If you’re new here, this is probably the easiest way in. These are a few posts I’d point someone to first — roughly grouped by topic. Pick whichever heading looks closest to what you’re after; the rest of the blog branches out from here.
AI Systems
A prompt and a skill can contain the same words. The difference is the machinery around them: a skill is a file the model loads on its own when your request matches its one-line description, and it can declare inputs, tools, and a scope it won't cross. Here's how that loading works and why it lets you build things a prompt can't.
Why AI agents fail: most failures trace to governance gaps (phase gates, state handoffs, capability boundaries) more than to the model itself, and the two need completely different fixes. How to tell them apart.
Token 是什麼？LLM 為何不直接處理完整字詞：解析字級、字元級、子詞級三種 tokenization 方法，包含 BPE 示範程式碼，以及 token 數量對計費和上下文長度的影響。
Machine Learning
Fitting a preprocessing or feature-selection step on the whole dataset before the train/test split leaks the labels and inflates a model's estimated accuracy. A pure-noise scikit-learn run shows the gap, and the pipeline fix closes it.
LSTM 用遺忘門、輸入門、輸出門三道閘控制 cell state，讓資訊靠加法而不是連乘往前傳，避開一般 RNN 的梯度消失。這篇把當年只列了名字的閘門部分補完，並交代它在 Transformer 之後的位置。
Python
A relaxed take on Python list comprehensions: translate them back into the equivalent for-loop, and check what's actually true about variable leaking and speed on Python 3.14.
用 Python 爬取台股即時股價：從 DevTools 找到證交所 getStockInfo API，解析 JSON 回應，取得台積電等個股的即時成交價、最高最低價與五檔報價。
