LessWrong (Curated & Popular) cover image

"How I stopped being sure LLMs are just making up their internal experience (but the topic is still confusing)" by Kaj_Sotala

LessWrong (Curated & Popular)

00:00

Simulation Bootstrap and Training Feedback

Kaj speculates that simulating human introspective language can be scaffolded by training, analogous to caregiver scaffolding children.

Play episode from 34:42
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app