←Applied AI Engineering
Chapter 4 of 23 · Level 1 · Foundations: How LLMs Work

Reasoning and Test-Time Compute

Thinking tokens, buying accuracy at inference, and deciding per task when the latency and the bill are worth it.

  1. 4.1

    Reasoning and Test-Time Compute

    A reasoning model buys accuracy with time. It generates thinking tokens before answering, which you pay for and rarely see. Knowing when that trade is worth it, and when it is waste, is now a routine engineering decision.

    6 min read
    →