Always in the middle of something.
Chasing ideas across ML, AI, and data. Building tools when the rabbit hole gets interesting enough.
Editor's picks
Kimi K3 Benchmarks vs Claude Fable 5 and GPT-5.6 Sol
Moonshot's model card scores Kimi K3 against Claude Fable 5 and GPT-5.6 Sol across 45 benchmarks. Some rows go to K3 and some to the others, with margins running from fifteen points down to a tenth — plus what $3/$15 per million tokens buys.
Kimi K3 適合什麼任務？跟 Fable 5、GPT-5.6 Sol 的對照表怎麼看
Moonshot 七月發表的開源模型 Kimi K3，README 附了一張跟 Fable 5、GPT-5.6 Sol 的對照表。這篇挑六項分數來看，也整理了價格與輸出速度，談哪些任務可以交給它。
What functools.wraps restores when you decorate a function
A decorator replaces your function with a wrapper, so its name, docstring, and signature change. Here is exactly what functools.wraps copies back and how it records __wrapped__.
Before an incident, test whether your AI provider will accept attack logs
Hugging Face's forensics were refused by the commercial APIs it tried first. The block is an access setting, so test what your account does with attack data.
Tokenization 到底佔多少成本？從 0.1% 到 99% 的落差是怎麼來的
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。
How temperature, top-k, and top-p shape an LLM's output
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.
Python 的可變預設參數為什麼會累積
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。
Claude Projects 新手教學：從零設一個專案，指令跟知識庫該放什麼
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。
How to Use Claude Projects: A First-Time Setup
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 preprocessing before the split inflates your accuracy
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.