Always in the middle of something.

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. METR says none of the launch benchmark numbers are a reliable measure of what the model can do.

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。至於它到底多強，獨立評測機構 METR 說現有的數字都不算可靠量測。

Agentjacking is an attack disclosed in June 2026: an attacker plants a fake error report, your AI coding agent reads it as instructions, and runs their code with your credentials. The nasty part is that telling the agent to ignore untrusted input doesn't stop it, and your security tools see nothing wrong.

Agentjacking 是 2026 年 6 月揭露的攻擊：攻擊者塞一封假的錯誤報告，你的 AI coding agent 把它讀成指令、用你的權限跑了攻擊者的 code。最麻煩的是，你在系統提示裡叫 agent 別理它也擋不住，資安監控也完全看不出異常。

打「貓」「小貓」「喵星人」，AI 怎麼知道講的是同一種東西？答案是 embedding：把文字變成座標，再用夾角量意思相不相近。這篇拆開它怎麼運作，順便聊聊「king − man + woman = queen」那個經典其實灌了點水。

Search for 'make my laptop quieter' and get a page about 'reducing fan noise' with zero words in common. That's embeddings: text turned into coordinates, with meaning measured as the angle between two points. Here's how the trick works, and where it's oversold.

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.