Notes from a mediocre idealist

A few quiet things
on memory, money & machines.

I do not know what I am doing. I am doing it anyway. The work is small and it is mine.

What I have written, slowly

Each one comes with a voice, made by a quiet machine, for the people who listen while they walk.

Copilot Studio
GenAI · Copilot Studio · Knowledge Work

Copilot Studio × Teams / Outlook: making GenAI actually land on the frontline.

Series #3. Four agents, three fallbacks, two integration paths. Why entry point + real data + observability is the last mile from PPT to production.

2026-07-27 Audio 5:37
Power BI DirectLake
Power Platform · BI · Automation

Power BI DirectLake × Power Apps/Automate: when data can act for itself.

Series #2. Three production scenarios — on-site pricing approval (1-2 days → 30 min), auto-launch reports, GMV anomaly alerts. One semantic model, four consumers.

2026-07-27 Audio 6:09
BigQuery to OneLake
Data Engineering · Cloud · Cross-cloud

When Google BigQuery meets Microsoft OneLake: three paths for a cross-cloud data lake.

Series #1. Data Factory + IR (recommended), Synapse Link (near-real-time), Spark on Databricks (most flexible). Decision tree, config YAML, four pitfalls.

2026-07-27 Audio 9:19
CXMT
Markets · Storage · China

CXMT's valuation logic: the new king of A-shares at 3.3 trillion yuan.

Listed July 27 at +471%. The only domestic DRAM supplier, fourth globally, riding the AI HBM super-cycle. Six drivers, three risks, three positioning ideas.

2026-07-27 Audio 2:38
NLP Learning Path
Career · GenAI · NLP

NLP + GenAI: a six-month path from data scientist to GenAI data scientist.

Six months. Three projects. One offer. Transformer, RAG, Agent — the exact curriculum, week by week, with the resources that work.

2026-07-26 Audio 2:28
Karpathy LLM Wiki
Methodology · Knowledge

Karpathy's LLM Wiki: an idea that quietly changes how we manage knowledge.

Three months, 5K stars, one idea. Stop re-reading raw documents on every query. Compile them into a wiki the LLM maintains. The compounding artifact.

2026-07-26 Audio 2:43
Wall Street
Markets · 13F

Wall Street's latest positioning: Berkshire and Bridgewater.

Two icons, opposite moves. Buffett piles $348B cash. Dalio rotates hard into AI hardware. What both signals say about the next year.

2026-07-25 Audio 2:14
Memory Cycle
Storage · Cycle

Is the memory cycle peaking? Six core signals.

DRAM up 60%, NAND up 70% — this is structural scarcity, not a normal cycle. Six data dimensions tell you where we are.

2026-07-24 Audio 1:54
Value & Quant
Investing · Method

Value meets quant: a personal approach.

Many retail investors see value and quant as opposing methods. They're not. Combined, they form a "selectable + executable" framework.

2026-07-24 Audio 1:42
RAG vs AutoRAG
AI · RAG

RAG vs AutoRAG: principles, trade-offs, scenarios.

Enterprise RAG accuracy below 30%? Not a model problem — a flow problem. How AutoRAG closes the 5% to 78% gap.

2026-07-24 Audio 1:35

About the writer

I am not particularly good at anything. I read more than I understand. I write more than I should.

I keep notes on things that probably do not matter — storage cycles, the rhythm of language models, the shape of value investing, the quiet algebra behind a good night of sleep. This place is where those notes land.

There is no mission. There is no growth funnel. There is no audience, except maybe you, on a slow afternoon, scrolling past without much expectation.

I write because I am the kind of person who needs to. It is a small and ordinary thing. I am proud of it and a little embarrassed by it at the same time. That feels about right.

Some of the pieces here come with a voice — a quiet, careful voice that I had a machine read aloud to me while I was making tea. You can press play if you want, or you can read silently. Either way is fine. Either way is real.

Everything is free. Nothing is optimized. The cover images were made by a small artificial mind that does not know what it is doing. The articles were written by a person who also does not know what he is doing. We made a reasonable team.

If something here is true, it was an accident. If something here is wrong, it was probably the coffee.

— Chase
Shanghai, occasionally.
网站二维码
a few quiet things
扫码查看文章
q