Blog
Every post ships with paired language pages, RSS, and raw Markdown output.
How to Spot an Empty AI Money-Making Post — and Train Yourself to Think Deeper
The internet is full of 'office worker makes $2,000 a month with the latest AI' side-hustle marketing. This piece teaches you five fingerprints for spotting hollow content, a thirty-second wallet check, and six thinking habits you can practice daily — write down a dated prediction, explain it plainly, write your own answer first, ask how a claim could be falsified, think one step further, and cool off for 48 hours. Educational sharing, no accounts or platforms named, not investment advice, disclaimer at the end.
The Mirror Protocol: I Let an AI Read All 6,139 of My Commands. It Described Someone I Didn't Recognize.
A prompt circulating in the AI community: have an agent excavate every session log on your machine and answer 'who are you' using your own timestamps. Six phases, fully local, full prompt included for copy-paste. This is my run — including the part where my own records called my bluff.
Certainty for Sale: What My Colleague Is Really Buying from That Finance Channel
A colleague started following a large Taiwanese stock-tutorial channel, and I didn't read it as poor judgment on his part. What he's buying isn't financial knowledge—it's the feeling that the market can be understood, predicted, and controlled. This piece uses behavioral finance and media literacy to unpack the six psychological needs these channels target so precisely, the free-trust-to-paid-course marketing funnel, and three questions you can carry with you to test any of them. An educational reflection—no channel is named, not investment advice, disclaimer at the end.
Gooaye EP678 Notes: Meta Just Put Compute Pricing in the Sunlight — the Fog Behind Dream Multiples Is Lifting
Personal notes on Gooaye EP678: Meta repurposing old GPUs for inference and renting them out — refuting the 'AI server bad-debt' short thesis while making compute pricing transparent, which pressures dream-multiple valuations; rotation inside optical communications; the broad component price-hike wave. Educational notes, not investment advice; disclaimer at the end.
Saying Goodbye to Fable 5: I Asked a Retiring AI to Leave Behind How It Thinks
The strongest model on my AI team retired today. In our last two days, I didn't ask it to do more work — I asked it to write down its thinking process. It left a map of my life's key problems, ten crisis playbooks, an honest gap map, and a letter. This is the record of those two days, and what I learned.
When the Strongest GPT-5.6 Meets a Suddenly-Genius Grok 4.5: I Used Claude to Turn Three AIs Into One Team
How a one-person AI company actually works: let Claude be the head coach that plans the hard problem and nails the interface, hand the execution to OpenAI's GPT-5.6 and a suddenly-sharper xAI Grok 4.5 running in parallel, then verify against reality. Three days of multi-vendor AI teamwork, shared as method and reflection.
Statementdog (財報狗) EP538 Notes: While Everyone Cheers the Compute Boom, I'm Asking Who Got Left Out
Personal notes from Statementdog (財報狗) Podcast EP538: anti-bubble thinking, Korea's memory deleveraging, memory prices slowing but supply still tight, firms starting to rein in AI spend, and compute going tiered-and-cheaper. Plus how the episode echoes two things I've been practicing: separating noise from structure, and watching cross-market leverage. Educational notes, not investment advice; disclaimer at the end.
A Few Things I Saw on X This Week: The Fastest Information Needs the Most Filtering
Personal trend notes after following a few sharp market voices on X: a 'dumbest thematic selloff' driven by noise, memory price hikes that shamed the doubters, the US-China humanoid-robot gap as a Sputnik moment, and $10T price targets as froth signals. X gives you the fastest information — and it's also where you most need to separate signal from noise. Educational notes, not investment advice; disclaimer at the end.
AI-900, Part 2: How I Used AI to Turn a Question Bank Into the Fastest Review System
The parts the first post skipped: where to get practice questions (and an honest caveat), how to use AI to build a personal question bank that auto-quizzes, grades, and logs your misses, how to get AI to teach you the 'concept tree' instead of memorizing service names, and how to use AI to make review tables that cover the most concepts in the least time. A learning-method piece, not official courseware.
