The Headline vs The Reality โModel trains itself over 100+ autonomous cycles.โ That was the headline when MiniMax released M2.7 on March 18, 2026 [1]. It sounds like science fiction: a model bootstrapโฆ
2026
Self-Improving Models: What MiniMax M2.7 Actually Does
The Citation Crisis: What AI Hallucinations Mean for Your Enterprise
The Reference I Almost Didnโt 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. One โฆ
Fischbrรถtchen and Failure Rates โ I'm Speaking at AWS Summit Hamburg
Fischbrรถtchen and Failure Rates Last year, the AWS Summit left Berlin for Hamburg. After years of presenting at the Berlin Summit, I wasnโt sure how Iโd feel about the move. Then I opened the Generatiโฆ
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 publicโฆ
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 thatโฆ
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 proโฆ
Is RAG Still Needed with 1M+ Token Context Windows?
The Kofferklausur, Revisited In September 2024, a colleague asked an audience: โWhat is RAG?โ I answered: Kofferklausur [1]. For non-German speakers: a Kofferklausur is an open-book exam. You bring yoโฆ
LLMs Don't Do Math โ 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 youโd type into ChatGPT or Claude expecting a quick, reliable anโฆ
Security Is Job Zero โ 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 reaโฆ
AI Coding Productivity: 10%, Not 10x
The Number Nobody Wants to Hear A few weeks ago, I wrote about running my entire workday through an AI agent [1], meetings, research, CRM, content creation. Eight hours of productive work, not a singlโฆ