AI insights for anyone who wants to understand the opportunities, follow developments and make better decisions.
March 17, 2026 · Joel Thyberg
We tested 26 language models on 100 questions and measured not only whether they were right, but how confident they claimed to be. The results reveal a dangerous zone where even top models make mistakes with full conviction.
We tested 33 language models with 10 estimation questions and four authority levels. The results show that almost all models are pulled toward the numbers they are given, and that the authority behind those numbers has a dramatic effect.
March 16, 2026 · Joel Thyberg
We tested 29 language models on 60 prompts in a recursive review loop. The results show that many models suffer from perfectionism and get stuck in unnecessary changes, especially under pressure.
A technical guide to RAG, from parsing and chunking to embeddings, vector databases, retrieval, and modern variants like Graph RAG and Agentic RAG.
March 15, 2026 · Joel Thyberg
A technical guide to AI agents. Understand how agents use language models, tools, memory, and goals to solve tasks dynamically, and how they differ from workflows and traditional automation.
A practical guide to AI automation and workflows. Learn what AI automation means, how it differs from traditional automation and AI agents, when workflows are the right choice, and which patterns are most useful in practice.