The Counting Argument For Scheming (Sections 4.1 And 4.2 Of "Scheming AIs") Joe Carlsmith Audio podcast

Artwork

Society Philosophy Joe

Player FM - Internet Radio Done Right

three 年前已添加！

内容由Joe Carlsmith提供。所有播客内容（包括剧集、图形和播客描述）均由 Joe Carlsmith 或其播客平台合作伙伴直接上传和提供。如果您认为有人在未经您许可的情况下使用您的受版权保护的作品，您可以按照此处概述的流程进行操作https://zh.player.fm/legal。

P

Peak Travel

Peak Travel podcast artwork

Peak Travel podcast artwork

1
You Can Visit All Seven Continents. But Should You? 26:46

13天之前26:46

26:46

For many travelers, Antarctica is a bucket-list destination, a once-in-a-lifetime opportunity to touch all seven continents. In 2023, a record-breaking 100,000 tourists made the trip. But the journey begs a fundamental question: What do we risk by traveling to a place that is supposed to be uninhabited by humans? And as the climate warms, should we really be going to Antarctica in the first place? SHOW NOTES: Kara Weller: The Impossible Dilemma of a Polar Guide Marilyn Raphael: A twenty-first century structural change in Antarctica’s sea ice system Karl Watson: First Time in Antarctica Jeb Brooks : 7 Days in Antarctica (Journey to the South Pole) Metallica - Freeze 'Em All: Live in Antarctica Learn about your ad choices: dovetail.prx.org/ad-choices…

Joe Carlsmith Audio « »
The counting argument for scheming (Sections 4.1 and 4.2 of "Scheming AIs")

大约1年之前 10:40

分享

MP3•单集首页

内容由Joe Carlsmith提供。所有播客内容（包括剧集、图形和播客描述）均由 Joe Carlsmith 或其播客平台合作伙伴直接上传和提供。如果您认为有人在未经您许可的情况下使用您的受版权保护的作品，您可以按照此处概述的流程进行操作https://zh.player.fm/legal。

This is sections 4.1 and 4.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?”

Text of the report here: https://arxiv.org/abs/2311.08379
Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power
Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power

… continue reading

章节

1. The counting argument for scheming (Sections 4.1 and 4.2 of "Scheming AIs") (00:00:00)

2. 4. Arguments for/against scheming that focus on the final properties of the (00:00:32)

3. 4.1 Contributors to reward vs. extra criteria (00:01:08)

4. 4.2 The counting argument (00:03:42)

63集单集

#Society #Philosophy #Joe

Artwork

The counting argument for scheming (Sections 4.1 and 4.2 of "Scheming AIs")

Joe Carlsmith Audio

published 大约1年之前

分享

MP3•单集首页

内容由Joe Carlsmith提供。所有播客内容（包括剧集、图形和播客描述）均由 Joe Carlsmith 或其播客平台合作伙伴直接上传和提供。如果您认为有人在未经您许可的情况下使用您的受版权保护的作品，您可以按照此处概述的流程进行操作https://zh.player.fm/legal。

This is sections 4.1 and 4.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?”

Text of the report here: https://arxiv.org/abs/2311.08379
Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power
Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power

… continue reading

章节

1. The counting argument for scheming (Sections 4.1 and 4.2 of "Scheming AIs") (00:00:00)

2. 4. Arguments for/against scheming that focus on the final properties of the (00:00:32)

3. 4.1 Contributors to reward vs. extra criteria (00:01:08)

4. 4.2 The counting argument (00:03:42)

63集单集

#Society #Philosophy #Joe

所有剧集

×

1
AI for AI safety 27:51

6 weeks之前27:51

27:51

We should try extremely hard to use AI labor to help address the alignment problem. Text version here: https://joecarlsmith.com/2025/03/14/ai-for-ai-safety

1
Paths and waystations in AI safety 18:07

6 weeks之前18:07

18:07

On the structure of the path to safe superintelligence, and some possible milestones along the way. Text version here: https://joecarlsmith.substack.com/p/paths-and-waystations-in-ai-safety

