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?
To reduce the number of iterations, it has worked for me to challenge the AI about its answers, for example, when faced with an answer, I ask it to review it and rigorously rate the originality of the answer by giving a score from 1 to 5. Then I ask the AI to give me more ideas or answers with the highest score possible.
Iterative process is always helpful in getting the right responses from AI Saving Changes...
Saurabh KumarService Delivery Manager| Tech Mahindra Ltd.Plano, TX, United States
I will start with few basics
1. Basic Knowledge of asked question and desired output based on PMs experience
2. Feedback of the output with peers and other team members
3. Different iteration of same question to evaluate the output results
4. Ensuring to provide relevant examples for Ai to give output in that lines.
5. Overall Human Intelligence and Historical Analysis Saving Changes...
Hello I am Teresa , Chemical Engineer student , passionate about Project Management and Project Engineering.
Best Practices for Accurate AI Results
When using AI systems, it's crucial to implement strategies to ensure the results are accurate, relevant, and aligned with your goals. Here are some best practices:
Data Quality and Quantity
Clean and High-Quality Data: Ensure your training data is accurate, consistent, and free from errors.
Sufficient Data: The more high-quality data you provide, the better the AI model can learn and produce accurate results.
Model Selection and Evaluation
Choose the Right Model: Select a model that is appropriate for your specific task and data type.
Regular Evaluation: Continuously evaluate the model's performance using relevant metrics to identify areas for improvement.
Prompt Engineering
Clear and Specific Prompts: Provide clear and concise prompts that accurately convey your intent.
Experimentation: Test different prompt variations to find the most effective ones for your use case.
Human Oversight
Human Review: Have human experts review and validate the AI-generated results to ensure accuracy and relevance.
Bias Mitigation: Be aware of potential biases in the data or model and take steps to mitigate them.
Continuous Learning
Iterative Improvement: Regularly update the model with new data and feedback to improve its performance over time.
Stay Informed: Keep up-to-date with the latest advancements in AI and machine learning to optimize your use of AI systems.
Ethical Considerations
Transparency: Be transparent about the limitations and potential biases of the AI system.
Fairness: Ensure the AI system is fair and unbiased in its decision-making.
By following these best practices, you can increase the likelihood of obtaining accurate, relevant, and goal-aligned results from your AI systems.
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.
Putting the content to the test for expert scrutiny has been my take on using the responses generated by AI. We tend to fall victim to AI Hallucination if we don't verify the data and responses generated by AI which could sometimes be catastrophic if major project decisions are made merely based on the output of AI. Saving Changes...
Anonymous
Agree Saving Changes...
Brian TripicchioConstruction-based Project ManagerAustin, Tx, United States
The best input provides the best output. As long as I am working under that directive with my prompts at all times, I will be far more confident in what I'm provided. Saving Changes...
Yakubu SalehPrincipal Regulatory Officer/PhD Student in Civil and Environmental Engineering| Nigerian Upstream Petroleum Regulatory CommissionGlasgow, Sct, United Kingdom
- Validation/Verification
- Reworking responses to fine tune prompts to meet your desired output Saving Changes...
You have to be aware and have as much as you can a good knowledge for what you need to Ask AI about. I think AI created for enhance our knowledge and help people to improve and develop their professional life. Saving Changes...
Understanding the CREATE and RTF models is a great way to understand the AI language. It is also important to understand why prompts fail and try using the right prompt patterns like RE ACT, Chain of Feedback, etc. which helps us tailor solutions based on the new information. Saving Changes...
PMI Team Member
