We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
back
“DeepMind: An Approach to Technical AGI Safety and Security” by Zach Stein-Perlman
34:45
Share
2025/4/6
LessWrong (30+ Karma)
AI Chapters
Transcribe
Chapters
What is the Extended Abstract?
What Are the Background Assumptions?
Identifying the Four Areas of AI Risk
How Can We Address Misuse Risks?
What Is Misalignment and How Do We Train Aligned Models?
Defending Against Misaligned Models
Ensuring Stronger Defenses and Alignment Assurance
What Are the Limitations of This Approach?
Shownotes
Transcript
No transcript made for this episode yet, you may request it for free.