Part 2: Add This Sentence To Your ChatGPT Prompts And Your Outputs Will Dramatically Improve.
Imagine if you can change the way you prompt ChatGPT with just a simple set of emotional based words and the outputs become many times better? Our research and now confirming acedemic research has produced a new way to prompt ChatGPT using element of human psychology that AI scientists could not have predicted. And it is a surprise on how and why it works.
Ask simple question we get simple answers. This is the reality of prompting Large Language Models like ChatGPT. Many folks, even AI experts approach prompts from a simplistic approach or even worse, like they are talking to a computer. This is the typical “Question/Answer” approach, called Input/Output (I/O) prompts. The results using this technique will always be the simplest path through the parametric data used to build the LLM. Mathematically, it is statistically the simplest path through the transformer system. If you have a very simple question, this will be ok. However it turns out this approach will always, I mean always produce the worse output based on any metric you care to use. Thus we can surmise that simple prompts need to be closer to SuperPrompt where a constellation of ideas are presented to the AI model so as to shape and produce the best possible output.
With the I/O prompting approach, even if you use follow-up questions, you will be on a “neuro pathway” that will have diminishing returns. This one of the 1000s of reasons I invented SuperPrompting. In relationship to “neuro pathway” it is vital we “activate” pathways that are in the model but not statically on the central path. The results are robustly better than simple I/O type prompts.
One aspect of a SuperPrompt is the ingredients we use to make it work. There are 1000s of parameters to consider. However, one has parameter, an exact sentence at the top of many of my SuperPrompts allows for the LLM to get consistently better outputs. And now a new university paper has been published that shows this to be confirmed empirically through their research also. I can say it uses human psychology to produce these outstanding results. This is not surprising as LLMs like ChatGPT are built on human language and humans are emotional being and thus it is reflected in our language.
In our research experimenting with the best possible prompts for ChatGPT we ran over 13 million iteration tests on how the system reacts to prompts and we made some spectacular and quite unbelievable discoveries. What did we discover? We will explore this in more detail in this member only article but I will say the thread of what we discovered is now being supported in academic papers. I also will say that what we discovered has fully confounded AI researchers and scientists. It uses natural language as a medium to express optimization of problems. This makes the process intuitive and easily understandable, bridging the gap between human intuition and machine processing. By presenting problems in a natural language format, it makes optimization tasks accessible to a broader audience
In this member only article, we will explore this new simple sentence added to a SuperPrompt and demonstrate why and how it works. We will also show you 100 useful and similar phrases that produce astonishing outputs. These are parts of the tools we use in Prompt Engineering, and it makes those that believe this is not a profession look quite uneducated and misinformed. There are so many powerful ways to prompt AI for great, if not believed, impossible outputs and this is just one.
If you are a member, thank you. If you are not yet a member, join us by clicking below.
🔐 Start: Exclusive Member-Only Content.
Membership status:
🔐 End: Exclusive Member-Only Content.
~—~
~—~
~—~
Subscribe ($99) or donate by Bitcoin.
Copy address: bc1q9dsdl4auaj80sduaex3vha880cxjzgavwut5l2
Send your receipt to Love@ReadMultiplex.com to confirm subscription.
IMPORTANT: Any reproduction, copying, or redistribution, in whole or in part, is prohibited without written permission from the publisher. Information contained herein is obtained from sources believed to be reliable, but its accuracy cannot be guaranteed. We are not financial advisors, nor do we give personalized financial advice. The opinions expressed herein are those of the publisher and are subject to change without notice. It may become outdated, and there is no obligation to update any such information. Recommendations should be made only after consulting with your advisor and only after reviewing the prospectus or financial statements of any company in question. You shouldn’t make any decision based solely on what you read here. Postings here are intended for informational purposes only. The information provided here is not intended to be a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your physician or other qualified healthcare provider with any questions you may have regarding a medical condition. Information here does not endorse any specific tests, products, procedures, opinions, or other information that may be mentioned on this site. Reliance on any information provided, employees, others appearing on this site at the invitation of this site, or other visitors to this site is solely at your own risk.
Copyright Notice:
All content on this website, including text, images, graphics, and other media, is the property of Read Multiplex or its respective owners and is protected by international copyright laws. We make every effort to ensure that all content used on this website is either original or used with proper permission and attribution when available.
However, if you believe that any content on this website infringes upon your copyright, please contact us immediately using our 'Reach Out' link in the menu. We will promptly remove any infringing material upon verification of your claim. Please note that we are not responsible for any copyright infringement that may occur as a result of user-generated content or third-party links on this website. Thank you for respecting our intellectual property rights.
Thank you!!!
Would this imply that these “tweaks” are context dependent ie. they depend on the type of “database”? being used to generate an output.
Matt, great question. Yes this is a good way to see it.