Posts

同一串討論底下，有人量到 tokenization 不到總推論時間的 0.1%，也有人量到九成以上的 CPU 時間都花在這裡。這篇看這個落差怎麼來的：算的窗口不同、模型大小不同，還有一些工作根本沒有模型在裡面。

A worked walk through the three main LLM sampling knobs: temperature reshapes the whole next-token distribution, while top-k and top-p truncate which tokens you may sample from.

用 list 或 dict 當函式的預設參數值，資料會跨呼叫累積，因為預設值在 def 執行時就算好一次並掛在函式物件上。本文示範現象、用 __defaults__ 驗證，並給出 None 哨兵修法。

第一次用 Claude Projects，最容易卡在規則跟資料該放哪。這篇帶你從零開一個專案：希望它每次照做的規則寫進專案指令，需要它參考的資料丟進知識庫，順便講免費帳號能開幾個。

A plain walkthrough of setting up your first Claude Project from scratch, organized around the one decision that makes it work: what goes in the project instructions versus the knowledge base.

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.

is 比對物件身分，== 比對值。小整數快取讓某些整數上兩者剛好一致，但那是不保證的 CPython 實作細節，整數值該用 == 比。

On July 18, 2026, Anthropic reversed its month-long plan to meter Claude Fable 5 and is keeping it in subscriptions permanently. Here is what changes on July 20 for Max, Team Premium, Pro, and Team Standard — and why a run of competitor launches made the reversal hard to avoid.

Anthropic 原本要在免費期後把 Claude Fable 5 從訂閱移除、改走計量付費，一個多月來截止日一延再延。7/18 方向翻轉：7/20 起把 Fable 5 併回 Max 與 Team Premium 訂閱、永久包含。這篇整理這段來回的時間軸、新的訂閱條款，還有 GPT-5.6 Sol 跟 Kimi K3 這波競爭扮演的角色。

GLM 5.2 shipped with open weights under an MIT license, which generally permits third parties to host and commercialize inference. As of writing, OpenRouter lists twenty-five providers offering it, at input prices from $0.93 to $3.00 per million tokens.