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 & TechnologyPisanie
Przemyślenia o projektowaniu, rozwoju, infrastrukturze AI i budowaniu produktów.
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 & TechnologyPublikacje zewnętrzne
Pisanie techniczne w Introl
Local LLM Hardware Pricing Guide 2025
Kompleksowe rekomendacje sprzętowe i analiza kosztów uruchamiania dużych modeli językowych lokalnie.
H100 vs. H200 vs. B200: Choosing the Right NVIDIA GPUs for Your AI Workload
Przewodnik wyboru GPU porównujący najnowsze akceleratory NVIDIA dla centrów danych do różnych zastosowań AI.
TPU Architecture: Complete Guide to Google's 7 Generations
Szczegółowa analiza techniczna ewolucji Tensor Processing Unit firmy Google od TPUv1 do TPUv5.
GPU Memory Pooling in Multi-Tenant Kubernetes
Strategie współdzielenia zasobów dla klastrów GPU w środowiskach kontenerowych.
Ray Clusters: Distributed AI Computing Infrastructure
Przewodnik po budowaniu i zarządzaniu rozproszonym przetwarzaniem AI z frameworkiem Ray.
DeepSeek V3 Open Source AI Cost Advantage
Analiza ekonomii open source LLM i pozycji konkurencyjnej DeepSeek.
NVIDIA Vera Rubin GPU 600kW Racks 2027
Przyszłe wymagania energetyczne centrów danych i plan rozwoju GPU nowej generacji NVIDIA.
SMR Nuclear Power for AI Data Centers
Rozwiązania małych reaktorów modułowych do zasilania infrastruktury AI nowej generacji.
DeepSeek MHC Architecture Breakthrough
Analiza techniczna innowacji architektury Multi-Head Compression firmy DeepSeek.