← All lessons
0130

Reasoning

A model often fails not because it cannot solve a problem, but because it commits to the first token of an answer too quickly. Reasoning models are trained to work through steps before answering.

Instead of jumping straight to a conclusion, the model generates a chain of intermediate steps, each token conditioned on the ones before. Spending more tokens on this hidden working is test-time compute: the same model gets more accurate on hard problems simply by thinking longer. The trade is latency for reliability.

A bat and ball cost $1.10. The bat costs $1 more than the ball. How much is the ball?

fast: $0.10 ✗
more steps = more compute

Check yourself

The fast and slow paths use the same weights. Why does forcing intermediate steps change the final answer?

Go deeper (free): Lilian Weng — Why we think (test-time compute)

Next: Agents