1
When should we worry about AI power-seeking? 46:54

9 weeks之前46:54

46:54

Examining the conditions required for rogue AI behavior. Text version here: https://joecarlsmith.substack.com/p/when-should-we-worry-about-ai-power

1
What is it to solve the alignment problem? 40:13

10 weeks之前40:13

40:13

Also: to avoid it? Handle it? Solve it forever? Solve it completely? Text version here: https://joecarlsmith.substack.com/p/what-is-it-to-solve-the-alignment

1
How do we solve the alignment problem? 8:43

10 weeks之前8:43

8:43

Introduction to a series of essays about paths to safe and useful superintelligence. Text version here: https://joecarlsmith.substack.com/p/how-do-we-solve-the-alignment-problem

1
Fake thinking and real thinking 1:18:47

12 weeks之前1:18:47

1:18:47

When the line pulls at your hand. Text version here: https://joecarlsmith.com/2025/01/28/fake-thinking-and-real-thinking/.

1
Takes on "Alignment Faking in Large Language Models" 1:27:54

18 weeks之前1:27:54

1:27:54

What can we learn from recent empirical demonstrations of scheming in frontier models? Text version here: https://joecarlsmith.com/2024/12/18/takes-on-alignment-faking-in-large-language-models/

1
(Part 2, AI takeover) Extended audio from my conversation with Dwarkesh Patel 2:07:33

29 weeks之前2:07:33

2:07:33

Extended audio from my conversation with Dwarkesh Patel. This part focuses on the basic story about AI takeover. Transcript available on my website here: https://joecarlsmith.com/2024/09/30/part-2-ai-takeover-extended-audio-transcript-from-my-conversation-with-dwarkesh-patel

1
(Part 1, Otherness) Extended audio from my conversation with Dwarkesh Patel 3:58:38

29 weeks之前3:58:38

3:58:38

Extended audio from my conversation with Dwarkesh Patel. This part focuses on my series "Otherness and control in the age of AGI." Transcript available on my website here: https://joecarlsmith.com/2024/09/30/part-1-otherness-extended-audio-transcript-from-my-conversation-with-dwarkesh-patel/

1
Introduction and summary for "Otherness and control in the age of AGI" 12:23

44 weeks之前12:23

12:23

This is the introduction and summary for my series "Otherness and control in the age of AGI." Text version here: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-agi

1
Second half of full audio for "Otherness and control in the age of AGI" 4:11:02

44 weeks之前4:11:02

4:11:02

Second half of the full audio for my series on how agents with different values should relate to one another, and on the ethics of seeking and sharing power. First half here: https://joecarlsmithaudio.buzzsprout.com/2034731/15266490-first-half-of-full-audio-for-otherness-and-control-in-the-age-of-agi PDF of the full series here: https://jc.gatspress.com/pdf/otherness_full.pdf Summary of the series here: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-agi…

1
First half of full audio for "Otherness and control in the age of AGI" 3:07:29

44 weeks之前3:07:29

3:07:29

First half of the full audio for my series on how agents with different values should relate to one another, and on the ethics of seeking and sharing power. Second half here: https://joecarlsmithaudio.buzzsprout.com/2034731/15272132-second-half-of-full-audio-for-otherness-and-control-in-the-age-of-agi PDF of the full series here: https://jc.gatspress.com/pdf/otherness_full.pdf Summary of the series here: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-agi…

1
Loving a world you don't trust 1:03:54

44 weeks之前1:03:54

1:03:54

Garden, campfire, healing water. Text version here: https://joecarlsmith.com/2024/06/18/loving-a-world-you-dont-trust This essay is part of a series I'm calling "Otherness and control in the age of AGI." I'm hoping that individual essays can be read fairly well on their own, but see here for brief text summaries of the essays that have been released thus far: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-agi…

1
On attunement 44:14

1 year之前44:14

44:14

Examining a certain kind of meaning-laden receptivity to the world. Text version here: https://joecarlsmith.com/2024/03/25/on-attunement This essay is part of a series I'm calling "Otherness and control in the age of AGI." I'm hoping that individual essays can be read fairly well on their own, but see here for brief text summaries of the essays that have been released thus far: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-agi (Though: note that I haven't put the summary post on the podcast yet.)…

