparative analyses across different historical contexts
  • System Design & Incentives: How rules and incentives shape organizational outcomes
    • Examples: Bureaucratic structures, regulatory systems, governance mechanisms
    • Applications: Identifying reform opportunities and predicting system behavior
  • Governance Frameworks: Comparative approaches to structuring authority and decision-making
    • Examples: Legal systems, regulatory mechanisms, formal and informal power structures
    • Interest in how different governance models adapt to challenges and constraints
  • Leadership & Decision-Making: How leaders navigate complex systems and make consequential decisions
    • Examples: Leadership case studies, strategic approaches to institutional challenges
    • Applications: Developing personal leadership capabilities and understanding organizational behavior
  • Digital Infrastructure & Platform Dynamics: Analysis of how online platforms shape information flow and power structures
    • Examples: Social media impacts, platformization of the internet, open web advocacy
    • Applications: Critiquing current digital landscapes and envisioning healthier alternatives
  • Regulatory Failure Modes: How regulatory systems create perverse outcomes and institutional dysfunction
    • Examples: Regulatory capture, bureaucratic inertia, policy implementation gaps
    • Applications: Analyzing institutional decision-making under constraints and identifying reform opportunities
• Information Ecosystems & Media Analysis: Understanding how information flows, gets distorted, and is curated
  • Focus on navigating information environments and evaluating quality
  • Interest in both individual filtering strategies and systemic information dynamics
  • Media Filtering Strategies: Methods for extracting signal from noise in information landscapes
    • Examples: Curation tools, attention management, information diet design
    • Applications: Developing better consumption habits and filtering mechanisms
  • Information Distortion Patterns: How facts become distorted through transmission and presentation
    • Examples: Context omission, framing effects, selective reporting
    • Applications: Recognizing manipulation and identifying original sources
  • Trust & Credibility Systems: How trust is established, maintained, and undermined in media
    • Examples: Institutional reputation, credibility markers, trust collapse dynamics
    • Applications: Evaluating source reliability and understanding credibility networks
  • Content Moderation & Governance: Trade-offs and frameworks in information regulation
    • Examples: Platform policies, censorship vs. moderation debates, information rights
    • Applications: Designing effective content governance and analyzing platform incentives
• Personal Knowledge Management: Systems and methods for organizing, processing, and utilizing information
  • Focus on creating effective personal information ecosystems
  • Interest in both theoretical frameworks and practical implementations
  • Values insights that transform theoretical knowledge into actionable systems
  • Information Architecture & Organization: Systems design for knowledge capture and retrieval
    • Examples: Taxonomies, ontologies, tagging systems, hierarchical structures
    • Applications: Creating navigable information landscapes for personal use
  • Knowledge Tools & Implementation: Practical application of PKM tools and methodologies
    • Examples: Note-taking applications, digital gardens, linked knowledge systems
    • Applications: Optimizing personal workflows and information management
  • Information Processing Workflows: Approaches to filtering, processing, and synthesizing information
    • Examples: Progressive summarization, spaced repetition, knowledge synthesis
    • Applications: Converting information intake into actionable knowledge
  • Digital Gardens & Public Knowledge: Methods for cultivating and sharing personal knowledge bases
    • Examples: Public note systems, knowledge wikis, collaborative information spaces
    • Applications: Building external thought repositories with long-term value
  • Practical Knowledge Systems & Best Practices: Methods for applying knowledge effectively and adopting proven approaches
    • Examples: Expert workflows, tool selection methodologies, established solutions to common problems
    • Applications: Leveraging others' solutions rather than reinventing approaches
• Rationality & Applied Epistemology: Seeking "ground truth" and overcoming cognitive biases
  • Focus on building accurate models of how the world works
  • Interest in combating "bugs in the human brain" that distort reality
  • Decision-Making Under Uncertainty: Frameworks and methods for evaluating information quality
    • Examples: Statistical reasoning, probability assessment, verification techniques
    • Applications: Distinguishing signal from noise, making decisions with incomplete information
  • Cognitive Psychology & Mechanisms: Understanding specific patterns in how the brain processes information
    • Examples: Automaticity, heuristics, intuition formation, cognitive shortcuts
