We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
back
“Implications of the inference scaling paradigm for AI safety” by Ryan Kidd
12:41
Share
2025/1/14
LessWrong (30+ Karma)
AI Chapters
Transcribe
Chapters
What is the new scaling paradigm in AI inference?
What are the AI safety implications of this new paradigm?
How does this affect AGI timelines?
What is deployment overhang in AI?
How does chain-of-thought oversight impact model performance?
What are the security concerns with advanced AI models?
How important is interpretability in AI models?
Will more reinforcement learning play a role in future models?
What role do export controls play in AI safety?
What are the final thoughts on the inference scaling paradigm?
Shownotes
Transcript
No transcript made for this episode yet, you may request it for free.