Best Atomic Library Podcasts (2024)

1
AF - Showing SAE Latents Are Not Atomic Using Meta-SAEs by Bart Bussmann 35:53

1d ago35:53

35:53

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Showing SAE Latents Are Not Atomic Using Meta-SAEs, published by Bart Bussmann on August 24, 2024 on The AI Alignment Forum.Bart, Michael and Patrick are joint first…

1
Martin's Must Reads: 'Honey and Venom' 1:50

19h ago1:50

1:50

If you’ve ever wanted to become better friends with bees, then you must read Honey and Venom by Andrew Cote.By Betty Martin

1
AF - Would catching your AIs trying to escape convince AI developers to slow down or undeploy? by Buck Shlegeris 5:55

16h ago5:55

5:55

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Would catching your AIs trying to escape convince AI developers to slow down or undeploy?, published by Buck Shlegeris on August 26, 2024 on The AI Alignment Forum.I…

1
AF - Owain Evans on Situational Awareness and Out-of-Context Reasoning in LLMs by Michaël Trazzi 8:33

1d ago8:33

8:33

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Owain Evans on Situational Awareness and Out-of-Context Reasoning in LLMs, published by Michaël Trazzi on August 24, 2024 on The AI Alignment Forum.Owain Evans is an…

1
AF - Invitation to lead a project at AI Safety Camp (Virtual Edition, 2025) by Linda Linsefors 7:27

13h ago7:27

7:27

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Invitation to lead a project at AI Safety Camp (Virtual Edition, 2025), published by Linda Linsefors on August 23, 2024 on The AI Alignment Forum.Do you have AI Safe…

1
AF - Interoperable High Level Structures: Early Thoughts on Adjectives by johnswentworth 12:28

3h ago12:28

12:28

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Interoperable High Level Structures: Early Thoughts on Adjectives, published by johnswentworth on August 22, 2024 on The AI Alignment Forum.Meta: This post is a rela…

1
AF - A Robust Natural Latent Over A Mixed Distribution Is Natural Over The Distributions Which Were Mixed by johnswentworth 8:37

5h ago8:37

8:37

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: A Robust Natural Latent Over A Mixed Distribution Is Natural Over The Distributions Which Were Mixed, published by johnswentworth on August 22, 2024 on The AI Alignm…

1
Disrupting The Real Estate Market - Our Interview with Ryan Sawchuk of ReUp 27:00

9h ago27:00

27:00

We are meeting with Ryan Sawchuk, founder of ReUp Living, to discuss how ReUp is disrupting the real estate market, expansion through franchising, and plans to open an experience center in Las Vegas this fall. ReUp is a pre-listing solution for homeowners, buyers, and real estate agents that increases a home’s value by remodeling it with no risk or…

1
AF - Measuring Structure Development in Algorithmic Transformers by Jasmina Nasufi 18:17

1d ago18:17

18:17

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Measuring Structure Development in Algorithmic Transformers, published by Jasmina Nasufi on August 22, 2024 on The AI Alignment Forum.tl;dr: We compute the evolution…

1
Martin's Must-Reads: 'Atomic Habits' 1:48

3h ago1:48

1:48

“It is so easy to overestimate the importance of one defining moment and underestimate the value of making small improvements on a daily basis. Too often, we convince ourselves that massive success requires massive action. Meanwhile, improving by 1 percent isn’t particularly notable - sometimes it isn’t even noticeable - but it can be far more mean…

1
AF - AGI Safety and Alignment at Google DeepMind: A Summary of Recent Work by Rohin Shah 16:31

9d ago16:31

16:31

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: AGI Safety and Alignment at Google DeepMind: A Summary of Recent Work, published by Rohin Shah on August 20, 2024 on The AI Alignment Forum.We wanted to share a reca…

1
AF - Finding Deception in Language Models by Esben Kran 7:36

1d ago7:36

7:36

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Finding Deception in Language Models, published by Esben Kran on August 20, 2024 on The AI Alignment Forum.This June, Apart Research and Apollo Research joined force…

1
AF - Limitations on Formal Verification for AI Safety by Andrew Dickson 37:37

8d ago37:37

37:37

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Limitations on Formal Verification for AI Safety, published by Andrew Dickson on August 19, 2024 on The AI Alignment Forum.In the past two years there has been incre…

1
AF - Clarifying alignment vs capabilities by Richard Ngo 13:26

20h ago13:26

13:26

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Clarifying alignment vs capabilities, published by Richard Ngo on August 19, 2024 on The AI Alignment Forum.A core distinction in AGI safety is between alignment and…

1
AF - Untrustworthy models: a frame for scheming evaluations by Olli Järviniemi 15:38

2d ago15:38

15:38

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Untrustworthy models: a frame for scheming evaluations, published by Olli Järviniemi on August 19, 2024 on The AI Alignment Forum.In this post, I'll talk about trust…

