AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
11min chapter
38.8 - David Duvenaud on Sabotage Evaluations and the Post-AGI Future
AXRP - the AI X-risk Research Podcast
Evaluating AI Sabotage Risks
This chapter explores the complexities of assessing advanced AI models for potential sabotage of human decision-making. It discusses the challenges in designing evaluations that effectively measure AI behavior, including the need for comprehensive oversight and understanding vulnerabilities. The conversation emphasizes strategies for mitigating risks, highlighting three key areas of evaluation to ensure robust AI deployment.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode