Skip to content
FRITS AI
Research About Contact GDPRchat

Publications

Research

Technical reports from FRITS AI. We document what we discover building and operating European AI systems in production — methods, failures and measurements included. Reports are self-published, numbered and citable; they are not peer-reviewed. Subscribe via RSS.

  • FRITS-TR-2026-04 5 July 2026 energyefficiencyroutingsustainabilityEU policy

    The Cruise Missile and the Lasagne: How to Make AI Chatbots Greener by Right-Sizing the Model to the Question

    Most questions people ask AI chatbots are easy — a lasagne recipe, an email draft, a word explained. Yet the industry default is to answer every question with the largest model available, the way one might sink a dinghy with a cruise missile. This report…

    Frits Lyneborg

    Read the report →
  • FRITS-TR-2026-03 5 July 2026 tool useroutingMistralproduction LLM systems

    Every Turn Ends in a Tool Call: Reliable Tool Use for Mid-Size Open Models via Two-Stage Forced Routing

    Production assistants want many tools; mid-size open models want few. Operating a Mistral-based assistant with more than twenty tools, we catalogued what actually goes wrong as tool count grows: the model answers from its priors in prose before deciding to…

    Frits Lyneborg

    Read the report →
  • FRITS-TR-2026-02 5 July 2026 translationmultilinguallocalisationLLM

    Re-Authoring, Not Translating: A Two-Stage Meaning-First Pipeline for Native-Quality Machine Translation

    Machine translation — including translation by strong LLMs — produces output that is technically correct and unmistakably foreign: calqued phrases no native speaker would write, invented compound words, English sentence structure wearing local vocabulary.…

    Frits Lyneborg

    Read the report →
  • FRITS-TR-2026-01 5 July 2026 model governancebiasevaluationmultilingual

    Language-Dependent Political Bias in Large Language Models: Detection and Neutralisation in a Multi-Provider Production System

    While calibrating an evaluation gate for admitting new language models into a production assistant, we found that a model can give measurably different answers to the same politically sensitive question depending on the language it is asked in — drifting…

    Frits Lyneborg

    Read the report →

FRITS AI ApS

  • Nyhavn 38, 1051 København K, Denmark
  • CVR (DK): 45733785
  • Contact form

Site

  • Research
  • About
  • Contact
  • RSS feed

Elsewhere

  • GDPRchat — our assistant
  • LinkedIn

© 2026 FRITS AI ApS. We build AI that runs entirely in Europe — and publish what we learn.