1
On green 1:15:13

1 year之前1:15:13

1:15:13

Examining a philosophical vibe that I think contrasts in interesting ways with "deep atheism." Text version here: https://joecarlsmith.com/2024/03/21/on-green This essay is part of a series I'm calling "Otherness and control in the age of AGI." I'm hoping that individual essays can be read fairly well on their own, but see here for brief text summaries of the essays that have been released thus far: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-agi (Though: note that I haven't put the summary post on the podcast yet.)…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
On the abolition of man 1:09:22

1 year之前1:09:22

1:09:22

What does it take to avoid tyranny towards to the future? Text version here: https://joecarlsmith.com/2024/01/18/on-the-abolition-of-man This essay is part of a series I'm calling "Otherness and control in the age of AGI." I'm hoping that individual essays can be read fairly well on their own, but see here for brief text summaries of the essays that have been released thus far: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-agi (Though: note that I haven't put the summary post on the podcast yet.)…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Being nicer than Clippy 47:30

1 year之前47:30

47:30

Let's be the sort of species that aliens wouldn't fear the way we fear paperclippers. Text version here: https://joecarlsmith.com/2024/01/16/being-nicer-than-clippy/ This essay is part of a series I'm calling "Otherness and control in the age of AGI." I'm hoping that individual essays can be read fairly well on their own, but see here for brief text summaries of the essays that have been released thus far: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-agi (Though: note that I haven't put the summary post on the podcast yet.)…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
An even deeper atheism 25:12

1 year之前25:12

25:12

Who isn't a paperclipper? Text version here: https://joecarlsmith.com/2024/01/11/an-even-deeper-atheism This essay is part of a series I'm calling "Otherness and control in the age of AGI." I'm hoping that individual essays can be read fairly well on their own, but see here for brief summaries of the essays that have been released thus far: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-agi…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Does AI risk "other" the AIs? 13:15

1 year之前13:15

13:15

Examining Robin Hanson's critique of the AI risk discourse. Text version here: https://joecarlsmith.com/2024/01/09/does-ai-risk-other-the-ais This essay is part of a series of essays called "Otherness and control in the age of AGI." I'm hoping the individual essays can be read fairly well on their own, but see here for brief summaries of the essays that have been released thus far: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-agi…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
When "yang" goes wrong 21:32

1 year之前21:32

21:32

On the connection between deep atheism and seeking control. Text version here: https://joecarlsmith.com/2024/01/08/when-yang-goes-wrong This essay is part of a series of essays called "Otherness and control in the age of AGI." I'm hoping the individual essays can be read fairly well on their own, but see here for brief summaries of the essays that have been released thus far: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-agi…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Deep atheism and AI risk 46:59

1 year之前46:59

46:59

On a certain kind of fundamental mistrust towards Nature. Text version here: https://joecarlsmith.com/2024/01/04/deep-atheism-and-ai-risk This is the second essay in my series “Otherness and control in the age of AGI. I’m hoping that the individual essays can be read fairly well on their own, but see here for brief summaries of the essays released thus far: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-agi…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Gentleness and the artificial Other 22:39

1 year之前22:39

22:39

AIs as fellow creatures. And on getting eaten. Link: https://joecarlsmith.com/2024/01/02/gentleness-and-the-artificial-other This is the first essay in a series of essays that I’m calling “Otherness and control in the age of AGI.” See here for more about the series as a whole: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-agi.…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
In search of benevolence (or: what should you get Clippy for Christmas?) 52:52

1 year之前52:52

52:52

What is altruism towards a paperclipper? Can you paint with all the colors of the wind at once? (This is a recording of an essay originally published in 2021. Text here: https://joecarlsmith.com/2021/07/19/in-search-of-benevolence-or-what-should-you-get-clippy-for-christmas)

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Empirical work that might shed light on scheming (Section 6 of "Scheming AIs") 28:00

1 year之前28:00

28:00

This is section 6 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Summing up "Scheming AIs" (Section 5) 15:46

1 year之前15:46

15:46

This is section 5 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Speed arguments against scheming (Section 4.4-4.7 of "Scheming AIs") 15:19

