"Ask any instructor what helps students learn, and it's unlikely any of them will answer "a really big wall of text". It's incredible to me, as both a university instructor and a UX designer, that the army of people working at OpenAI are not imagining better tools for our students. I want to walk you through a design pattern in ChatGPT that, despite its good intentions, might be creating unintended hurdles for students."
"I'm talking about "verbosity compensation", which is an LLM's tendency to provide overly wordy answer. We've all seen it. You ask for help, and the AI provides a dense, multi-part response, that sounds like high-quality until you look closer. The challenge for learning specifically, is that managing the learner's cognitive load is critical, and presenting information this way can be overwhelming. It's a bit like asking how to boil an egg and getting the entire science of how water boils, the protein structure of an egg, and two egg salad recipes in response."
AI chat interfaces can produce overly verbose, dense, and multi-part answers that raise learners' cognitive load and impede comprehension. Verbosity compensation leads models to pack facts, clarifying questions, structure suggestions, and scaffolding into a single heavy reply, often exceeding the specificity a novice prompt provides. Students frequently submit vague prompts, so interfaces should anticipate non-expert needs rather than overwhelming them. Applying cognitive science and UX design practices like chunking, progressive disclosure, and minimal clarifying questions can reduce extraneous load and create more effective study-support tools.
Read at Medium
Unable to calculate read time
Collection
[
|
...
]