Tip2025-10-28#prompting

Make it think before it answers

Autoregressive models can only condition on what they have already written. If the answer comes first, the explanation is generated to fit a token that is already locked in. It is rationalization, not reasoning.

Flip the order and the reasoning tokens become real scratch space the final answer can lean on. This is the entire mechanism behind chain-of-thought, and it is why 'answer, then explain' quietly underperforms.

Aha moment

Explanation after an answer often explains a commitment; reasoning before an answer can still change it.

Try this

Put scratch work, constraints, and uncertainty checks before the final answer field.

Open NotesEntry JSON

Watch for

  • Post-hoc explanations that never revise the answer
  • A final answer that appears before evidence is considered
  • Reasoning sections that only paraphrase the conclusion