Director, Learning Design & Development| PMIAsheville, NC, United States
Validating and checking outputs is critical when working with AI systems like Generative AI. Such validation approaches may include establishing clear criteria, implementing strong testing protocols, and continuous refinement.
In your experience with AI, what are some best practices for ensuring the results you receive are accurate, relevant, and aligned with your original goals?
Keisha CurtisCreative Program Management Team Lead| SquareAtlanta, Ga, United States
A best practice is to craft a detailed, specific prompt to align AI responses with your goals. If the initial output falls short, assess gaps and refine the prompt iteratively to achieve more accurate and relevant results.
Saving Changes...
Eric DUEZProject Director| NokiaGif-Sur-Yvette, IDF, France
Jun 07, 2024 9:24 AM
Replying to Sergio Luis Conte
...
AI is a broader term. Generative AI is just an ancient model but everything "explode" when Google published the new architecture called transformer in 2017. So, with that said, take into account that generative AI is just "predictive test with steroids" just simplifying the model. With that said, two key points has to be taking into account when somebody works with AI: 1-human in the loop. 2-AI without Data (today called data science discipline or big data or whatever) is the same thing that live without oxygen. Talking about generative AI all related to technology has almost not impact with relation to all related to non-technological roles and activities. What you stated about accuracy and things like that are easy to implement because there are a lot inside disciplines like statistics. Most of them to make things "a priori" to prevent instead of cure. Few organizations taking into account that when generative AI environments are put in place almost a new business unit has to be created where roles like lawyers, linguistic, diversity and inclusion specialist must be hire to help on put it in place.
you need to work with iteration and to review constinuously the outputs ... the human is accountable for the outputs Saving Changes...
AI ecosystem is undoutbedly pretty huge and at the same time, is complex. Let's constrained it to Gen-AI specifically to lead it to a response to the question. Well, I'll frame it like any system/subsystem in the world needs an input to perform specific tasks as per the input provided and produce an output. The key to quality outcome is somehow or other is the quality input. That in our case is Prompting with Gen-AI platforms. Following practices would facilitate an effeective outcome.
1- Be "specific" in our prompts to enquire what we need from Gen-AI in response. Providing generic prompts, expect generic results. Avoid Garbage in, Garbage out scenario.
2- Provide "clear context" in the prompt to facilitate Gen-AI engine to visualize the situation/query on the same lines we are thinking or expecting or experiencing
3- Provide "examples or sample information as attachment" to keep our co-pilot/Gen-AI buddy aligned with what we are expecting in AI generated result
4- Communicate through our prompt to Gen-AI engine/bot/co-pilot what "format/Structure" we would like to see the result set so it meer our needs. Saving Changes...
Clear goals, scrutiny of the output, adjusting and improving input, cross functional team collaboration, risk/benefit analysis can all help in producing results that are accurate, relevant, and in alignment with your goals. Saving Changes...
Tyler MellorOwner, Project Manager| Elevated Projects LLCRaleigh, NC, United States
Ensuring prompts are developed to suit the outputs goal. Saving Changes...
Pallab MajiSenior Engineer| Carrier CorporationBengaluru, KA, India
Fine tune the prompt iteratively and adjust its result to get more precise and actionable insights. Saving Changes...
PMI Team Member