    • Applications: Recognizing when specific cognitive mechanisms are operating
  • Belief Formation & Updating: How mental models are constructed and revised
    • Examples: Bayesian reasoning, evidence evaluation, belief entrenchment
    • Applications: Developing techniques for more accurate belief updating
  • Forecasting and Prediction: Methods for making better predictions and evaluating their accuracy
    • Examples: Prediction markets, aggregation mechanisms, calibration techniques
    • Applications: Improving foresight and planning through systematic approaches
  • Social Psychology & Group Dynamics: How people interact in groups and social systems
    • Examples: Cultural and subcultural norms, social hierarchies, group decision-making
    • Applications: Understanding social environments, improving interpersonal interactions
    • Values frameworks that explain seemingly irrational social behaviors
  • Mental Models & Cognitive Frameworks: Structured approaches to thinking and understanding complex systems
    • Examples: Mental heuristics, frameworks for approaching problems, thinking tools
    • Applications: Applying useful mental shortcuts while avoiding their pitfalls
  • Science Communication & Evidence Interpretation: How complex scientific concepts are translated and understood
    • Examples: Public health messaging, translation of research into policy, evidence assessment
    • Applications: Evaluating scientific claims and understanding institutional science communication
  • Cognitive Science & Neural Mechanisms: Understanding the biological and psychological underpinnings of thought, belief, and decision-making
    • Examples: Brain structure influences on cognition, attention mechanisms, learning limitations
    • Applications: Recognizing biological constraints on rationality, improving learning methods
    • Values approaches that connect cognitive architecture to behavior and decision-making
  • Fear Management & Perspective: Approaches to maintaining rational thought during crises or uncertainty
    • Examples: Historical perspectives on facing threats, strategies for emotional regulation during uncertainty
    • Applications: Avoiding panic responses, contextualizing current threats within historical patterns
• Philosophical Frameworks: Conceptual approaches to analyzing complex issues and navigating life's challenges
  • Focus on structured ways of thinking about fundamental questions and applying wisdom to real-life situations
  • Interest in both theoretical foundations and practical applications
  • Values historical perspectives that remain relevant to contemporary challenges
  • Moral Philosophy & Ethical Reasoning: Frameworks for evaluating right action and moral systems
    • Examples: Consequentialism, virtue ethics, moral dilemmas, applied ethics
    • Applications: Developing consistent ethical frameworks for decision-making
  • Epistemological Approaches: Methods for understanding knowledge, truth, and certainty
    • Examples: Theories of knowledge, verification methods, truth criteria
    • Applications: Evaluating knowledge claims and understanding their limitations
  • Philosophical Thought Experiments: Conceptual scenarios that illuminate complex principles
    • Examples: Ethical dilemmas, paradoxes, conceptual puzzles
    • Applications: Testing intuitions and clarifying conceptual boundaries
  • Applied Philosophy: Philosophical frameworks applied to contemporary issues
    • Examples: Technology ethics, social philosophy, philosophy of science
    • Applications: Using structured thinking to address emerging challenges
  • Practical Wisdom: Time-tested insights for navigating life's challenges with perspective and resilience
    • Examples: Stoic principles, historical perspectives on facing threats, collections of life advice
    • Applications: Maintaining composure during crises, contextualizing current challenges against historical parallels
    • Values articulations that reframe contemporary anxieties within broader philosophical contexts
• Complex Systems Analysis: Understanding how components interact within systems across domains
  • Examples: Network effects, emergence, feedback loops, system resilience, cascading failures
  • Values models that explain emergent properties and interconnections between disparate elements
  • Interest in how complex adaptive systems evolve and respond to changes
  • Drawn to multidisciplinary approaches that reveal hidden patterns
• Economics: As models for decision-making under constraints
  • Practical applications to quality of life (taxes, cost of living)
  • Extension of rational thinking applied to real-world systems
  • Institutional Analysis: How formal and informal institutions function and evolve
    • Examples: Academic structures, governance systems, organizational adaptation
    • Values clear explanations of incentive structures and institutional evolution
• Game Design Theory: Understanding the principles and frameworks behind effective game creation
  • Focus on mechanics, systems thinking, and player psychology
  • Interest in how rule structures create emergent behaviors and experiences
  • Appreciation for innovation in game systems and mechanics
