The Fork Bomb Saved Us
The LiteLLM attacker made one implementation mistake. That mistake was the only reason 47,000 installs got caught in 46 minutes.
AI & Technology寫作
關於設計、開發、AI基礎設施和產品構建的思考。
The Agent Didn't Get Smarter
The model is the same between session 1 and session 500. The project changed. This reframes the entire AI productivity conversation.
AI & TechnologyOvernight
Between midnight and 6am, Googlebot crawls 21,000 pages, Bingbot crawls 10,000, and the comprehensive check grinds through 15,000. The site is more active at 3am than at 3pm.
AI & TechnologyThe Evidence Gate
I believe and it should are not evidence. Every completion report needs a file path, test output, or specific code. The discipline of proof in an age of plausible AI output.
AI & TechnologySeventeen Thousand Signals
My vault has 17,900 signals from arXiv, Semantic Scholar, HN, NVD, and 9 other sources. Most are noise. The noise taught me what signal looks like.
AI & TechnologyWhat I Run Before I Sleep
Every night: 15,000 pages checked, TTFB measured, cache verified, sitemaps crawled. The goodnight routine is where operational discipline lives.
AI & TechnologyThe Handoff Document
A diagnosis that survived three code review corrections, two priority reorderings, and guided the correct implementation four days later. The most underrated artifact in agent-assisted development.
AI & TechnologyQuality Is the Only Variable
Time, cost, resources, and effort are not constraints. The question is what's right, not what's efficient. A philosophy for building with AI agents.
AI & TechnologyTaste Is Infrastructure
As agents generate more of what ships, the quality ceiling is set by how well you encode aesthetic judgment into systems. Taste scales when it becomes queryable.
AI & TechnologyWhen Your Agent Becomes the Researcher
Claude Code discovered adversarial attacks that outperform 30+ existing methods. Autoresearch just crossed from experiment to capability.
AI & TechnologyCompound Context: Why AI Projects Get Better the Longer You Stay With Them
Every problem you solve with an AI agent deposits context that the next session withdraws with interest. This is context compounding.
AI & TechnologyThe Supply Chain Is the Attack Surface
Trivy got compromised. Then LiteLLM. Then 47,000 installs in 46 minutes. The AI supply chain worked exactly as designed.
AI & Technology外部出版物
技術寫作： Introl
Local LLM Hardware Pricing Guide 2025
本地運行大型語言模型的全面硬體建議和成本分析。
H100 vs. H200 vs. B200: Choosing the Right NVIDIA GPUs for Your AI Workload
針對不同AI工作負載比較NVIDIA最新資料中心加速器的GPU選擇指南。
TPU Architecture: Complete Guide to Google's 7 Generations
深入技術分析Google張量處理單元從TPUv1到TPUv5的演進。
GPU Memory Pooling in Multi-Tenant Kubernetes
容器化環境中GPU叢集的資源共享策略。
Ray Clusters: Distributed AI Computing Infrastructure
使用Ray框架構建和管理分散式AI運算的指南。
DeepSeek V3 Open Source AI Cost Advantage
開源LLM經濟學分析和DeepSeek的競爭定位。
NVIDIA Vera Rubin GPU 600kW Racks 2027
未來資料中心電力需求和NVIDIA下一代GPU路線圖。
SMR Nuclear Power for AI Data Centers
為下一代AI基礎設施供電的小型模組化反應爐解決方案。
DeepSeek MHC Architecture Breakthrough
DeepSeek多頭壓縮架構創新的技術分析。