We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
back
“AI CoT Reasoning Is Often Unfaithful” by Zvi
15:33
Share
2025/4/4
LessWrong (30+ Karma)
AI Chapters
Transcribe
Chapters
What Did They Discover About AI CoT Reasoning?
How Does Reward Hacking Affect AI Reasoning?
Why Didn't More Training Improve the Models?
Was the Inaccuracy in AI Reasoning Intentional?
Shownotes
Transcript
No transcript made for this episode yet, you may request it for free.
