Home

Published

- 2 min read

Check My Understanding

AI Learning Education LLM Productivity Self-Improvement Teaching
img of Check My Understanding

Check My Understanding

We often fall into the trap of passive learning - consuming content without truly understanding it. Drawing from David Deutsch’s insight in “The Beginning of Infinity” that knowledge creation comes from developing explanations1, I’ve been utilising a powerful learning pattern using Large Language Models (LLMs) that vastly improves the speed at which we can validate and improve our understanding in real-time.

The Power of Instant Feedback

Think about traditional learning: you might spend hours developing your understanding of a concept, only to discover your mental model was flawed when you finally get feedback from a teacher or peer. With LLMs, we now have an unprecedented ability to check our understanding immediately, at any time.

It’s like having a world-class tutor available 24/7 who can instantly analyse your explanations, point out logical flaws, identify gaps, and suggest improvements. This rapid feedback loop accelerates learning by orders of magnitude.

The Pattern

  1. When learning something new, force yourself to write out your current understanding. Even if your current understanding is limited. Force yourself to communicate whatever you can to the LLM.
  2. Start your prompt with “Check my understanding…”
  3. Get immediate, detailed feedback on the quality of your explanation
  4. Refine your understanding based on the feedback
  5. Repeat until your explanation is solid

The key is that you’re not asking the LLM to explain things to you - you’re having it critique your own explanations. This transforms the LLM from an answer machine into a collaborative tutor that helps you think better.

The real-time feedback makes all the difference. You can rapidly iterate on your explanations until they’re robust. And you get specific, targeted feedback that’s uniquely based on your understanding (or lack thereof).

Most people I meet seem to jump at LLM’s for pure generation of emails, documents etc. I think the general public so far are completely underutilising LLM’s as learning tools. Research has shown that actively engaging in creating explanations is key to effective learning and problem-solving2.

To be honest I don’t know what I’d do without being able to utilise this pattern now. Having to search out feedback from external sources to validate my understanding of any given topic feels excruciatingly slow.

Footnotes

  1. Deutsch, D. (2012). The Beginning of Infinity: Explanations That Transform the World. Penguin Books. Link ↩

  2. Chi, M. T., Bassok, M., Lewis, M. W., Reimann, P., & Glaser, R. (1989). Self-explanations: How students study and use examples in learning to solve problems. Cognitive science, 13(2), 145-182. Link ↩