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.

Notes on memory, money & machines

A small library of slow, deliberate essays. Each comes with a voice.

karpathy autoresearch
AI Research · Karpathy · Agentic

karpathy/autoresearch:3 文件 + 1 agent = 100 实验/晚。

630 行 Python 教了科研范式转变。agent 编辑 train.py、跑固定 5 分钟、比较 val_bpb、keep / discard。一晚 100 个实验,~12% 命中率。

2026-07-29 Audio 2:25
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 4:00
BigQuery × OneLake
Data Engineering · Cloud · Cross-cloud

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

Open lakehouse (Iceberg + Trino) wins on flexibility. Direct federation wins on speed. Mirrored lake wins on ops. Most teams want #1, ship #2, regret it.

2026-07-27 Audio 5:12
CXMT
Markets · Storage · China

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

Why CXMT's 3.3T market cap, 80x P/E, 9% earnings yield compression is not a bubble but a national strategic repricing.

2026-07-27 Audio 4:50
GenAI path
Career · GenAI · NLP

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

Personal learning log, 6 months, 5 phases. From RAG to agents to prod. What worked, what didn't, what took longer than expected.

2026-07-27 Audio 6:24
LLM Wiki
Methodology · Knowledge

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

Karpathy's idea-file pattern: a self-rewriting markdown index for everything you've read. Reviewed, not stored.

2026-07-27 Audio 4:18
13F
Markets · 13F

Wall Street's latest positioning: Berkshire and Bridgewater in Q1 2026.

13F filings decoded: Berkshire trimmed Apple, Bridgewater went long China, Tiger Global rotated from tech to staples. What it tells us about Q2.

2026-07-27 Audio 5:33
Memory cycle
Storage · Cycle

Is the memory cycle peaking? Six core signals.

DRAM and NAND pricing, capex, inventory, customer behavior, lead times, geopolitical exposure. A framework for knowing when the top is in.

2026-07-27 Audio 4:55
Value + quant
Investing · Method

Value meets quant: a personal approach.

How I merge Buffett-style quality with momentum and a 5-year backtest. Less rule-following, more first-principles.

2026-07-27 Audio 3:42
RAG vs AutoRAG
AI · RAG

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

When RAG is enough. When you need agents. Why most 'AutoRAG' projects are actually configuration-management, not research.

2026-07-27 Audio 1:35

Where the math meets the market

A-share backtests, sentiment indices, factor models. Code on GitHub, data via AkShare. All real, no simulations.

Semi 14 ML
Quant · Cross-Section ML · 14 Dragons

半导体 14 龙头横截面 ML:Mean IC +0.045,Top 10% +76.92%。

把 14 只 A 股半导体龙头拉成横截面,26 alpha + LightGBM walk-forward 18 月。最强因子是量能 z-score + 52w 低点位置 + 3 月动量。板块集中信号比全市场扫描稳定 6 倍。

2026-07-31 New research
Quant 5 Schools
Quant Research · Factor · ML

Quant 5 Schools + Cross-Section ML: real A-share backtests.

用 A 股真实数据跑量化五大流派 + 横截面 ML:5 个里 4 个跑输 buy & hold,IC -0.018,但 Q5 +1.13% alpha。坦诚地跑一遍。

2026-07-30 New research
A-Sentiment
Quant · Sentiment · Fear & Greed

A 股情绪指数:当市场恐慌到 24.4 分,我做了件事。

仿 CNN 恐惧与贪婪指数的 A 股版。13 个成分 + 滚动分位数标准化。当前 24.4 分极度恐惧,按 2018-2026 回测极恐(<25)后做多 60 日胜率 55.3%,极恐 2 胜率 60%。

2026-07-28 Audio 4:44
Sector Sentiment v2
Quant · Sector Sentiment v2

行业版 v2:1 个极度恐惧,5 个恐惧,1 个中性。v1 极恐 4 个全修正。

v1 5 成分(漏接 macro)→ v2 13 成分全档(接上 macro_china_market_margin + stock_hsgt_hist_em + index_option_50etf_qvix)。科技 +19.9、周期 +19.2、新能源 +18.1。

2026-07-28 v2 Update
A-Sentiment v2 Upgrade
Quant · v2 Upgrade · Data Repair

v2 升级:从 24.4 到 14.7 · 13 成分全档 + 0 元数据修复。

v1 标记的 4 个数据缺口,80% 是我用错了接口。修正后:13 成分全档、当前情绪从 24.4 跌到 14.7、极恐样本翻倍、胜率更准。成本 0 元。

2026-07-28 Audio 3:48

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