Text Centric Data Science

Data Science 2.0?

Three forces are converging:

1 LLMs in general are getting much better at extracting structured data

2 Open Source LLMs are getting better and catching up with the best LLMs over time

3 LLMs are also becoming much, much cheaper which means you can use multiple LLMs for the same structured data extraction task for cross verification

In my opinion, this move towards "Text Centric Data Science" is going to be a big shift in how we will be approaching the field in the future.

In the course, I use a specific example to explain this change.

This is a very short course and you can get through all the videos in about 30 minutes.