Always in the middle of something.

Token counts land on your API bill and decide whether a prompt fits the context window. Here's why Chinese usually costs more tokens than English, why eyeballing it fails, and how to see the real number for any chunk of text.

Token 數會反映在你的 API 帳單，也決定一段文字塞不塞得進 context window。這篇聊為什麼中文通常比英文花更多 token、為什麼用猜的估不準，以及怎麼實際看一段 prompt 有多少。

SpaceX 用 600 億美元買下了 Cursor，大約是它年收入的 15 倍，普遍認為是史上最大的 VC 新創收購案。這個倍數背後有個具體的賭法：AI coding 工具的乘數效應，讓你值得付出基礎建設等級的溢價。

SpaceX's $60B acquisition of Cursor isn't just M&A. At roughly 15x revenue for a four-year-old startup, the price encodes a specific thesis: that AI-assisted engineering compounds engineer output in a way worth paying an industrial premium for.

uv is Astral's Rust-written Python tool that folds pip, venv, pyenv, and pipx into one command — and installs packages several times faster. What it replaces, how fast it really is, and whether you should switch.

uv 是 Astral 用 Rust 寫的 Python 套件工具，把 pip、venv、pyenv、pipx 收進同一個指令，安裝又快上好幾倍。聊一下它取代了哪些東西、快多少，還有要不要換。

f-string 不只是 f"{變數}"。冒號後面的格式設定、3.8 的 = 自我說明、3.12（PEP 701）鬆綁的同引號巢狀與跨行，一層一層看完，順便聊什麼時候別用它。

lambda 語法五分鐘學得會，難的是什麼時候用。聊它真正的家（sorted 的 key=）、PEP 8 為什麼叫你別把它綁給變數，還有迴圈裡三個 lambda 都回同一個值的陷阱。

Sam Altman said people saying 'please' and 'thank you' to ChatGPT costs OpenAI tens of millions. I measured it with a tokenizer: your 'thanks' is two tokens. The real cost is the whole reply it forces.

Sam Altman 說大家對 ChatGPT 講禮貌，燒掉 OpenAI 幾千萬美元。我用 tokenizer 實際量了一次：你那句「謝謝」只值兩個 token，真正貴的是它叫醒的整台機器。