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
What the parameter count in a model's name means
The B in a name like gpt-oss-20b counts parameters, in billions. Multiply that count by the bytes each parameter takes and you get a floor for the memory the weights need. That is also why some models now ship with two numbers instead of one.
7B、70B 是什麼意思？看懂模型名字裡的參數量
模型的 7B、70B、235B 講的是參數量，B 就是十億。這篇說明參數量代表什麼、怎麼換算，以及 Qwen3-235B-A22B 這種寫法裡的兩個數字又各自代表什麼。
Running more AI reviewers on the same code
Fan three or four AI reviewers at the same diff and what comes back is a list of candidates. Agentic OS's own audit records show how many survive checking, and why its default has dispatched subagents return evidence while one primary owns the write.
subagent 分派：第二個 agent 該拿到什麼
開一個 agent 去看另一個 agent 做完的東西很容易，難的是後面那個看得見前面漏掉了什麼。從 Agentic OS 的 review 規定看下去：要讓第二個 agent 看得出東西，靠的是刻意不給它 session、對話記錄和實作理由。
How the KV cache speeds up LLM generation
A transformer redoes the same attention projections for every past token at each decoding step. The KV cache stores those keys and values so they get reused instead of recomputed, and the one cost it adds is memory that grows with the sequence.
為什麼分類的損失函數幾乎都是交叉熵
把 softmax 加交叉熵對 logit 的導數一路算出來，結果剛好是預測機率減去標籤。這篇從一個三類別的小例子走進這個梯度，看它為什麼乾淨、又為什麼信心錯得越離譜就修得越用力。
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.