(www.dwarkeshpatel.com)

308 points synthmeat | 4 comments | 14 Nov 24 08:56 UTC | HN request time: 0.801s | source

1. nutanc ◴[14 Nov 24 10:46 UTC] No.42134935[source]▶

Experimenting with creating semantic chunks of large podcasts. Got the following chunks, https://gist.github.com/nutanc/a9e6321649be5ea9806b4450b0bd6...

I got 171. So roughly 9 context discussions in one time stamp.

replies(1): >>42140515 #

2. maujim ◴[14 Nov 24 19:59 UTC] No.42140515[source]▶

What did you use to create the chunks?

replies(1): >>42144308 #

3. nutanc ◴[15 Nov 24 06:02 UTC] No.42144308[source]▶

It's a new approach I am experimenting with.

replies(1): >>42149835 #

4. maujim ◴[15 Nov 24 19:05 UTC] No.42149835{3}[source]▶

Interesting approach. Have you tried using existing clustering algorithms to determine the chunks instead of using distance or slope as a measure?

Interview with gwern