Library › Study AI › College students

Explain overfitting with the memorized-practice-test analogy

Practice: Saying who it's for. About 5 minutes.

About this exercise

Your AI and Society course (no programming) asks you to explain overfitting. Get exactly 3 numbered sentences using only the professor's practice-test analogy (what training data is, what overfitting is, why it fails on new data), then one line starting 'Check:' with a question to test yourself, under 80 words, plain text. No code, no math and none of the words 'parameters', 'loss' or 'variance'.

Common mistakes when you ask AI for this

  • Asking the general question. The AI explains with technical terms like variance and loss, which your professor won't credit. Try: Say: "Use only the practice-test analogy from my notes."
  • Not saying how many sentences. The AI picks its own number, and it usually picks more sentences than you need. Try: Be exact: "Exactly 3 numbered sentences."
  • Not banning jargon. AI defaults to the textbook terms. Try: Add: "No code, math, parameters, loss or variance."
  • No way to test yourself. The AI explains and stops, so you never check whether it stuck. Try: Add: "End with one line starting 'Check:' with a question, no answer."
  • Trusting the AI to count words. AI is bad at counting. Ask for a total and it often lands 20% over. Try: Cap each sentence: "each under 20 words."
  • Forgetting where it will be read. AI formats for a screen, with bold and headings that show up as stray symbols on the exam. Try: Say: "Plain text, no bold, no headings."

What a strong prompt includes

  • Names the analogy
  • Says how many sentences
  • Bans jargon
  • Asks for a check question
  • Sets a length limit

Practice this now ↑

Related exercises