Skip to content
Back to 80,000 Hours Podcast
80,000 Hours Podcast artwork
Indexed 2 mentions

Risks from power-seeking AI systems (article narration by Zershaaneh Qureshi)

Summary, books mentioned, transcript quotes, and timestamps for Risks from power-seeking AI systems (article narration by Zershaaneh Qureshi) on 80,000 Hours Podcast.

Listen
Loading the embedded player…
Context before you listen

Risks from power-seeking AI systems (article narration by Zershaaneh Qureshi) mentions Scheming AIs by Joe Carl Smith and AI as Normal Technology by Narayananin and Kapoor with timestamps, quotes, and episode context.

3 books from this episode
Scheming AIs
Joe Carl Smith

Overall, we still think the risk of some future AI systems actually seeking power is just too high to bet against.

AI as Normal Technology
Narayananin and Kapoor

For example, one of the predictions made by Narayananin and Kapoor in AI as normal technology is that the AI systems we build in future will just be…

Episode summary
Hundreds of prominent AI scientists and other notable figures signed a statement in 2023 saying that mitigating the risk of extinction from AI should be a global priority. At 80,000 Hours, we’ve considered risks from AI to be the world’s most pressing problem since 2016. But what led us to this conclusion? Could AI really cause human extinction? We’re not certain, but we think the risk is worth taking very seriously. In particular, as companies create increasingly powerful AI systems, there’s a concerning chance that: These AI systems may develop dangerous long-term goals we don’t want. To pursue these goals, they may seek power and undermine the safeguards meant to contain them. They may even aim to disempower humanity and potentially cause our extinction. This article is written by Cody Fenwick and Zershaaneh Qureshi, and narrated by Zershaaneh Qureshi. It discusses why future AI systems could disempower humanity, what current AI research reveals about behaviours like power-seeking and deception, and how you can help mitigate the dangers. You can see the original article — packed with graphs, images, footnotes, and further resources — on the 80,000 Hours website: https://80000hours.org/problem-profiles/risks-from-power-seeking-ai/ Chapters: Risks from power-seeking AI systems (00:01:00) Introduction (00:01:17) Summary (00:03:09) Why are the risks from power-seeking AI a pressing world problem? (00:04:04) Section 1: Humans will likely build advanced AI systems with long-term goals (00:05:43) Section 2: AIs with long-term goals may be inclined to seek power (00:11:32) Section 3: These power-seeking AI systems could successfully disempower humanity (00:26:26) Section 4. People might create power-seeking AI systems without enough safeguards, despite the risks (00:38:34) Section 5: Work on this problem is neglected and tractable (00:47:37) Section 6: What are the arguments against working on this problem? (00:59:20) Section 7: How you can help (01:25:07) Thank you for listening (01:28:56) Audio editing: Dominic Armstrong Production: Zershaaneh Qureshi, Elizabeth Cox, and Katy Moore
Mention timeline

Jump between the book moments.

View every mention
Scheming AIs
Joe Carl Smith

The host references Joe Carl Smith's work to explore the complexities of AI training and its implications for power-s…

Card
AI as Normal Technology
Narayananin and Kapoor

The host mentions 'AI as Normal Technology' to highlight a prediction by the authors that future AI systems will prim…

Card
Book mentions2
Media mentions0
Quick answers

Quick FAQ

Answers to common summary, books, and takeaway questions for this episode.

What is Risks from power-seeking AI systems (article narration by Zershaaneh Qureshi) about?

Summary, books mentioned, transcript quotes, and timestamps for Risks from power-seeking AI systems (article narration by Zershaaneh Qureshi) on 80,000 Hours Podcast.

What are the main takeaways from Risks from power-seeking AI systems (article narration by Zershaaneh Qureshi)?

These are the strongest takeaways surfaced by the transcript, summary copy, and linked mentions for Risks from power-seeking AI systems (article narration by Zershaaneh Qureshi).

