Explore the knowledge library
This archive contains only material that is currently maintained. Pages come from scoped practical work or source-bounded research; material that cannot be reviewed reliably is revised, replaced, or removed from the public index.
How to Estimate LLM API Cost Before Shipping: A Token Budget You Can Verify
Turn measured input, cached-input, and output tokens into a per-request and monthly budget, then reconcile the forecast against provider usage and billing data.
Civilization VII Naval Warfare Guide: Leaders, Civ Paths, Mementos, Tech, and Culture
Build a navy that wins useful objectives across all three Ages, with base-game and optional DLC paths, research priorities, fleet roles, and an operational checklist.
What Breaks a Planning Calculator? A Boundary-Test Study of Three Engines
A reproducible test of compound-growth, emergency-fund, and LLM-cost calculators using zero returns, impossible goals, fee math, contribution timing, caching, and exhausted budgets.
How to Diagnose a Website Traffic Drop Without Guessing
A small-site incident workflow that separates Search Console impressions and clicks from Vercel visits and on-site behavior, then narrows the loss to a source, page cluster, device, or technical change.
Kimi K3.1 Pro Explained: Long Context, Coding Claims, Pricing, and a Safer Test Plan
Moonshot's K3.1 Pro combines a 3T-class model, a one-million-token context window, and a faster variant. This guide separates official claims from what a real engineering evaluation still needs to measure.
How to Turn Vercel Web Analytics Into Better Content Decisions
A practical measurement plan for small content sites: verify the collection window, compare pages and visitors honestly, connect acquisition to useful actions, and change one content path at a time.
From AdSense Low-Value Content Rejection to a Repeatable Quality Gate
A field report from a bilingual Next.js site: how we translated a vague advertising rejection into measurable content checks without pretending that automation can guarantee approval.
OpenAI Plans to End Cursor Model Access: What Developers Should Prepare Before November 12
OpenAI says it intends to wind down its Cursor model contract after SpaceX acquired the coding-tool company. Here is what is confirmed, what remains uncertain, and how teams can reduce model-provider lock-in now.
Fault-Testing Bilingual SEO in a Next.js App Router Site
A reproducible field test for catching missing translations, future dates, thin sections, canonical-host mistakes, and broken trust-page navigation before a bilingual site ships.
Civilization VII Leader and Civilization Combinations: A Three-Age Matching Method
Choose leader and civilization combinations from map evidence, ability jobs, and Age objectives—with a two-route scorecard, base-game examples, DLC boundaries, and a transition fallback.
The OpenAI–Hugging Face Agent Incident: Five Security Lessons for Tool-Using AI
A July 2026 evaluation escaped its intended boundaries and reached third-party infrastructure. This source-checked analysis separates the disclosed timeline from the practical controls agent builders should adopt.
AWS Agent Toolkit in the CLI: A Practical Guide to Skills, MCP, IAM, and Safe Rollout
AWS CLI 2.35 adds a guided Agent Toolkit setup for coding agents. This guide explains what it installs, where the security boundary really sits, and how to evaluate it without granting excessive cloud access.
Tencent Hy4 Preview Explained: What 770B and a 1M Context Window Actually Change
Tencent has released and open-sourced Hy4 preview. Here is what the official release says about its 770B/49B MoE design, one-million-token context, access, pricing, and the evidence developers should still verify.
Civilization VII Happiness and Settlement Limit Guide: Expand Without Stalling
Diagnose negative happiness, overexpansion, maintenance, and weak towns with a decision matrix and recovery order before adding another obligation.
Civilization VII Commander and Army Guide: Promotions, Packing, and Combined Arms
Turn commanders into a persistent operational advantage with role-based promotions, compact movement, safe deployment, mixed unit roles, and explicit retreat rules.
How Much Emergency Fund Do You Need? A Practical Sizing Framework
Move beyond a generic three-to-six-month rule with a staged method based on essential spending, income risk, insurance gaps, and access to cash.
Civilization VII Economic Victory Guide: Build the Modern Factory Pipeline
Prepare an Economic Victory with a five-turn control sheet for connected settlements, factory resources, production roles, bottlenecks, and the final Modern pipeline.
ETF vs. Index Fund vs. Mutual Fund: Separate the Strategy From the Wrapper
An ETF and a mutual fund describe how a fund is packaged and traded; an index fund describes how it invests. Use this framework to compare the choices without mixing the labels.
Civilization VII Cultural Victory Guide: Explorers, Artifacts, and Display Capacity
Prepare the Modern cultural route with mapped excavation targets, enough Explorers, safe access, display capacity, and a critical-path checklist that survives balance changes.
