The Swyx Mixtape
Home
Episodes
About
swyx.io blog
Subscribe
menu
close
Home
Episodes
About
swyx.io blog
Subscribe
play
pause
[AI] Behind ChatGPT: RLHF and the Proximal Policy Optimization - Practical AI
January 24, 2023
/
14:07
/
E507
Download MP3
A great discussion of RLHF exhibited by ChatGPT by the PracticalAI guys
Show Notes
from https://overcast.fm/+HaNPbG9CU/
24:00
to read: https://overcast.fm/+HaNPbG9CU/
24:00
headphones
Listen Anywhere
Apple Podcasts
Listen On
Apple Podcasts
Spotify
Listen On
Spotify
Overcast
Listen On
Overcast
Pocket Casts
Listen On
Pocket Casts
YouTube
Listen On
YouTube
More Options »
Broadcast by
transistor logo
![[AI] Behind ChatGPT: RLHF and the Proximal Policy Optimization - Practical AI](https://img.transistor.fm/ehfVRtOTdvanujsOR_PvWAZpieYtHwCRnQtepj-ExmI/rs:fill:800:800:1/q:60/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9zaG93/LzE3NjMxLzE2MjY4/NDU3NzgtYXJ0d29y/ay5qcGc.webp)