The head of AI Macro Nexus Research at 22V Research is unveiling a step-by-step guide on how chatbot users can supercharge their prompts and get elite-level results from AI.
In a new interview with Anthony Pompliano, Jordi Visser says he follows one pattern to get the best results from large language models (LLMs).
He notes that he starts with Grok, which leverages the intelligence on X, to get a prompt template for his subject of interest.
“Go to Grok and just type in there, ‘Find me a post on X with a template for an efficient prompt.’ It’ll come back with something, and you have that. You copy that right from the X post. You bring that into Grok or your favorite LLM and say, ‘Here’s what I want to do. I’m going to do a deep research dive into this company. Take this prompt and convert it using this as the template into doing what I want to do,’ which you mentioned at the top.
It doesn’t have to be [about] investment. It could be anything you want. It could be your health, anything. It creates the prompt, and I say three to eight pages because most templates of prompt engineering are like that.”
According to Visser, getting a template and converting it to serve a user’s purpose is a far superior method of prompt engineering than just typing in what comes to mind.
“Right off the bat, you’ve done something that is a thousand times better than just typing in, ‘I want to do a research report on that,’ because it’s saying you’re an expert in this field, you’re going to do deep research, it’s going to be this many pages [and] it’s going to go through. It may ask you a question, and it may say, ‘I want to know specifically what you want to do,’ and then go run that prompt in all four different LLMs, see the results you get, and if you want, take those four and upload them into Gemini and say, ‘Take these four and give me the best answer that combines the things that they overlap,’ and use all four of these to create one report.
That is the way I do things. I’m taking four. I view them as four individual people, the LLMs. They all have different skills. They all have different training models. They give me different answers.”
Disclaimer: Opinions expressed at CapitalAI Daily are not investment advice. Investors should do their own due diligence before making any decisions involving securities, cryptocurrencies, or digital assets. Your transfers and trades are at your own risk, and any losses you may incur are your responsibility. CapitalAI Daily does not recommend the buying or selling of any assets, nor is CapitalAI Daily an investment advisor. See our Editorial Standards and Terms of Use.