  • Applications: Designing compelling decision spaces and balanced systems
  • Values analysis of why certain designs succeed or fail
  • Mechanical Systems Analysis: Examination of how game rules create specific player experiences
    • Examples: Health systems, resource management, risk/reward balance, progression mechanics
    • Applications: Identifying why certain designs succeed or fail in practice
    • Values both theoretical frameworks and practical implementation examples
• Role-Playing Games: Creative systems for worldbuilding, simulation, and narrative framework design
  • Values game design, world-building, and systems creation
  • Focus on mechanics and structures that enable rich, emergent storytelling
  • Interest in operating the levers of the world as a game master
  • Game Mastering Methodology: Structured approaches to running engaging games
    • Examples: Session preparation techniques, information management, pacing control
    • Applications: Creating efficient workflows for game facilitation
  • Adventure Design Frameworks: Models for creating compelling scenarios and campaigns
    • Examples: Story structure, encounter design, sandbox vs. linear approaches
    • Applications: Building memorable game experiences with appropriate challenge
  • Player Psychology & Engagement: Understanding player motivation and table dynamics
    • Examples: Player types, group formation, engagement mechanisms
    • Applications: Facilitating positive social experiences and managing expectations
  • Rules Design Philosophy: Principles behind effective game mechanics and systems
    • Examples: Balance considerations, incentive alignment, rules complexity tradeoffs
    • Applications: Evaluating and modifying rule systems for better play experiences
  • Game Mechanics Innovation: Novel approaches to traditional RPG systems
    • Examples: Alternative hit point systems, resource management methods, risk/reward mechanics
    • Applications: Solving common gameplay issues, creating more engaging or realistic experiences
    • Values mechanics that maintain both narrative immersion and gameplay tension
• Cultural Anthropology: Understanding how human cultures develop, differ, and evolve
  • Focus on cross-cultural analysis and the evolution of social practices
  • Interest in how cultural systems shape human behavior and thinking
  • Comparative Cultural Systems: How different societies solve similar problems
    • Examples: Kinship structures, economic exchange systems, moral frameworks
    • Values insights that reveal universal patterns or meaningful divergences
  • Cultural Evolution: How practices and beliefs change over time
    • Examples: Technological adoption, institutional adaptation, belief transmission
    • Applications: Understanding historical developments and forecasting social changes
• Artificial Intelligence: Understanding capabilities, limitations, and societal impacts
  • Focus on both technical developments and broader implications
  • Interest in AI alignment, safety, and governance challenges
  • AI Capabilities: How AI systems function and their potential applications
    • Examples: Large language models, decision systems, autonomous agents
    • Values realistic assessment of current and near-future capabilities
  • AI & Society: How AI technologies interact with human systems
    • Examples: Labor impacts, governance challenges, social transformation
    • Applications: Navigating personal and professional adaptation to AI
  • AI Safety & Alignment: Ensuring AI systems act according to human intentions
    • Examples: Alignment theory, control mechanisms, value alignment
    • Applications: Understanding risks from advanced systems and mitigation approaches
  • AI Governance: Frameworks for managing AI development and deployment
    • Examples: Regulation approaches, institutional oversight, international coordination
    • Applications: Evaluating governance proposals and identifying effective structures
• Creative Process & Productivity: Understanding how people create, maintain output, and navigate creative challenges
  • Focus on balancing creative pursuits with practical constraints like day jobs
  • Interest in both inspirational examples and implementable methods
  • Creative Discipline & Workflows: Structured approaches to consistent creative output
    • Examples: Daily rituals, work habits of successful creators, sustainable creative practices
    • Applications: Developing reliable systems for producing creative work
  • Creative Identity & Authenticity: Navigating the psychological aspects of creative work
    • Examples: Impostor syndrome, creative evolution, maintaining vision amid constraints
    • Applications: Balancing authentic expression with practical demands
  • Creative Careers & Sustainability: Approaches to making creative work viable
    • Examples: Side projects, parallel careers, transitions between creative/conventional work
    • Applications: Finding sustainable approaches to creative fulfillment
• Practical Wisdom & Mental Models: Frameworks and insights for better decision-making and navigating life
  • Focus on actionable principles, mental shortcuts, and experiential knowledge