1
AF - Calendar feature geometry in GPT-2 layer 8 residual stream SAEs by Patrick Leask 7:17

9h ago7:17

7:17

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Calendar feature geometry in GPT-2 layer 8 residual stream SAEs, published by Patrick Leask on August 17, 2024 on The AI Alignment Forum.TL;DR: We demonstrate that t…

1
How should we version design systems? 26:09

9d ago26:09

26:09

In this episode, we explore the enigma that is design system versioning. How do we make sense of versioning? How do you sync versions between code, design, and documentation? Maybe it’s easier to ignore versioning, but at what cost?By zeroheight

1
AF - Fields that I reference when thinking about AI takeover prevention by Buck Shlegeris 17:03

15d ago17:03

17:03

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Fields that I reference when thinking about AI takeover prevention, published by Buck Shlegeris on August 13, 2024 on The AI Alignment Forum.Is AI takeover like a nu…

1
Martin's Must-Reads: 'The Lie Maker' 1:43

6h ago1:43

1:43

“He could have some one out there, “ the man said, pulling back the front window curtains a tentative inch. “Watching the house right now.” He was careful not to step directly in front of the glass as he peeked outside. He ran his fingers nervously through his thick, dark hair. His handsome features were undercut by the fear in his eyes. He wasn’t …

1
AF - Extracting SAE task features for ICL by Dmitrii Kharlapenko 17:20

16d ago17:20

17:20

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Extracting SAE task features for ICL, published by Dmitrii Kharlapenko on August 12, 2024 on The AI Alignment Forum.TL;DRWe try to study task vectors in the SAE basi…

1
AF - In Defense of Open-Minded UDT by Abram Demski 23:26

21h ago23:26

23:26

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: In Defense of Open-Minded UDT, published by Abram Demski on August 12, 2024 on The AI Alignment Forum.A Defense of Open-Minded Updatelessness, with applications to a…

1
AF - You can remove GPT2's LayerNorm by fine-tuning for an hour by Stefan Heimersheim 19:03

6d ago19:03

19:03

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: You can remove GPT2's LayerNorm by fine-tuning for an hour, published by Stefan Heimersheim on August 8, 2024 on The AI Alignment Forum.This work was produced at Apo…

1
Beyond the Button #10: How do design systems foster user trust? 58:27

15d ago58:27

58:27

This month, Michelle is joined by two new faces: Tim Legierse, one of the most tenured members of the zeroheight team, and Beau Ulrey, Sr. Design System Manager at U.S. Bank. This month’s discussion is about how design systems can foster user trust. Sure, a good set of reusable components can create a more consistent product. But what does that mea…

1
Industry Evolution, Leadership, Resilience & Franchise Growth - Pillar to Post 38:00

20d ago38:00

38:00

We have a great show. We are meeting with Charles Furlough, President and CEO of Pillar To Post. Pillar To Post® is the #1 North American Home Inspection Franchise with more than 550+ locations in North America. Pillar To Post™ believes that home inspection is crucial in every homeownership story. A home inspection is designed to assess the home yo…

1
Back to School #6: Accessibility and Design Systems 59:35

5d ago59:35

59:35

Is there really such a thing as an accessible design system component? How can the systems team ensure accessible products? Geri and Amy turn the colour contrast up to 11:1 in their final podcast on accessibility.By Amy Hupe and Geri Reid

1
AF - Inference-Only Debate Experiments Using Math Problems by Arjun Panickssery 4:41

7d ago4:41

4:41

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Inference-Only Debate Experiments Using Math Problems, published by Arjun Panickssery on August 6, 2024 on The AI Alignment Forum.Work supported by MATS and SPAR. Co…

1
Martin's Must-Reads: 'The Underground Library' 1:51

7d ago1:51

1:51

“It is estimated that over half a million people used the London Underground stations as shelters during the war, many on a regular basis. The stations were up to the task, becoming underground communities with provisions and services.”By Betty Martin

1
AF - Self-explaining SAE features by Dmitrii Kharlapenko 19:36

23d ago19:36

19:36

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Self-explaining SAE features, published by Dmitrii Kharlapenko on August 5, 2024 on The AI Alignment Forum.TL;DRWe apply the method of SelfIE/Patchscopes to explain …

1
AF - The Bitter Lesson for AI Safety Research by Adam Khoja 6:33

26d ago6:33

6:33

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: The Bitter Lesson for AI Safety Research, published by Adam Khoja on August 2, 2024 on The AI Alignment Forum.Read the associated paper "Safetywashing: Do AI Safety …

1
AF - A Simple Toy Coherence Theorem by johnswentworth 11:59

26d ago11:59

11:59

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: A Simple Toy Coherence Theorem, published by johnswentworth on August 2, 2024 on The AI Alignment Forum.This post presents a simple toy coherence theorem, and then u…

1
AF - The 'strong' feature hypothesis could be wrong by lewis smith 31:14

12d ago31:14

31:14

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: The 'strong' feature hypothesis could be wrong, published by lewis smith on August 2, 2024 on The AI Alignment Forum.NB. I am on the Google Deepmind language model i…

