By Judith van Stegeren
A conference report of day 3 of AI Engineer Europe 2026 in London. Mario Zechner's plea to slow down, talks on agentic trace analysis and BullshitBench, and an interview with Tuomas Artman on quality engineering.
By Judith van Stegeren
A conference report of day 2 of AI Engineer Europe 2026 in London. Keynotes on agentic engineering and DeepMind research, talks on eval platforms and finetuning small models, and a fireside chat with Gergely Orosz.
By Judith van Stegeren
A conference report of day 1 of AI Engineer Europe 2026 in London. Hallway Track conversations about coding agent tooling, workshops on agentic feedback loops, demand-driven context, and a Claude Code meetup focused on production robustness.
By Alexander de Ranitz
By Alexander de Ranitz
By Alexander de Ranitz
By Alexander de Ranitz
By Alexander de Ranitz
By Judith van Stegeren
By Alexander de Ranitz
By Alexander de Ranitz
By Alexander de Ranitz
By Alexander de Ranitz
By Alexander de Ranitz
By Alexander de Ranitz
By Yorick van Pelt
By Judith van Stegeren
This is a write-up of my experiments with Claude, Anthropic's large language model. Claude has a huge context size compared to GPT-4, while also being cheaper. I find that Claude is an interesting alternative to OpenAI's GPT, especially for non-fiction use cases.
By Judith van Stegeren
By Yorick van Pelt
New models are coming out every day. Here's an overview that can aid in selecting one for commercial use.
By Judith van Stegeren
In Good Strategy/Bad Strategy, Richard Rumelt explores how we can take advantage of significant shifts in society to gain an edge over competitors. This works well, even for really small companies. Rumelt provides thinking points for analyzing these changes in his book. How can we apply Rumelt's ideas to generative AI?
By Yorick van Pelt
By Judith van Stegeren
By Judith van Stegeren
Subscribe to our newsletter to get our writing delivered straight to your inbox.