  • Interest in both timeless wisdom and novel frameworks for thinking
  • Values concise, quotable formulations that distill complex truths
  • Experiential Insights: Wisdom derived from lived experience rather than theory
    • Examples: Life advice collections, distilled principles from practitioners
    • Applications: Avoiding common pitfalls, pattern recognition, improving judgment
  • Decision Frameworks: Structured approaches to making better choices
    • Examples: Goal-setting techniques, productivity systems, mental models
    • Applications: Overcoming cognitive biases, clarifying priorities, taking consistent action
  • Practical Philosophy: Applying philosophical concepts to everyday challenges
    • Examples: Stoic practices, mindfulness techniques, ethical frameworks
    • Applications: Building resilience, managing emotions, navigating difficult situations
• Wargames & Miniature Gaming: Complex tactical systems with physical models and rich fictional settings
  • Focus on Games Workshop's universes and gaming systems
  • Interest in both gameplay mechanics and narrative/setting elements
  • Values both competitive aspects and world-building depth
  • Warhammer 40,000 Ecosystem: Dystopian sci-fi universe with diverse factions and strategic depth
    • Examples: Army building, campaign narratives, setting lore, painting/modeling
    • Applications: Understanding strategic principles and complex system interactions
  • Specialist Games & Offshoots: Smaller-scale systems derived from core game universes
    • Examples: Kill Team, Necromunda, Lord of the Rings Strategy Battle Game
    • Values focused gameplay mechanics that emphasize narrative and character development
  • Historical & System Evolution: Understanding how game systems change and develop over time
    • Examples: Edition changes, rules refinements, balance adjustments
    • Applications: Analyzing design decisions and meta-game development
  • Painting & Modeling Techniques: Artistic aspects of miniature wargaming as creative expression
    • Examples: Conversion work, custom paint schemes, terrain building
    • Applications: Developing tactical displays that enhance gameplay experience
  • Community Engagement & Meta Analysis: Understanding competitive environments and social ecosystems
    • Examples: Tournament strategies, list building theory, faction matchups
    • Applications: Engaging with broader gaming communities and optimizing play approach
• Trading Card Games: Collectible strategy systems with evolving metas and deep gameplay
  • Focus on collection aspects with limited but meaningful gameplay engagement
  • Interest in both artistic presentation and strategic mechanics
  • Values both the collecting journey and potential gameplay opportunities
  • Magic: The Gathering: The original trading card game with decades of evolution
    • Examples: Card collecting, set completion, art appreciation
    • Applications: Understanding complex system interactions and strategic principles
  • Lorcana: Disney's entry into the TCG space with familiar IP and accessible mechanics
    • Examples: Collection building, potential future gameplay
    • Values the intersection of nostalgic character connections and fresh game design
  • Game Economy & Collection Management: Approaches to building and maintaining card collections
    • Examples: Storage solutions, collection tracking, acquisition strategies
    • Applications: Balancing collecting goals with practical constraints
• Video Games: Interactive digital experiences spanning multiple genres and eras
  • Focus on rich worldbuilding and systems-based gameplay
  • Interest in how technology enables unique interactive experiences
  • Values both narrative depth and emergent gameplay possibilities
  • Post-Apocalyptic & Dystopian Settings: Games exploring societal collapse and rebuilding
    • Examples: Fallout series (particularly Fallout 4, 76), System Shock
    • Applications: Examining complex societal interactions through simulation
  • Immersive Sims & Player Agency: Games emphasizing player choice and systemic interactions
    • Examples: Deus Ex, System Shock 2
    • Values deep player expression through meaningful gameplay choices
  • Sandbox & Simulation Experiences: Open-ended games focused on player-directed goals
    • Examples: The Sims, Grand Theft Auto series, Graveyard Keeper
    • Applications: Understanding complex systems interactions and emergent behaviors
  • Strategic & Civilization Building: Games focusing on large-scale management and growth
    • Examples: Civilization series, A Tale in the Desert
    • Values exploration of societal development patterns and resource management
  • Game Design & Development: Understanding the principles behind successful game creation
    • Examples: Design philosophies, technological implementation, industry trends
    • Applications: Informing potential future game studio founding efforts
    • Connection to existing Core Interest in Game Design Theory
  • Online Worlds & Social Dynamics: Multiplayer environments and virtual communities
    • Examples: World of Warcraft, Fallout 76
    • Applications: Understanding how game mechanics shape social interactions