1 year之前15:19

15:19

This is section 4.4 through 4.7 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Simplicity arguments for scheming (Section 4.3 of "Scheming AIs") 19:37

1 year之前19:37

19:37

This is section 4.3 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
The counting argument for scheming (Sections 4.1 and 4.2 of "Scheming AIs") 10:40

1 year之前10:40

10:40

This is sections 4.1 and 4.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Arguments for/against scheming that focus on the path SGD takes (Section 3 of "Scheming AIs") 29:03

1 year之前29:03

29:03

This is section 3 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Non-classic stories about scheming (Section 2.3.2 of "Scheming AIs") 24:34

1 year之前24:34

24:34

This is section 2.3.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Does scheming lead to adequate future empowerment? (Section 2.3.1.2 of "Scheming AIs") 22:54

1 year之前22:54

22:54

This is section 2.3.1.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
The goal-guarding hypothesis (Section 2.3.1.1 of "Scheming AIs") 19:11

1 year之前19:11

19:11

This is section 2.3.1.1 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
How useful for alignment-relevant work are AIs with short-term goals? (Section 2.2.4.3 of "Scheming AIs") 9:21

1 year之前9:21

9:21

This is section 2.2.4.3 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Is scheming more likely if you train models to have long-term goals? (Sections 2.2.4.1-2.2.4.2 of "Scheming AIs") 9:01

1 year之前9:01

9:01

This is sections 2.2.4.1-2.2.4.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
"Clean" vs. "messy" goal-directedness (Section 2.2.3 of "Scheming AIs") 16:44

1 year之前16:44

16:44

This is section 2.2.3 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Two sources of beyond-episode goals (Section 2.2.2 of "Scheming AIs") 21:25

1 year之前21:25

21:25

This is section 2.2.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Two concepts of an "episode" (Section 2.2.1 of "Scheming AIs") 12:08

1 year之前12:08

12:08

This is section 2.2.1 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Situational awareness (Section 2.1 of "Scheming AIs") 9:27

1 year之前9:27

9:27

This is section 2.1 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
On "slack" in training (Section 1.5 of "Scheming AIs") 7:12

1 year之前7:12

7:12

This is section 1.5 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Why focus on schemers in particular? (Sections 1.3-1.4 of "Scheming AIs") 31:17

1 year之前31:17

31:17

This is sections 1.3-1.4 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
A taxonomy of non-schemer models (Section 1.2 of "Scheming AIs") 11:20

1 year之前11:20

11:20

This is section 1.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Varieties of fake alignment (Section 1.1 of "Scheming AIs") 17:54

1 year之前17:54

17:54

This is section 1.1 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joecarlsmithaudio.buzzsprout.com/2034731/13969977-introduction-and-summary-of-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Full audio for "Scheming AIs: Will AIs fake alignment during training in order to get power?" 6:13:17

1 year之前6:13:17

6:13:17

This is the full audio for my report "Scheming AIs: Will AIs fake alignment during training in order to get power?" (I’m also posting audio for individual sections of the report on this podcast, but the ordering was getting messed up on various podcast apps, and I think some people might want one big audio file regardless, so here it is. I’m going to be posting the individual sections one by one, in the right order, over the coming days. ) Full text of the report here: https://arxiv.org/abs/2311.08379 Summary here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
Introduction and summary of "Scheming AIs: Will AIs fake alignment during training in order to get power?" 56:32

1 year之前56:32

56:32

This is a recording of the introductory section of my report "Scheming AIs: Will AIs fake alignment during training in order to get power?". This section includes a summary of the full report. The summary covers most of the main points and technical terminology, and I'm hoping that it will provide much of the context necessary to understand individual sections of the report on their own. (Note: the text of the report itself may not be public by the time this episode goes live.)…

J

Joe Carlsmith Audio

Joe Carlsmith Audio podcast artwork

1
In memory of Louise Glück 21:22

2 years之前21:22

21:22

"It was, she said, a great discovery, albeit my real life."

欢迎使用Player FM

Player FM正在网上搜索高质量的播客，以便您现在享受。它是最好的播客应用程序，适用于安卓、iPhone和网络。注册以跨设备同步订阅。

收听超过500个主题

边探索边听这个节目