Scaling Language Models

Raphaël discusses the potential risks of scaling language models and the concept of power-seeking behavior in AI alignment. Sean explores the differences between biological and artificial intelligences, highlighting the absence of embodied experiences in large language models.

In this clip
From this podcast
Mindscape Podcast
Mindscape 230 | Raphaël Millière on How Artificial Intelligence Thinks
Related Questions
- Can large language models replicate human behavior as discussed in the episode 168 - How to Solve AI Alignment with Paul Christiano and the clip AI Models and Ethical Behavior?
- Can large language models replicate human behavior?