The G-A-L Method
Dennis Kennedy's Group Advisory Layer Method (G-A-L Method™) to be used with GPT-4 (the paid version).
Alma Deutscher is a genius and former child prodigy who wrote an opera at the age of ten with the help of an imaginary country populated by imaginary composers who each wrote in their own style. Some of Alma’s imaginary composers provided materials well outside Alma's own 10-yo emotional range. In her own words: “I have lots of composers [in my mind] and sometimes when I'm stuck with something when I'm composing I go to them and ask them for advice. And quite often they come up with very interesting things.”
Now, you may have the same 'mental resources' as Alma Deutscher. We're in a strange world, to a degree that it may seem absurd to implement Dennis Kennedy’s Sept 2023 whitepaper describing his Group Advisory Layer Method (G-A-L Method™) to be used with GPT-4 (the paid version). Nevertheless, it's worth reading his whitepaper carefully and experimenting with his approach. The G-A-L Method generates a "mastermind advisory group", conjuring something like a traditional advisory board using only generative AI. Today is the worst this technology and technique will ever perform. Let me know how it works for you.
Here's the abridged essence of Kennedy's Method and ChatGPT prompts, from the whitepaper:
Explaining the persona, the context, the request, and the output
Many people use a prompt like “ChatGPT, show me some ways I might exercise to lose weight.”
Compare that prompt to this one: (a) “ChatGPT, assume that you are an experienced and expert personal trainer with specialized training in low-impact exercises and exercise as part of a weight loss program. (b) Also assume that I am a reasonably fit older adult male who exercises regularly. (c) What would be a great low-impact workout regimen to help me lose weight? (d) Create a recommended workout plan for the next thirty days that includes reasonable objectives.”
Which prompt will give you the results that you want? I invite you to try them and compare the results. I call these four core prompt components a) the persona, b) the context, c) the request, and d) the output (PCRO). The Group Advisory Layer (G-A-L) Method extends the PCRO process and takes it in new directions. In short, I get creative with how I use the persona and output components.
G-A-L Method: Create the personas in context
“ChatGPT, consider yourself a seasoned expert in mentoring, coaching, mastermind groups, and persona creation, drawing upon the wisdom from foundational books and guided by leading individuals in the field. Imagine yourself as a specialist with profound knowledge, having been trained using key techniques and principles. Now, analyze the following text and, based on your expertise, generate six thoughtful and insightful persona descriptions of ideal types of members for a mastermind group or advisory board for the purposes described: [INSERT DETAIL CONTEXT INFORMATION HERE]
What is the DETAILED CONTEXT INFORMATION?
To illustrate the context component, I use an advisory group as part of my weekly review. The context I give the group is a list of my annual goals and priorities, and a list of the main projects and tasks that I plan to work on during the next week. The group then gives me recommendations on priorities and schedules.
G-A-L Method: Prompting with the request and output
“ChatGPT, convene a meeting of the Mentors Mastermind Group:
Members present:
[INSERT STORED DESCRIPTIONS OF MEMBER PERSONAS]
Context:
[INSERT DETAIL CONTEXT INFORMATION HERE (again)]
Discussion Question:
[INSERT SPECIFIC QUESTION HERE]
Engage in a four-round round-robin discussion and extract one-paragraph insights from each and every member’s unique perspective in each round as they consider the discussion question and react critically to the comments of the others in the group. After round four, the group will reach a consensus and provide detailed recommendations, advice, and action steps for me based on their consensus opinion.”
Limitations
A response ChatGPT once gave me said it well: “Remember, while ChatGPT can provide diverse insights and simulate advice from different personas, it doesn’t replace the dynamic interactions, personal experiences, and nuanced understanding of a real group of experts. It’s based on patterns and information present in the data it was trained on and does not have personal experiences or subjective insights. Still, it can be a useful tool for generating new ideas, thinking through problems, and getting a semblance of diverse expert advice.”
The G-A-L Method is a framework for structured prompting that adds a layer to help guide desired responses from generative AI tools. It is not a replacement for actual human advice.