Stage 2 of 9 · 6 lessons · ~2 weeks
Reasoning quality: when a bigger model pays off
Some tasks need a model that thinks before it answers, and some only need a quick, obedient one. Learn what reasoning models and effort settings do, why multi-step tasks punish small mistakes, and how to tell when the price of a bigger model is cheaper than the price of a wrong answer.
Start: Reasoning models and fast modelsLessons· one lesson for each topic, in this order
Start with· follow one of these
- CoursePaidGrokking Prompt Engineering for Software Engineers
Design Gurus · Beginner · Subscription
Write prompts with clear rules and formats, so you can test instruction following properly
- VideoFreeDeep Dive into Large Language Models like ChatGPT
Andrej Karpathy · Intermediate
Free: a clear explanation of how reasoning models are trained and why thinking helps
Practise
Keep handy
Also worth your time
How reasoning effort works in practice and where the reasoning tokens show up in usage
- Large Language Model CourseGo deeper
Free: go deeper into how models are trained, which explains where reasoning comes from
Before moving on: Take the hardest five examples from your feature and run them on a fast model and on a reasoning model at two effort levels. Record correctness, tokens and time for each, then write one paragraph on whether the extra reasoning pays for itself using price plus the cost of errors.
Do not reach for the biggest model by default, and do not refuse it on price alone. Count the steps, price a wrong answer, and test effort levels before switching models. Many teams find that the same model at a different effort level solves the problem.