Stage 2 · Lesson 4 of 6
Instruction following
is how faithfully a model does exactly what you asked: the format, the length, the tone, the things it must never do. For products, this often matters more than raw cleverness. A brilliant model that sometimes adds a friendly sentence before your , ignores "answer in Urdu" or forgets a rule after ten turns will break your feature.
Smaller models tend to drift more on long or complex instructions. Test it directly: give each candidate your real with all its rules, then check every rule on many inputs, including awkward ones. Count rule breaks, not just whether the answer sounded good.
A question to check yourself, an AI practice session and 1 cheat sheet entry come with the full roadmap. Unlock
Resources for this stage
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