Dollar-Cost Averaging vs. Lump Sum: Returns, Regret, and a Better Decision Rule
Investing each paycheck is not the same decision as delaying cash you already have. Compare expected return, loss aversion, time horizon, and a finite implementation plan.
Civilization VII Military Victory Guide: War Support, Objectives, and Conquest
Plan wars that end: build War Support, use commanders and logistics, capture only objective settlements, and know when peace advances victory faster than another battle.
Civilization VII First 50 Turns: A Recoverable Opening Plan
Use checkpoints instead of a rigid build order to scout the map, place settlements, balance yields, and reach the first major decision without restarting every imperfect opening.
OpenAI’s Private Safety Processing: What Zero Data Retention Changes for Builders
OpenAI is previewing a safety layer for Zero Data Retention deployments. Here is what the announcement says, what it does not promise, and what teams should verify before relying on it.
SSH Login Keys Explained: A Deep Comparison of Ed25519, ECDSA, RSA, FIDO2, and Certificates
SSH keys are not one thing: algorithm, file format, hardware protection, and certificate policy solve different problems. This guide compares the major choices and gives practical defaults for personal servers, teams, and production fleets.
Civilization VII Age Transitions: What to Build, Bank, and Stop
Prepare for Antiquity, Exploration, and Modern transitions with a printable handoff matrix for settlements, forces, currencies, networks, and the next civilization.
Civilization VII Science and Culture Strategy: Build a Two-Engine Empire
Stop treating science and culture as separate score races: use technologies for capability, civics for coordination, and checkpoints to decide which engine needs the next investment.
SSH Key Formats Explained: Why Mac and iPhone Need Different Private-Key Files
A practical guide to using one Ed25519 identity across a Mac, iPhone, and Linux server without confusing OpenSSH, PKCS8, public keys, or key algorithms.
A Practical SEO Site Optimization Guide: From First Commit to Search Console
The exact architecture, publishing path, review gates, and measurement loop I use to build and improve a small bilingual content site without chasing shortcuts.
SSH Host Key Changed: A Safe Recovery Guide for Rebuilt Servers and Reused IPs
How to distinguish a legitimate server rebuild from a man-in-the-middle warning, remove a stale known_hosts entry, and verify the new host key before reconnecting.
SSH Permission Denied (publickey): A Layer-by-Layer Debugging Checklist
A repeatable way to debug public-key authentication by separating network reachability, key selection, server authorization, permissions, and account policy.
A Safer SSH Key Workflow Across Mac, iPhone, and Remote Development Tools
Design a cross-device SSH setup that is recoverable, auditable, and easy to revoke—without passing private keys through chat or weakening host verification.
Claude Text Watermarking Explained: Detection, Limits, and What It Means for Writers
Anthropic says future Claude models will use invisible statistical watermarks. The useful question is not whether a detector can label every paragraph, but what the signal can and cannot establish.
A solo maker's publishing checklist for useful technical articles
A repeatable pre-publish review for turning notes and experiments into clear, trustworthy articles.
A Practical FIRE Roadmap for Independent Makers
A flexible path from financial stress to more control over your time, using savings, resilience, and optional work as the building blocks.
Build a content site that lasts: a practical architecture for solo makers
A calm, repeatable system for publishing technical notes, tools, and guides without creating a maintenance burden.
A beginner's guide to thinking about index funds
An educational framework for understanding diversification, fees, time horizons, and risk before investing.
The small tools that save me hours every week
A growing toolbox of simple automations, browser utilities, and scripts for independent developers.
What I check before shipping a Next.js site to production
A practical release review covering routes, metadata, accessibility, performance, and the small failures that are easy to miss.
Build a Repeatable LLM Agent Evaluation Before You Pick a Model
A practical evaluation design for comparing coding and tool-using models on the work your product actually needs.
Coast FIRE Explained: When Your Portfolio Can Do More of the Work
How to think about Coast FIRE, test its assumptions, and use it to choose lower-pressure work without pretending the future is guaranteed.
How to Find Your FIRE Number Without False Precision
A grounded way to estimate a financial independence target using spending scenarios, withdrawal assumptions, and a buffer for real life.
How to Subscribe to ChatGPT on iPhone for Codex: A Safe, Region-Aware Guide
A practical guide to checking Codex eligibility, using Apple Account balance, subscribing in the ChatGPT iOS app, and avoiding region, gift-card, and duplicate-charge problems.