Seventeen 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 & TechnologyTextos
Reflexões sobre design, desenvolvimento, infraestrutura de IA e criação de produtos.
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 & 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 & 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 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 & 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 & 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 & 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 & 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 & 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 & TechnologyPublicações Externas
Redação técnica em Introl
Local LLM Hardware Pricing Guide 2025
Recomendações abrangentes de hardware e análise de custos para executar modelos de linguagem grandes localmente.
H100 vs. H200 vs. B200: Choosing the Right NVIDIA GPUs for Your AI Workload
Guia de seleção de GPU comparando os mais recentes aceleradores de datacenter da NVIDIA para diferentes cargas de trabalho de IA.
TPU Architecture: Complete Guide to Google's 7 Generations
Análise técnica aprofundada da evolução da Unidade de Processamento Tensor do Google, do TPUv1 ao TPUv5.
GPU Memory Pooling in Multi-Tenant Kubernetes
Estratégias de compartilhamento de recursos para clusters de GPU em ambientes containerizados.
Ray Clusters: Distributed AI Computing Infrastructure
Guia para construir e gerenciar computação de IA distribuída com o framework Ray.
DeepSeek V3 Open Source AI Cost Advantage
Análise da economia de LLMs de código aberto e do posicionamento competitivo da DeepSeek.
NVIDIA Vera Rubin GPU 600kW Racks 2027
Requisitos futuros de energia para datacenters e o roteiro de GPUs de próxima geração da NVIDIA.
SMR Nuclear Power for AI Data Centers
Soluções de reatores modulares pequenos para alimentar a infraestrutura de IA de próxima geração.
DeepSeek MHC Architecture Breakthrough
Análise técnica das inovações da arquitetura Multi-Head Compression da DeepSeek.