Harder study works better — not because difficulty is inherently virtuous but because the specific kinds of difficulty associated with retrieval and interleaving trigger deeper encoding than the easier alternatives. This has direct implications for how to design AI study sessions. This concept covers the research rationale and the practical translation into study session design.
Desirable difficulty refers to study conditions that feel harder in the moment but produce stronger long-term learning — such as varying practice contexts, delaying feedback, or reducing hints — because the extra cognitive effort deepens memory encoding. Coined by psychologist Robert Bjork, it explains why easy, fluent studying often creates an illusion of learning without real retention.
Understanding desirable difficulty helps learners stop mistaking comfort for progress — and AI can be configured to deliberately introduce productive friction into study sessions rather than simply making things easier.
When using ChatGPT to study, add this instruction to your prompt: 'Do not give me the answer immediately. First ask me to attempt it, then give me one small hint only if I ask, and delay full explanations until I've struggled for at least two responses. Track where I needed hints.' This systematically applies desirable difficulty to any subject.
Peri can explain this concept, give practical examples, help you decide whether it applies to your situation, or recommend a journey if appropriate.
Explore related journeys or tell Peri what you're working through.