Currents 082: Dan Shipper on Practical Applications of GPT-3
The Jim Rutt Show
How to Find Relevant Text
The most common way right now that all of these libraries and programmers who are doing this stuff are choosing relevant piece of text is using what's called embeddings. And you can think of the numbers that come out of the text as being something like longitude and latitude. So they allow you to plot the text onto like something like a map. Then if you have two pieces of text that you've turned into these numbers, you can map the distance between those those two sets of numbers to see how similar or different the piece of text are. The meaning of the word relevant changes depending on the context.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
