Martin
.
Blog
Neurons
Playground
Podcast
About
Contact
Meet Martin
DE
/
EN
Newsletter
← All articles
Net
Timeline
Reset
AI · Opinion: Can an AI really escape and make itself better?
From the workshop: Test data without data: how to compare production against test without anyone seeing the customer data
Software · Agents: Code is getting cheap. Knowledge isn’t.
Agents: “We want an AI agent”. The wrong requirement
Customers: Invited, showed a way to a solution, never heard back. And why I am putting the approach here anyway.
Projects: Our first model, 2020: object recognition in the living room. And why Xcode 2026 hangs on it.
Behind the scenes: From whiteboard to production system
Other: A weekend without a phone
Personal: From the terminal to the reception. Talking to non-IT people is on us, not on them.
Location: Zurich checks, Dubai delivers: How we combine GPUs, speed and Swiss quality
AI Driven Development: Innovation workshop: The three questions that immediately weed out 80 percent of AI ideas
Projects: NewTechForge: From idea to production, and why those are two different jobs
AI Driven Development: Vibe coding in the enterprise needs a security concept. This is what ours looks like.
AI Driven Development: From 20 developers to 5: How to rebuild a team without losing it
AI Driven Development: The first conversation with a CTO who wants to "just introduce AI"
AI Driven Development: I don't just build AI. I take teams to the place where they can work with it.
AI Driven Development: The architect is not dying out. He is becoming more important than ever.
AI · Opinion: Nvidia is almost giving GPUs away. And why that won't last
Personal: Built instead of posted: why I am writing after all
Agents: Contract first: why our backend and frontend agents aren't allowed to look at each other's code
Agents: An agent must never sign off its own work. The one rule that saved NeoCoder
From the workshop: Keeping 50 micro-models alive: why automation isn't optional, it's mandatory
AI · Opinion: Factor 400,000: why anyone who only pays for tokens doesn't know the price of AI
From the workshop: 900 categories, 50,000 examples, 40 training runs: what a "small" model really costs
AI · Opinion: In the beginning the models lied. And I believed them.
Projects: YOW: one year, three people, one catapult. And every angle, every weight really computed.
Projects: Dunk Museum for Titolo: a storyboard, Unity in the browser, and a budget nobody understood
From the workshop: 80 MB for Apple: What shrinking a model taught me about AI
Projects: Scan Your World: the attempt after. LiDAR, our own tracking, and a why I cannot fully piece together anymore.
Projects: SKIMO: the fridge that knew what was inside. And where we went from a small model to a bigger one.