When prompting, it's important to give the model an 'out' for unexpected inputs, allowing it to indicate uncertainty when necessary.

A good prompt engineer must communicate clearly, iterate on prompts, and anticipate potential misinterpretations by the model.

Treating the model as capable and giving it complex instructions can lead to better outcomes than simplifying the task.

Reading prompts and model outputs closely helps improve prompting skills; experimentation is key.

It's important to evaluate prompts by testing them in real scenarios, as this can reveal flaws in the prompt design that need addressing.

When prompts become too complex, using examples can be more effective than trying to articulate every detail in prose, similar to test-driven development in programming.

Chain of thought prompting, where you instruct the model to think step-by-step, is less necessary with modern reasoning models but can still be useful in some cases. If you're running thousands or millions of inputs through your prompt, you'll still need to use classical prompting techniques to make your prompt more robust.

It's crucial to think about edge cases when designing prompts, ensuring they work not just for typical scenarios but also for unusual inputs.

You can enhance your prompting by including examples in your prompt. For instance, provide a problem and a good answer, and then ask the model to solve a similar problem.