Welcome to the alpha release of TYPE III AUDIO.
Expect very rough edges and very broken stuff—and regular improvements. Please share your thoughts.
Readings from the AI Safety Fundamentals: Alignment course.
We’ve released a paper, AI Control: Improving Safety Despite Intentional Subversion. This paper explores techniques that prevent AI catastrophes even if AI instances are colluding to subvert the safety techniques. In this post:
Source:
https://www.alignmentforum.org/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion
Narrated for AI Safety Fundamentals by Perrin Walker
Click “Add to feed” on episodes, playlists, and people.
Listen online or via your podcast app.