Home » Tags

Governance

AI Systems

Why AI Agents Fail in Production

Why AI agents fail: most failures trace to governance gaps (phase gates, state handoffs, capability boundaries) more than to the model itself, and the two need completely different fixes. How to tell them apart.

Governance

See all 26
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

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.

Agent

See all 20
AI Systems

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.

AI Systems

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。

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。

Agentic OS

See all 12
AI Systems

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.

AI Systems

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。

Claude Code

See all 11
AI Systems

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.

AI Systems

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。

LLM

See all 9
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。

Architecture

See all 7
AI Systems

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.

AI Systems

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。

AI Systems偏技術，給工程的Read in English

MCP 資安危機：問題出在治理

MCP（Model Context Protocol）一年內成為 AI 業界標準，2026 年卻接連爆出 RCE、tool poisoning、rug pull 等資安漏洞。本文整理多方專家觀點，並提出我的看法：真正要補的是治理這一層。

AI Systems看中文版

MCP Security Is a Governance Problem

MCP became the industry's default agent-to-tool interface in barely a year, then 2026 brought a wave of RCE, tool poisoning, and rug-pull disclosures. Weighing the expert debate, my take: the real exposure is a governance gap that better protocol design alone won't close.

Token Economics

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。

Dev Tools

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。

All posts (26)

Support My Work

Buy Me a Coffee