Scheming AIs
Listen before buying
Scheming AIs by Joe Carl Smith comes up on 80,000 Hours Podcast, with transcript quotes, timestamps, and episode context.
Scheming AIs by Joe Carl Smith appears 1 time across 1 podcast episode on 1 show, with transcript quotes and timestamps.
“Overall, we still think the risk of some future AI systems actually seeking power is just too high to bet against.”
Why people keep bringing this up
Scheming AIs is repeatedly mentioned in conversations about AI risk because episode guests and narrators cite a specific technical claim from the work. The 80,000 Hours Podcast references Section 4.2 of Joe Carl Smith’s paper in a narration by Zershaaneh Qureshi, highlighting its analysis of whether AIs might fake alignment during training to obtain power.
This focused citation shows the book is being used as a source for discussions about strategic deception and training-time behavior of AI systems. The mention on the 80,000 Hours episode frames the work as relevant to debates on power-seeking and alignment arguments within the AI risk community.
The host references Joe Carl Smith's work to explore the complexities of AI training and its implications for power-seeking behavior. They discuss how current AI systems may not develop long-term goals that lead to power-seeking, but caution against underestimating the risks involved.
Recent show rotation: 80,000 Hours Podcast.
Fastest path back to the source: the strongest indexed mention lands at 1:05:45 in the episode where we captured it.
Quick FAQ
Answers to common book, episode, podcast, and guest questions.
Which episode mentioned Scheming AIs?
Risks from power-seeking AI systems (article narration by Zershaaneh Qureshi) on 80,000 Hours Podcast is one of the clearest indexed episodes that mentioned Scheming AIs by Joe Carl Smith. The first indexed transcript timestamp lands at 1:05:45.
Which podcast mentioned Scheming AIs?
80,000 Hours Podcast is the main indexed podcast currently tied to Scheming AIs by Joe Carl Smith.
Who mentioned Scheming AIs on podcasts?
PodcastMentions ties Scheming AIs by Joe Carl Smith to 80,000 Hours Podcast, but the underlying mentions do not yet expose stable guest names for every episode.
Why do podcast guests bring up Scheming AIs?
The host references Joe Carl Smith's work to explore the complexities of AI training and its implications for power-seeking behavior. They discuss how current AI systems may not develop long-term goals that lead to power-seeking, but caution against underestimating the risks involved. It most often appears in conversations about AI power-seeking behavior.
Mentions across episodes
Every mention card links back to the episode page and exact transcript anchor.
“Section 4.2 of Joe Carl Smith's paper discusses whether AIs will fake alignment during training in order to get power.”