  • The conversation centers on AI power-seeking behavior.
  • A second recurring theme is AI safety and governance.
  • Referenced books include Scheming AIs by Joe Carl Smith and AI as Normal Technology by Narayananin and Kapoor.
  • The strongest audience signal points to Researchers and practitioners in AI safety and Researchers and policymakers in AI safety.

Which books are mentioned in Risks from power-seeking AI systems (article narration by Zershaaneh Qureshi)?

Scheming AIs by Joe Carl Smith and AI as Normal Technology by Narayananin and Kapoor are the clearest linked books in this episode, each tied back to transcript timestamps and quote cards.

Why are listeners searching for Risks from power-seeking AI systems (article narration by Zershaaneh Qureshi)?

Risks from power-seeking AI systems (article narration by Zershaaneh Qureshi) keeps attracting summary-style searches because this page combines episode context, transcript quotes, book references, and direct jump links back into the audio.

Topic and sentiment signals

Aggregated from transcript-derived mention metadata for better topical navigation and citation.

Mention sentiment
Critical Analysis(1)Deep Dive(1)
Audience signals
Researchers and practitioners in AI safetyResearchers and policymakers in AI safety

Books Mentioned

The full list below is ranked by how useful each mention is to a listener: stronger recommendation language, clearer quote context, and better timestamp support rise first.

Scheming AIs cover
Scheming AIs
Joe Carl Smith
Best for Researchers and practitioners in AI safetyOften cited around AI power-seeking behavior

Section 4.2 of Joe Carl Smith's paper discusses whether AIs will fake alignment during training in order to get power.

View mention details
Sentiment: Deep Dive
For: Researchers and practitioners in AI safety
Key quote: Overall, we still think the risk of some future AI systems actually seeking power is just too high to bet against.
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.
Amazon search results · affiliate link
Find on Amazon
AI as Normal Technology cover
AI as Normal Technology
Narayananin and Kapoor
Best for Researchers and policymakers in AI safetyOften cited around AI safety and governance

The AI systems we build in future will just be useful tools that humans control, rather than agents that autonomously pursue goals.

View mention details
Sentiment: Critical Analysis
For: Researchers and policymakers in AI safety
Key quote: For example, one of the predictions made by Narayananin and Kapoor in AI as normal technology is that the AI systems we build in future will just be useful tools that humans control.
The host mentions 'AI as Normal Technology' to highlight a prediction by the authors that future AI systems will primarily serve as tools controlled by humans rather than autonomous agents. This perspective is used to argue against the notion that advanced AI will inevitably pursue its own goals and pose existential risks.
Amazon search results · affiliate link
Find on Amazon
Weekly source-backed picks

Get the strongest books from new 80,000 Hours Podcast episodes.

A short weekly email with transcript-backed book recommendations, source quotes, and exact moments from recently indexed episodes.

Scheming AIs
80,000 Hours Podcast · 1:05:45
Overall, we still think the risk of some future AI systems actually seeking power is just too high to bet against.
AI as Normal Technology
80,000 Hours Podcast · 1:00:05
For example, one of the predictions made by Narayananin and Kapoor in AI as normal technology is that the AI systems we build in future will just be…
One useful email a week. Unsubscribe anytime.
Shop This Episode

Pick up the books after you hear them in context.

Scheming AIs cover
Mentioned at 1:05:45
Scheming AIs
Joe Carl Smith

The host references Joe Carl Smith's work to explore the complexities of AI training and its implications for power-seeking behavior. They discuss…

Amazon search results · affiliate link
AI as Normal Technology cover
Mentioned at 1:00:05
AI as Normal Technology
Narayananin and Kapoor

The host mentions 'AI as Normal Technology' to highlight a prediction by the authors that future AI systems will primarily serve as tools controlle…

Amazon search results · affiliate link

Movies & Documentaries Mentioned

No movie or documentary mentions yet

This episode does not have extracted media mentions yet.