Listing to the demos they aren't really boots but rather just pre-recorded sound bytes. Lenny actually changes it's response depending on what the caller does. Pauses, keywords, etc.

> Lenny actually changes it's response depending on what the caller does. Pauses, keywords, etc.

It's actually a sequence of recordings played in the same order every time in a loop from the 5th. Telemarketers usually realize it a few recordings into the second loop.

Now imagine combining machine learning with conversation analysis to create the ultimate Lenny.

You should listen to some on youtube, they are not simple loops

https://www.youtube.com/results?search_query=lenny+telemarke...

one of them keeps trying for over 50 minutes

They are loops. I just listened to the 50 minute one, and 35 minutes in he's saying the same phrases he's already said near the beginning. "3rd eldest daughter..."

The article says the opposite.

"Lenny simply plays a set of audio recordings one after another to interact with the caller. The same set of prompts is always used in the same order."