We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
back
“Thoughts on the conservative assumptions in AI control” by Buck
23:37
Share
2025/1/17
LessWrong (30+ Karma)
AI Chapters
Transcribe
Chapters
What Conservative Assumption Do I Not Make?
Are Hard Worlds Plausible?
Why Are These Assumptions Hard to Evaluate?
Why Relying on Conservative Assumptions is Methodologically Clean
Kerckhoff's Principle: An Analogy in Computer Security
What Are the Main Downsides of These Assumptions?
Insane Game Theory Requirements to Evaluate Techniques
Conclusion
Shownotes
Transcript
No transcript made for this episode yet, you may request it for free.