Home » Tags

LLM

AI Systems

What Makes an AI Skill Different from a Prompt?

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.

AI Systems

Token 是什麼？LLM 為何只讀 Token？

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。

LLM

See all 47
AI Systems

Claude 的文字浮水印怎麼運作

Anthropic 說明了未來 Claude 的文字浮水印怎麼做：做法是換一個亂數來源，用來決定下一個字挑哪一個，不加字也不多花 token。這篇是來聊聊我們目前獲得的資訊有哪些。

AI Systems

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.

Token Economics

See all 16
AI Systems

The Same GLM 5.2 Has Different Prices Across Providers

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.

Agent

See all 15

Prompt Engineering

See all 14
AI Systems

What Makes an AI Skill Different from a Prompt?

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.

Architecture

See all 8
AI Systems

What Makes an AI Skill Different from a Prompt?

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.

Governance

See all 8
AI Systems

Claude 的文字浮水印怎麼運作

Anthropic 說明了未來 Claude 的文字浮水印怎麼做：做法是換一個亂數來源，用來決定下一個字挑哪一個，不加字也不多花 token。這篇是來聊聊我們目前獲得的資訊有哪些。

AI Systems看中文版

What Are GPT-5.6's Sol, Terra, and Luna?

OpenAI shipped GPT-5.6 as Sol, Terra, and Luna on July 9, 2026, and quietly ended the dedicated Codex checkpoint. What replaced it is a reasoning-effort dial whose top notch spawns subagents. This post lays out the three models, the six effort levels, and what the independent benchmarks measured.

AI SystemsRead in English

GPT-5.6 的 Sol、Terra、Luna 是什麼

GPT-5.6 在 2026 年 7 月 9 日全面上線，分成 Sol、Terra、Luna 三階，而這一代的 Codex 沒有專用模型。專用 checkpoint 換成一格叫 ultra 的 reasoning effort，官方說它會叫 subagent 出來把大任務拆開做。這篇整理三顆模型怎麼分、六段 reasoning effort 是什麼，以及幾份獨立評測量到的數字。

Claude Code

AI Systems

The Skill Your Annoyed Prompt Becomes

Your first Claude Code skill won't look like the polished examples in tutorials. It'll look like a prompt you've typed three times in a row, saved into a four-line markdown file. This post walks that minimum shape, shows the three things that break, and compares it to a real seventeen-line production-grade skill from the framework I use daily.

AI Systems

What a 13-Line Skill Leaves Out

I asked Claude to draft me a skill that calls OpenAI's Codex CLI. It came back as thirteen lines of markdown. The thirteen lines aren't the skill — they point to where the skill actually lives. That split between dispatcher and contract is what separates a skill from a prompt.

NLP

AI Systems看中文版

Why Does AI Forget What You Said Earlier?

Chat with an AI long enough and it ignores the rules you set up top; open a new chat and it's blank. It isn't 'forgetting' — it has no memory. Every reply, it re-reads the whole conversation from scratch. Here's what the context window is, and how it differs from ChatGPT's 'memory' feature.

AI SystemsRead in English

為什麼 AI 會忘記我前面說過的話？

跟 AI 聊久了，它就忘記你開頭交代的事；開新對話更是整個忘光。背後的原因是它根本沒有記憶——每次回你都是把整段對話重讀一遍。用一個失憶但讀很快的人的畫面，聊聊 context window 是什麼，還有它跟 ChatGPT 那個「記憶」功能差在哪。

AI Systems

Token 是什麼？LLM 為何只讀 Token？

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。

All posts (47)

Support My Work

Buy Me a Coffee