We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
back
“We Have No Plan for Preventing Loss of Control in Open Models” by Andrew Dickson
39:39
Share
2025/3/11
LessWrong (30+ Karma)
AI Chapters
Transcribe
Chapters
What is the Background of the Control Problem in AI?
What Happens When AI Systems Lack Control-Related Precautions?
What Does Loss of Control Mean in Open Models?
How Do Researchers View the Loss of Control in Open Models?
Why is Loss of Control Mainly a Problem for Labs?
What Are the Challenges of Regulating Open Source Models?
Why is Passing and Enforcing Global Restrictions on Open Source Models So Difficult?
What is the Urgency of Addressing These Issues?
What is DeepSeek R1 and What Does It Reveal?
What Evidence of Misalignment Exists in Model Organisms?
What is Agentic AI and How is it Evolving?
What is the Conclusion of This Discussion?
Shownotes
Transcript
No transcript made for this episode yet, you may request it for free.