MEPX
Chapter 9 of 12All chapters
  1. 1What AI means
  2. 2How machine learning works
  3. 3Training data
  4. 4Kinds of learning
  5. 5Neural networks
  6. 6Large language models
  7. 7Limits and hallucination
  8. 8Bias and fairness
  9. 9Using AI well
  10. 10Privacy and safety
  11. 11Beyond text
  12. 12AI and work

Chapter 9 of 12

Using AI well

Getting value without getting caught out.

Where it is strong

Drafting, summarising, explaining, translating, rewriting and generating options are all tasks where being roughly right quickly is genuinely useful and the cost of an error is low.

  • Give context and examples. Vague questions get vague answers.
  • Ask for the reasoning when the reasoning is what you need to check.

Where to verify

Anything factual, legal, medical, financial or numerical needs checking against a real source. Treat output as a first draft from a fast, well read colleague who sometimes invents things.