Always in the middle of something.

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.

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。其實它不是「忘記」，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。

網路上常說：要 AI 每次給一樣的答案，把 temperature 設成 0 就好。但有人拿同一個 prompt、temperature 0 連跑 1000 次，還是冒出 80 種不同輸出。原因不是浮點誤差這麼簡單，而是它在 GPU 上跟多少別的請求湊成一批一起算。聊聊為什麼『最確定』不等於『可重現』。

Ask an AI the same thing three times and you often get three different answers. It isn't being flaky — it never picks the single most-likely word, it draws one by probability. Here's the dial behind it, why even temperature 0 isn't fully repeatable, and why 'varies' isn't the same as 'making things up'.

同一個問題問 AI 三次，常常拿到三個不一樣的答案。不是它在亂講——它本來就不是每次都挑機率最高的那個字，而是照機率抽一個。用一個加權抽籤的畫面，聊聊它為什麼會飄，還有飄跟唬爛其實是兩回事。

An AI's 'done' sounds the same whether the work happened or not. The fix is one small habit: don't take its word for it, ask it to show you a result you can check yourself, sized to the task.

AI 回報「完成了」的時候，真的做完、做一半繞過去、方向整個誤會，那段話讀起來幾乎一樣。與其判斷那句話可不可信，不如養成一個反射：給我看一個我自己查得到的東西，commit、測試輸出、diff。

Anthropic released Claude Fable 5 on June 9 — the first publicly available Mythos-class model, one tier above Opus. What it is, what it costs, the June 22 deadline on the subscription window, and what changed when I pointed three real projects at it for a day.

Anthropic 6/9 釋出第一個公開的 Mythos 級模型 Claude Fable 5。這篇整理它跟 Opus 4.8 的關係、定價、6/22 截止的訂閱免費期，加上第一天把三個專案丟給它跑的心得：它對治理流程的遵守程度是真的，token 也是真的兇。

流程裡那些閘門其實不在執行時擋住 AI agent,它要的是一張改不掉的收據。真正有牙齒的不是閘門,是記錄抹不掉、賴不掉。