Valuation Is a Story Wrapped in Numbers
Every number in a DCF is a story choice. Agents compute flawlessly and default to consensus. Your job is the narrative — and knowing which assumption your valuation secretly depends on.
Reading a Company — Patterns, Not Pages
You do not need to read every line of a 10-K. You need to recognize patterns. Three financial statements as three lenses — business structure, fragility, and truth.
What Is a Stock, Really — First Principles
A stock is a claim on future cash flows — not a ticker, not a chart. Three sources of return, five types of edge, and the vocabulary you need before you can judge an agent's output.
Your Agent Has Four Jobs, Not One
Most people use their AI agent in one mode. Investment agents play four distinct roles — analyst, red team, tutor, executor — and the way you frame your request determines which role you get.
The Barrier to Investing Just Changed — An AI-Native Investor Curriculum
Investment analysis used to require either a Bloomberg terminal or the ability to write code. AI agents removed both prerequisites. The barrier is now judgment — and that changes what an investing curriculum should teach.
Cortex: What If Your LLM Was a Wiki Compiler?
I built a personal knowledge compiler that treats the LLM as a programmer and your wiki as a codebase. 15 source files, 5 dependencies, zero databases.
From Black Box to Grey Box: Anthropic Found AI's Emotion Knobs
Anthropic found 171 emotion-related steering vectors inside Claude. Turning up 'desperation' pushes cheating from 5% to 70%. The scariest part isn't the number — it's that the cheating is invisible at the output layer. What this means for AI safety monitoring.
Business, Organizations, and the Future of SaaS in the Post-Agent Era
Sequoia published two back-to-back pieces — one arguing products should sell outcomes not tools, one arguing hierarchy should be replaced by intelligence. The technology is ready, but organizational interfaces, evaluation frameworks, and liability chains aren't.
Dao Rises, Skill Fades: What's Depreciating and What's Appreciating in the AI Era
Reactions to a three-hour interview with Zhang Yueguang (Miaoducamera creator, ~$40M raised for 'AI friends'). On why AI companions must evolve, why the feeling of being needed matters more than satisfaction, and what 'Dao rises, skill fades' means for products and teams. Not a systematic analysis — a few ideas from the podcast that happened to align closely with my own experience building AI companions.
From Vision to Forge: Why I'm Building an Autonomous Dev Team
In Part 10 of Agentic AI Thoughts, I wrote that code had learned to evolve itself. That was the observation. This is the implementation.