We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
back
“AI for AI safety” by Joe Carlsmith
34:07
Share
2025/3/25
LessWrong (Curated & Popular)
AI Chapters
Transcribe
Chapters
Introduction and summary
What is AI for AI safety?
A tale of two feedback loops
Contrast with human-labor-driven radical alignment progress views
Contrast with other ideas in the literature
Why is AI for AI safety so important?
The AI for AI safety sweet spot
The AI for AI safety spicy zone
Can we benefit from a sweet spot?
Objections to AI for AI safety
Other practical concerns
Shownotes
Transcript
No transcript made for this episode yet, you may request it for free.
