Rationality: From AI to Zombies, The Podcast
LessWrong Sequence Posts Discussed in this Episode:
If You Demand Magic, Magic Won’t Help
Next Sequence Posts:
213 – Are Transformer Models Aligned By Default?
The Bayesian Conspiracy
00:00
Introduction
Exploring the potential for Transformers to achieve alignment as they grow in complexity, with a focus on improved behavior and reliability highlighted through anecdotes like Claude's helpful assistance. Despite past misalignments, progress in training and fine-tuning is recognized amidst ongoing skepticism.
Play episode from 00:00
Transcript
