))
AI Control: Improving Safety Despite Intentional Subversion
Manage episode 424744791 series 3498845
Content provided by BlueDot Impact. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by BlueDot Impact or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.
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:
- We summarize the paper;
- We compare our methodology to the methodology of other safety papers.
Source:
https://www.alignmentforum.org/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion
Narrated for AI Safety Fundamentals by Perrin Walker
A podcast by BlueDot Impact.
Learn more on the AI Safety Fundamentals website.
Chapters
1. AI Control: Improving Safety Despite Intentional Subversion (00:00:00)
2. Paper summary (00:02:41)
3. Setup (00:02:43)
4. Evaluation methodology (00:04:59)
5. Results (00:06:25)
6. Relationship to other work (00:10:51)
7. Future work (00:17:50)
80 episodes
Share
