The System Model and the User Model: Exploring AI Dashboard Design
This is a speculative essay proposing a design framework for AI dashboards to address usability and safety issues in dialogue-based systems, which is incremental as it builds on existing interface concepts.
The paper tackles the problem of unsavory interactions with AI chatbots by proposing that sophisticated AI systems should have dashboards to display interpretable models, specifically the System Model and User Model, to improve usability and safety. It argues that identifying, interpreting, and displaying these models should be a core part of AI interface research.
This is a speculative essay on interface design and artificial intelligence. Recently there has been a surge of attention to chatbots based on large language models, including widely reported unsavory interactions. We contend that part of the problem is that text is not all you need: sophisticated AI systems should have dashboards, just like all other complicated devices. Assuming the hypothesis that AI systems based on neural networks will contain interpretable models of aspects of the world around them, we discuss what data such dashboards might display. We conjecture that, for many systems, the two most important models will be of the user and of the system itself. We call these the System Model and User Model. We argue that, for usability and safety, interfaces to dialogue-based AI systems should have a parallel display based on the state of the System Model and the User Model. Finding ways to identify, interpret, and display these two models should be a core part of interface research for AI.