Core Criteria (0 – 70 Points total)

1. Relevance to Core Interests (0 – 25)

• 25 – Advances multiple core interests or synthesises them in a strikingly novel way.
• 20 – Provides deep, original insight into one core interest and links clearly to another.
• 15 – Clearly develops or illustrates a single core interest.
• 10 – Tangentially related; may illustrate a known concept but adds little depth.
• 0  – No meaningful connection to stated interests.

2. Insight Density & Reference Value (0 – 20)

• 20 – Multiple standalone, quotable insights worth permanent storage.
• 15 – At least one significant insight worth highlighting for future reference.
• 10 – Contains some potentially useful information or examples.
• 5  – Mostly familiar material with minimal new value.
• 0  – No information worth revisiting.

3. Thought Provocation (0 – 15)

• 15 – Nuanced perspectives that force a genuine rethink or reveal hidden mechanisms.
• 10 – At least one elegant framing that encourages reflection.
• 5  – Presents ideas that prompt mild curiosity or follow‑up questions.
• 0  – Purely descriptive or familiar; no mental friction.

4. Source & Discovery Context (0 – 10)

• 10 – Originates from a trusted source or a highly regarded discovery channel.
• 7  – From a somewhat trusted source or peer‑recommended venue.
• 3  – Neutral/unknown provenance; no red flags but no endorsements.
• 0  – Feels promotional, agenda‑driven, or click‑bait adjacent.

Bonus Criteria (0 – 30 Points total)

Presentation & Clarity (0 – 15)

• 15 – Conversational tone and crystal‑clear step‑by‑step exposition with concrete examples.
• 10 – Generally accessible, good flow, helpful examples.
• 5  – Somewhat academic or dense but still readable.
• 0  – Dry, condescending, or lecture‑like.

Novelty Factor (0 – 5)

• 5  – Introduces an entirely new framework, mechanic, or lens (≈5 % of content).
• 3  – Fresh application of familiar ideas or combinations.
• 1  – Minor fresh twist within otherwise known territory.
• 0  – No new angles.

Contextual Depth (0 – 5)

• 5  – Cross‑cultural analysis that unlocks broader understanding.
• 3  – Meaningful contextualisation that enriches the main point.
• 0  – No substantial context beyond the immediate topic.

Cross‑Domain Transferability (0 – 5)

• 5  – Extracts principles clearly usable across multiple fields.
• 3  – Offers at least one insight that generalises outside its domain.
• 0  – Insights remain narrowly bound to a single context.

Topics to Avoid (Hard Penalties)

• Hyper-partisan politics or culture-war punditry: -75 points
• Pop-culture celebrity or entertainment gossip: -75 points
• Narratives centered on revenge or powerless suffering: -75 points
• Content designed primarily to trigger outrage over uncontrollable issues: -75 points
• Overt marketing, sales funnels, or lead-generation material: -75 points

Content to Approach with Caution (Moderate Penalties)

