I was invited to given a talk on the topic “Knowledge Discovery in Large Datasets using LLMs” at the 2nd Conference on Impact and Social Work.
In the presentation, I tried to make that case that current LLMs, like ChatGPT, allow people with limited background in programming to analyze datasets, thereby contributing to a “democratization” of data science.
The talk was basically a walk-through of a small data analysis project where I did not write a single line of the code myself, instead relying solely on ChatGPT pro.
There are, of course, some caveats: at some level of complexity, the LLM make mistakes, and without sufficient knowledge of coding, it becomes basically impossible to detect these situations.
