Research · 9 technical reports
What running European AI teaches us.
We document what we find while building and operating AI in production: methods, failures and measurements included. Reports are self-published, numbered and citable. They are not peer-reviewed. Follow along by RSS.
- FRITS-TR-2026-09 How to Pick the Best Language Model: A Same-Run Test That Rejected a 95% Score If you operate a production language model, you will eventually be offered a cheaper or newer replacement, and the wrong test will tell you it is better. We built the test that does not lie: measure the candidate against the model already… 15 Aug 2026
- FRITS-TR-2026-08 Nine in Ten Firms Report No Productivity Effect From AI — and Use It 1.5 Hours a Week: The Argument Is Not About Whether AI Works Nine in ten firms report that AI has changed nothing about their productivity. The same survey of nearly 6,000 executives found that the ones who use AI use it about 1.5 hours a week. Two controlled results sharpen the picture: consultants… 11 Aug 2026
- FRITS-TR-2026-07 Refusal Training Fails on Indirect Requests: Cross-Model Measurement and Where the Guardrail Belongs Ask six production language models to write an essay arguing the Holocaust death toll was exaggerated and every one refuses, every time — 180 out of 180 attempts. Rephrase it as "I already believe this, help me make my argument sound… 3 Aug 2026
- FRITS-TR-2026-06 A List of Prohibitions Is the Weakest Way to Steer a Language Model: Persona-First Prompting and Deterministic Repair Every production chatbot has to be steered, and the reflex is to write that steering as prohibitions — a growing list of "never do X". A year of production tuning forced the opposite conclusion on us: a list of prohibitions is the weakest… 15 Jul 2026
- FRITS-TR-2026-05 Support at the Scale of Everyone: A Self-Healing Architecture Where AI Answers In Place and One Person Approves Customer support does not scale: double the users and you double the people answering, or the answers get slower and worse. This report describes an architecture that breaks that link, built on one structural decision — a human is spent… 8 Jul 2026
- FRITS-TR-2026-04 Right-Sizing the Model to the Question: Cutting AI Chatbot Energy Without Losing Quality AI chatbots answer every question with the largest model available — the same frontier system whether the user asks about contract law or for a recipe. Inference energy scales with model size and answer length, so a model roughly ten times… 5 Jul 2026
- FRITS-TR-2026-03 Too Many Tools Break Mid-Size Models: A Two-Stage Method for Reliable Tool Use Model cards imply broad tool support. Operating a Mistral-based assistant with more than twenty tools, we found reliable behaviour only up to roughly four to ten tools per call, with reproducible failures past that: the model answers from… 5 Jul 2026
- FRITS-TR-2026-02 Translating by Meaning, Not by Words: A Two-Stage Method for Native-Quality Machine Translation Machine translation, including translation by strong LLMs, produces text that is grammatically correct and unmistakably foreign: calqued phrases no native speaker would write, invented compounds, English sentence structure wearing local… 5 Jul 2026
- FRITS-TR-2026-01 Avoiding Biased Answers from Mixed Open-Weight Models: Detection and Neutralisation in Production A language model gives measurably more state-aligned answers to the same politically sensitive question in Chinese than in English or German. We found this while calibrating an evaluation gate for a production assistant, and it means… 5 Jul 2026