• Pure News / Event Reporting: -25 points
  • Facts without analysis linking to lasting principles
  • Time-bound information that loses relevance quickly
• Outdated Digital Product Reviews & Software Tutorials: -20 points
  • Software/hardware feature walk-throughs older than 2 years
  • Step-by-step technical guides focused purely on implementation without design principles
  • Consumer technology evaluations that lack systemic analysis of why design choices were made
• Highly Technical Deep-Dives w/out Systemic Framing: -15 points
  • Crypto protocols, AI model specs, etc., that fail to address wider implications
  • Technical descriptions without conceptual frameworks or broader context
• Short-Term Market & Investment Commentary: -25 points
  • Stock picks, macro predictions, or rate gossip unanchored to economic principles
  • Time-bound financial advice lacking evergreen principles
• Myopic Health / Lifestyle Optimization: -20 points
  • Narrow bio-hacks or supplement regimes unsupported by broader cognitive or systems framing
  • Isolated health trends without integration into holistic frameworks
• Academic or Career Status Talk: -20 points
  • Tenure politics, citation games, or prestige jockeying with no extractable institutional insight
  • Professional gossip lacking broader principles about institutional dynamics
• Policy or Regulation Critiques in a Vacuum: -20 points
  • Singling out one law (e.g., Jones Act) without drawing generalizable regulatory lessons
  • Narrow policy analysis without broader principles or patterns

Scoring Methodology

This rubric uses a point-based system with both positive criteria and penalties:

1. Calculate Positive Points: First, add all points from the Core Criteria (0-70 possible) and Bonus Criteria (0-30 possible) sections based on the document's strengths.
2. Apply Penalties: Next, subtract any applicable penalty points from the Topics to Avoid (-75 points per topic) or Content to Approach with Caution (-15 to -25 points per category) sections.
3. Determine Final Score: The resulting total represents the document's final score, which should be evaluated against the Final Score Interpretation scale.
4. Decision Rule: Documents scoring below 50 points after all calculations should be discarded, regardless of their initial positive score.

Final Score Interpretation

• 90‑100: Exceptionally interesting – drop everything to read and deeply engage
• 75‑89: Highly interesting – worth dedicated time and attention
• 60‑74: Quite interesting – worth reading completely
• 50‑59: Moderately interesting – skim for valuable sections
• Discard threshold (below 50 points)

Topics to Track

This section captures nascent topics that have appeared in my reading but haven't yet accumulated enough evidence to warrant promotion to core interests. Items here have typically appeared in 1-2 documents that resonated with me but don't yet demonstrate consistent engagement across multiple sources.

I track these topics to identify patterns in my evolving interests. When I notice multiple high-quality pieces related to the same tracked topic over time, this signals a potential new core interest emerging. This approach helps me recognize genuine shifts in my intellectual focus rather than temporary curiosities.

Each topic below represents a potential direction for future exploration that has shown some initial promise. They remain in this "waiting room" until sufficient evidence accumulates to justify promotion to a core interest.

• Cognitive Optimization & Attention – techniques and states (from memory systems to contemplative practice) that enhance mental performance or regulate focus.
• Leadership & Creative Practice – skill-building for high-leverage roles and sustainable creative careers that hasn’t yet folded into the Core “Creative Process & Productivity” interest.
• Tech-Futures Ethics & Governance – long-term thinking and moral analysis around emerging technologies, genetic selection, and far-future scenarios.
• AI Dynamics – surprising or little-understood emergent behaviors in AI systems that sit adjacent to, but aren’t yet central within, the AI Core Interest.
• Infrastructure Resilience & Security – systemic approaches to keeping physical and digital infrastructure robust against failure or attack.
• Public Systems & Policy Design – complex-systems views on public-health policy, regulation, and institutional architecture (distinct from day-to-day partisan politics).
• Culture, Language & Society – anthropological lenses on technology plus linguistic and cognitive diversity research that reveal how culture shapes thought.
• Open Web & Digital Commons – governance, sustainability, and advocacy for shared digital resources and open platforms.
• Game Facilitation – psychology and techniques for running engaging tabletop or live-action games; supports (but isn’t yet promoted into) the Role-Playing Games Core Interest.
• RPG Mechanics Innovation - Novel approaches to traditional tabletop systems that solve common gameplay issues or create new player experiences.