Monday, smooth AI operator! Let’s make AI work more, and you less, in 5 min:

Today we have the prompting GOD paper:

24 pages of tested AI research to get the MAXIMUM output from AI.

I went through it & here are the TOP 9 principles you NEED to know:

1. No need to be polite with LLM so there is no need to add phrases like “please”, “if you don’t mind”, “thank you”,

“I would like to”, etc.

Get straight to the point.

2. Break down complex tasks into a sequence of simpler prompts in an interactive conversation.

3. Employ affirmative directives such as ‘do,’ while steering clear of negative language like ‘don’t’.

4. Add “I’m going to tip $x for a better solution!” LOL

5. Incorporate the following phrases:

“Your task is”

“You MUST”

“You will be penalized”.

6 Use the phrase ”Answer a question given in a natural, human-like manner” in your prompts.

7. Use leading words like writing “think step by step”.

8. Allow the model to request precise details and requirements from you by asking you questions until it has enough information to provide the needed output

(for example, “From now on, I would like you to ask me questions to...”).

9. When formatting your prompt, start with ‘###Instruction###’, followed by either ‘###Example###’ or ‘###Question###’ if relevant.

Use one or more line breaks to separate instructions, examples, questions, context, and input data.

Check out the full paper here, good stuff: https://arxiv.org/pdf/2312.16171v1

Try it out and let me know your thoughts, or answer this email if you have more questions.

P.S. Next AI Power User cohort opening soon (round 3)!

If you want a spot, reply “AI Power” to this email and I will add you to the early bird list (extra discount and exclusive bonuses).

So you can get what 300+ business leaders are getting in New York.

Did you already try out our free AI productivity mini-course?

1500+ students loved it:

The 4-Hour AI Workweek Ignition

Previous issue, in case you missed it:

The ONLY solution is to learn FASTER

- Alex

P.S. if you have questions or looking for solutions, just answer this email, I try to answer and be helpful, I’m a human, not an AI. Yet.