Director, Learning Design & Development| PMIAsheville, NC, United States
With Generative AI, iteratively refining and optimizing prompts can lead to better AI-generated results. This may involve adjusting the specificity or clarity of the prompt to increase relevance and accuracy of results.
What examples do you have of how improving a prompt drastically changed the output quality? What specific changes did you make that led to the improvement?
When prompting the AI to compare products, I specify a side-by-side table with relevant features and info to compare. Organizing features, specifications, and pros and cons into clear columns improved readability and allowed to make confident decisions. Saving Changes...
Anonymous
I have not yet used GenAI, but look forward to it one day, especially to assist in 3D prototyping, and project management too. Thank you. Saving Changes...
Increasing specifity and more context leads to more accurate and refined results/output. I am not familiar with the diverse frameworks provided by Sergio Luis Conte; speaking to GenAI engine as I would speak to another human (thus, providing context and sufficient level of detail) provides great outputs.
I agree. When I use closed AI models with internal clients or companies, I also ensure I upload an acronym guide to help it learn more. This reduces the time spent on reviewing results since the output is more accurate. Saving Changes...
Refining the promp is very important, but you need to check the LLM that you are using, in my case, I work refining a promp with Copilot, but alwas have differente results, in fact I use de same promp in ChatGPT and the result are more consistent. I think is importat tho choose the right tool. Saving Changes...
It is important to remember this: generative AI is just "predictive text with storoids". Obviously not only text will be the result. BUT the important thing is the answer will just to complete your question (prompt) with the things that have more probability to complete it. You can manage it using some of the parameters like temperature. So, it is very important when creating the prompt to put clear the role, the place where the role works/live/etc, the task the role has to accomplish and the format of the answer. This is an example of R-T-F. You have to eliminate as ambiguity as possible. If not, then hallucinations will happened.
Thank you Sergio. This is well put and summarizes it all Saving Changes...
Parke BrownProject Manager| Seed CompanyElizabethtown, Pa, United States
Refining has helped me further align content as my understanding of the problem develops with each step. Often, I begin an exploration with one sense of the need and discover additional, assumed factors over the process. Saving Changes...
Lily MurariuResearch Council Officer Program Advisor| National Research Council CanadaCantley, Quebec, Canada
It takes time, understanding of the process, and awareness from the user (s) of the iteratively refining and optimizing prompts process to get the desired results. Clarity of the desired output, use of explicit but concise language play a role in the final results when iterative process is used. As an applicable learning, document the prompts while applying the process. Saving Changes...
PMI Team Member
