Platformer

The scientific case for being nice to your chatbot

April 17 · 19 min · 28.8 MB
0:00-19:58

Streams straight from the publisher. podnod never proxies or re-hosts episode audio.

New research confirms that LLMs often perform better when you encourage them. But why?


Read the newsletter here: https://www.platformer.news/chatbot-emotion-research-anthropic-alignment-interpretability/


Hosted on Acast. See acast.com/privacy for more information.