Hook

Their other posts in the index, biggest breakout first.
This might be the best ChatGPT prompt that I've ever found. It turns on execution mode, which makes sure ChatGPT never lies, never hallucinates, and always follows user instructions. It also includes a list of forbidden behaviors and an output structure in all of its responses. And this prompt actually works, let me show you. If you come over to your ChatGPT settings and go to personalization, you can paste this prompt into the custom instructions so that it always follows it. This is a response without the prompt, and you can see that the information isn't very straightforward and it's actually wrong. Whereas when you use the prompt and ask the same question, you're going to get a much more direct answer and the exact source that it came from. And if you want to try this out yourself, comment "Prompt" and I'll drop you a link where you can just click copy up here and paste it directly into your ChatGPT.