A powerful collection of artificial intelligence technologies capable of generating virtually any kind of text, drawings, videos, code...you name it. This is generative AI , and its current capabilities are truly impressive. But with great generative power comes plenty of risks. Many users of GAI tools seem to ignore that these tools make mistakes.
Not surprisingly, some of these GAI tools are often used as a replacement for search engines. I once asked ChatGPT for a research paper I could use as a reference for the known risks of solely using anonymization and pseudonymization techniques for protecting sensitive information. ChatGPT provided the paper's title, the authors' names and affiliations, the conference the paper was presented at, and the paper's abstract.
Although GAI strives to emulate humans, it necessitates detailed instructions to generate an output of high quality and relevance. According to,"In prompt engineering, you choose the most appropriate formats, phrases, words and symbols that guide the AI to interact with your users more meaningfully. Prompt engineers use creativity plus trial and error to create a collection of input texts, so an application's generative AI works as expected.
Experience brings the notion of"I have been there" and"I have done that," which is often crucial to providing the best answer to any given question, considering details from applicable contexts. Competence is related to having the skills and knowledge required to execute a specific task properly. Discernment is critical for detecting wrong answers, avoiding common pitfalls, reducing unnecessary trial and error, and optimizing each effort.