Why write out the work instead of answering right away? — Thinking before answering
Once it wrote out its work instead of answering right away, it started getting right what it used to get wrong.
1 · Think first
The secret to AI suddenly getting good at hard problems wasn't getting bigger — it was making it go through the steps before answering.
At first, it worked when a person told it 'think step by step,' but later came models trained to write out their work on their own first. These are called reasoning models.
But there's a price. The longer it thinks, the slower the answer and the more text it writes. So for easy questions, it doesn't bother.
2 · Experiment · Put it in order
Try it — Put the steps of the work in order
Tap the mixed-up pieces in the order you think is right. When you've picked them all, it'll grade you. The point is to feel for yourself that the answer only comes out right if the order is right.
Tap the pieces below in the order you think is right.
Figure
Answering right away vs. thinking first
Same model family, but just changing the order it answers in changes the results.
3 · Quiz
Quick check
Three questions. Pick an answer and it's marked right away, with the reason why.
Today in one line
Today in one line
Once it wrote out its work instead of answering right away,
it started getting right what it used to get wrong.
Learn more
- A 2022 paper showing that just adding one line — 'Let's think step by step' — makes math accuracy jump a lot — Large Language Models are Zero-Shot Reasoners (2022)
- The official 2024 intro to a model that works through the steps without being told — the 12% and 74% numbers come from here — Learning to Reason with LLMs (OpenAI, 2024)