Inspired by a discussion on Hacker News about Google’s new AI-produced podcast feature in NotebookLM, I decided to see what podcasts would be created with minimal or whimsical data. Here are three examples.
Proverb
For the first, I uploaded a text file (named “Text.txt”) containing only the proverb “If wishes were horses, then beggars would ride.”
3.14159265358979
For this one, the only information provided was “3.14159265358979.”
Common words
For the third, I just pasted in a list of the most frequent words in English: “the of and to a in for is on that by this with i you it not or be are from at as your all have new more an was we will home can us about if.”