Episode
AI Control: Using Untrusted Systems Safely with Buck Shlegeris of Redwood Research, from the 80,000 Hours Podcast
- Published
- May 4, 2025
- Duration seconds
- 8781
- Processing state
processed- Canonical source
- https://www.cognitiverevolution.ai
Actions
POST https://stenobird.com/v1/public/podcasts/the-cognitive-revolution/episodes/ai-control-using-untrusted-systems-safely-with-buck-shlegeris-of-redwood-research-from-the-80-000-hours-podcast/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/the-cognitive-revolution/ai-control-using-untrusted-systems-safely-with-buck-shlegeris-of-redwood-research-from-the-80-000-hours-podcast.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
In this episode, we share a fascinating conversation from the 80,000 Hours Podcast between Rob Wiblin and Buck Shlegeris, CEO of Redwood Research. Buck dives deep into the emerging field of AI Control strategies for safely working with powerful AIs even if they’re not fully aligned. They explore innovative techniques like always-on auditing, honeypotting, re-sampling, and factored cognition to monitor and manage AI behaviors. This discussion highlights both the promise and challenges of controlling increasingly autonomous AI systems in today’s fast-evolving landscape. Tune in for a thoughtful, first-principles look at how we might secure useful outcomes from AIs we can’t fully trust. Original source: https://80000hours.org/podcast/episodes/buck-shlegeris-ai-control-scheming/ Upcoming Major AI Events Featuring Nathan Labenz as a Keynote Speaker https://www.imagineai.live/ https://adapta.org/adapta-summit https://itrevolution.com/product/enterprise-tech-leadership-summit-las-vegas/ SPONSORS: ElevenLabs: ElevenLabs gives your app a natural voice. Pick from 5,000+ voices in 31 languages, or clone your own, and launch lifelike agents for support, scheduling, learning, and games. Full server and client SDKs, dynamic tools, and monitoring keep you in control. Start free at https://elevenlabs.io/cognitive-revolution Oracle Cloud Infrastructure (OCI): Oracle Cloud Infrastructure offers next-generation cloud solutions that cut costs and boost performance. With OCI, you can run AI projects and applications faster and more securely for less. New U.S. customers can save 50% on compute, 70% on storage, and 80% on networking by switching to OCI before May 31, 2024. See if you qualify at https://oracle.com/cognitive Shopify: Shopify powers millions of businesses worldwide, handling 10…