Daniel Wentsch

The “devil’s advocate” prompt:

The goal is to create genuine intellectual friction. You want AI to surface weaknesses you can’t see because you’re too close to the work.

So how do we do it? Let’s imagine that we want to come up with 20 ideas for marketing slogans for a new mail-order cheese shop. The AI can generate those for us, but we will get even better quality if we remember the principle of telling AI who it is: You are an expert at marketing. When asked to generate slogan ideas you come up with ideas that

But if this Trojan Horse operation was as precise as it appears to have been, then it ranks among the most ethical acts of self-defense in memory. There are no “innocent” members of Hezbollah—whose only contributions to human culture have been the ruination of Lebanon and the modern evil of suicide bombing. This Iranian proxy has been firing

So when you discuss pricing with your designer (and it should be a discussion), make sure they can stand behind their quote. Have them walk you through it and explain why they’re charging what they’re charging. You should get an itemized breakdown for the project’s major parts. Some designers and studios may even be willing to give you an hourly

In an emotionally healthy childhood, the child can see that the good carer isn’t either entirely good or wholly bad and so isn’t worthy of either idealization or denigration. The child accepts the faults and virtues of the carer with melancholy maturity and gratitude—and in doing so, by extension, becomes ready to accept that everyone they like

You actually have likely read enough at this point to be a good prompt engineer. Let’s start with the third principle I shared earlier—treat AI like a person and tell it what kind of person it is. LLMs work by predicting the next word, or part of a word, that would come after your prompt, sort of like a sophisticated autocomplete function. Then