AI Control: Improving Safety Despite Intentional Subversion

AI Safety Fundamentals: Alignment - Podcast tekijän mukaan BlueDot Impact

kokeile Podimo ilmaiseksi 60! päivän ajan

kokeile Podimo ilmaiseksi 60! päivän ajan

universumia joka on täynnä satoja podcasteja ja äänikirjoja, klikkaa tätä kokeillaksesi

 Sponsored

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-subversionNarrated for AI Safety Fundamentals by Perrin WalkerA podc...

Visit the podcast's native language site