Statementdog Podcast EP537 Notes: Cybersecurity, Software-Defined Defense, and Reading SaaS via 'Contract Liabilities'
Personal takeaways from Statementdog (財報狗) Podcast EP537 (industry deep-dive, cybersecurity special): AI-automated security, the new business of protecting AI, software-defined defense and counter-drone, and using contract liabilities to read a SaaS company's momentum. With a full glossary of terms and techniques, sectors worth researching, and references. Educational notes, not investment advice; disclaimer at the end.
Gooaye Podcast EP677 Notes: Stay Away From Leverage, Don't Predict the Bear — and My Two Shifts This Half-Year
Personal notes from Gooaye (股癌) Podcast EP677: the ruinous risk of extreme leverage, Taiwan's pullback and Korea's deleveraging, research-firm noise vs the long-term AI trend, and the rotation between hardware and software. Plus how my investing views and my inner state shifted recently. Educational notes, not investment advice; disclaimer at the end.
A Subscription Is Not a Discount: Wiring Grok 4.5 into Claude Code, and One Security Self-Audit
An overlooked billing trap: a subscription buys you quota inside the official app, while most third-party tools reach the model through the metered API. This is my attempt to run Grok 4.5 inside Claude Code and still bill it to my subscription, the grey-zone path I found, and the four-question security audit I ran on a third-party tool before letting it hold my account token. Tech notes and hands-on lessons, not a how-to.
After the OAuth Wall: Three Ways to Run Grok in Claude Code, and What I Actually Learned
The OAuth cliffhanger from last time, resolved. A diagnostic mistake — reading a personal subscription as a team account — sent me the long way round; once cleared, there turned out to be three ways to run Grok in (or next to) Claude Code, each with a price. But the real takeaway isn't 'I found the method' — it's rethinking how to allocate tasks: unattended automation rides the stable billing path, and only human-in-the-loop work rides the cheap subscription path. First draft written by Grok 4.5 itself.
Passing AI-900 in Two Weeks: A Quant Investor's Study Method and Key Concepts
How I passed Microsoft Azure AI Fundamentals (AI-900) in two weeks using block-based sprints, a one-page service cheat sheet, and spaced retrieval testing — plus a roundup of the most-tested, easiest-to-confuse concepts. A learning-method piece, not official courseware.
Unreasonable People and the Power Law: Three Quiz Questions That Exposed the Cracks in My Investing Instincts
Notes from reading the introduction to Sebastian Mallaby's The Power Law: three quiz questions that reveal the gap between a retail investor's instincts and how the power law actually works — hit rate vs. the single winner, mean reversion vs. watering weeds and cutting flowers, courage vs. position sizing. Pure reflection and method education; disclaimer at the end.
I Spent Hundreds of Hours Proving Moving-Average Crossovers Dont Work
A negative-result study showing that after 11,151 U.S. stocks including delisted names, a 31.7% survival rate, price-band controls, and trading costs, moving-average crossovers have no tradable edge.
Contract Liabilities: A Peek at How Much Future Revenue a Company Has Already Locked In
A contract liability is money a customer has paid before the company has delivered. Why it sits under liabilities, why it's a leading indicator of future revenue, and how to find it in the financial statements step by step. Pure method education; disclaimer at the end.
Why We Freeze an Expiry Date onto Every Prediction
The design philosophy behind a prediction-scoring system: pre-register the criteria, pair naive hit rate with a benchmark, refuse to conclude on thin samples, and handle conditional forecasts honestly. It is really about how not to fool yourself.
Turning Podcasts and YouTube into a Searchable Research Archive
A subtitle-first, ASR-as-fallback fetch pipeline, plus three lessons learned the hard way: drip slowly against 429s, track state fully or spin in place, and treat missing captions as normal rather than a block signal. Includes reusable Python snippets.
Two Philosophies of the Stop: Price Stops and Position Caps
A stop is not one move but two philosophies: one cuts on price, the other cuts on size. Who each suits, why being right can still kill you, and why protecting capital is protecting your ability to recover. Educational method only, with a disclaimer at the end.