))
AI Control: Improving Safety Despite Intentional Subversion
Manage episode 424744791 series 3498845
Konten disediakan oleh BlueDot Impact. Semua konten podcast termasuk episode, grafik, dan deskripsi podcast diunggah dan disediakan langsung oleh BlueDot Impact atau mitra platform podcast mereka. Jika Anda yakin seseorang menggunakan karya berhak cipta Anda tanpa izin, Anda dapat mengikuti proses yang diuraikan di sini https://id.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.
Chapter
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)
83 episode
Bagikan
