You know all those #promptengineering courses? By the time they are made they are already obsolete.

The latest OpenAI course on the latest model (o1) teaches us the latest principles of prompting reasoning models:

-Be simple and direct.
-No explicit chain-of-thought required (thought you had learned something? Needless now 😅 )
-Use structure.
-Show rather than tell (no more begging and/or cheering and thanking?)
-Use cheaper models for certain things (optimizing costs becomes and even higher priority).
-Meta-prompting: use o1 to improve your prompts. (no more prompt engineering courses needed?)

PS: OpenAI's courses are free and available at DeepLearning.ai
PS2: This is tongue-in-cheek. I'm not saying one should stop taking such courses. Knowing how the tech works is paramount.