Electrons In, Tokens Out AI is a five-layer cake. Nvidia sits in the middle. Long weekend drive, sunny weather, and nearly two hours of Jensen Huang arguing with Dwarkesh Patel about whether Nvidia&rs…
2026
Nvidia's Real Moat: What Jensen Huang Told Dwarkesh Patel
Self-Improving Models: What MiniMax M2.7 Actually Does
The Headline vs The Reality Self-evolution: the model improves the process that improves the model. “Model trains itself over 100+ autonomous cycles.” That was the headline when MiniMax re…
The Citation Crisis: What AI Hallucinations Mean for Your Enterprise
The Reference I Almost Didn’t Check A few days ago, I was reviewing an article my AI agent had drafted. The sources section looked clean: numbered references, proper formatting, plausible titles…
Fischbrötchen and Failure Rates — I'm Speaking at AWS Summit Hamburg
Fischbrötchen and Failure Rates Hamburg won me over. Last year, the AWS Summit left Berlin for Hamburg. After years of presenting at the Berlin Summit, I wasn’t sure how I’d feel about the…
From Cloud-Native to AI-Native: What Actually Changes
The Fifteen-Year Echo Fifteen years apart. Same stage. Different world. In 2010, Adrian Cockcroft stood on the QCon stage and told the audience that Netflix was running its entire business on a public…
The Protocol We Should Have Built for Humans
Namaste from 6,165 Meters I just summited Imja Tse (Island Peak, 6,165 meters) in Nepal. No Slack, no email, no MCP servers crashing in the background. Just ice, thin air, and the kind of clarity that…
Building Agents That Read the Web Right
The Other Side of the Coin In a recent article, I made my website AI-agent friendly [1], adding llms.txt, Markdown output, and content negotiation to a Hugo site on AWS. That article was about the pro…
Is RAG Still Needed with 1M+ Token Context Windows?
The Kofferklausur, Revisited In September 2024, a colleague asked an audience: “What is RAG?” I answered: Kofferklausur [1]. For non-German speakers: a Kofferklausur is an open-book exam. …
LLMs Don't Do Math — They Predict What Math Looks Like
The Invisible Error To test this, I designed five calculations that anyone in business might ask an AI assistant — the kind of questions you’d type into ChatGPT or Claude expecting a quick, reli…
Security Is Job Zero — Even (Especially) in the Age of Coding Agents
$20 and Two Hours On February 28, 2026, security startup CodeWall gave an autonomous AI agent a single input: a domain name. Two hours and approximately $20 in API tokens later, the agent had full rea…