1
AF - The need for multi-agent experiments by Martín Soto 17:17

27d ago17:17

17:17

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: The need for multi-agent experiments, published by Martín Soto on August 1, 2024 on The AI Alignment Forum.TL;DR: Let's start iterating on experiments that approxima…

1
Has AI made everyone a designer? A spicy conversation with Pablo Stanley 29:49

22d ago29:49

29:49

AI tools are transforming the landscape, making it easier than ever to create and design. Is this making everyone a designer? Will design system makers have to herd even more cats? We’ll be joined by special guest Pablo Stanley, the brilliant co-founder of two AI-based design tools, Musho and Lummi. We’ll unpack the potential of AI-based design too…

1
AF - Against AI As An Existential Risk by Noah Birnbaum 0:44

1M ago0:44

0:44

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Against AI As An Existential Risk, published by Noah Birnbaum on July 30, 2024 on The AI Alignment Forum.I wrote a post to my Substack attempting to compile all of t…

1
AF - Self-Other Overlap: A Neglected Approach to AI Alignment by Marc Carauleanu 19:29

1M ago19:29

19:29

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Self-Other Overlap: A Neglected Approach to AI Alignment, published by Marc Carauleanu on July 30, 2024 on The AI Alignment Forum.Many thanks to Bogdan Ionut-Cirstea…

1
Martin's Must-Reads: 'Lenny MarksGets Away with Murder' 1:45

14d ago1:45

1:45

“Lenny Marks seldom found herself unprepared. Lessons for her grade five students were religiously compiled a fortnight in advance, her tax return would be ready to submit no later than the fifteenth of July every year and her home fire escape plan was reviewed and updated each summer. She found tremendous peace in this level of organization, which…

1
AF - Investigating the Ability of LLMs to Recognize Their Own Writing by Christopher Ackerman 23:09

1M ago23:09

23:09

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Investigating the Ability of LLMs to Recognize Their Own Writing, published by Christopher Ackerman on July 30, 2024 on The AI Alignment Forum.This post is an interi…

1
AF - Can Generalized Adversarial Testing Enable More Rigorous LLM Safety Evals? by Stephen Casper 8:19

1M ago8:19

8:19

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Can Generalized Adversarial Testing Enable More Rigorous LLM Safety Evals?, published by Stephen Casper on July 30, 2024 on The AI Alignment Forum.Thanks to Zora Che…

1
Yuliya Solntseva: the forgotten queen of Soviet film 17:29

15d ago17:29

17:29

In this profile, written by critic and curator Rachel Pronger and first published on the Klassiki Journal, we introduce you to one of the most consequential and misunderstood figures in Soviet film history: Yuliya Solntseva. A silent star who became one half of Ukraine’s most influential creative marriage but whose place in history has been obscure…

1
AF - AXRP Episode 34 - AI Evaluations with Beth Barnes by DanielFilan 1:37:11

1M ago1:37:11

1:37:11

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: AXRP Episode 34 - AI Evaluations with Beth Barnes, published by DanielFilan on July 28, 2024 on The AI Alignment Forum.YouTube linkHow can we figure out if AIs are c…

1
AF - A Solomonoff Inductor Walks Into a Bar: Schelling Points for Communication by johnswentworth 35:18

1M ago35:18

35:18

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: A Solomonoff Inductor Walks Into a Bar: Schelling Points for Communication, published by johnswentworth on July 26, 2024 on The AI Alignment Forum.A Solomonoff induc…

1
AF - Pacing Outside the Box: RNNs Learn to Plan in Sokoban by Adrià Garriga-Alonso 3:34

1M ago3:34

3:34

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Pacing Outside the Box: RNNs Learn to Plan in Sokoban, published by Adrià Garriga-Alonso on July 25, 2024 on The AI Alignment Forum.Work done at FAR AI.There has bee…

1
AF - Does robustness improve with scale? by ChengCheng 2:16

1M ago2:16

2:16

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Does robustness improve with scale?, published by ChengCheng on July 25, 2024 on The AI Alignment Forum.Adversarial vulnerabilities have long been an issue in variou…

1
Franchise Interviews Meets with Ryan Wimpey, the founder of Tip Top K9 Franchise 28:00

1M ago28:00

28:00

We have a great show. We are meeting with Ryan Wimpey, the founder of TipTop K9, a company that provides families dog training, obedience, and manners training. Since 2008, Tip Top K9 has expanded to 18 locations across the U.S., and they have been shaping the dog training industry in unique ways. Key Takeaways Ryan will share his journey of growin…

1
AF - AI Constitutions are a tool to reduce societal scale risk by Samuel Dylan Martin 35:15

1M ago35:15

35:15

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: AI Constitutions are a tool to reduce societal scale risk, published by Samuel Dylan Martin on July 25, 2024 on The AI Alignment Forum.Sammy Martin, Polaris Ventures…

1
AF - A framework for thinking about AI power-seeking by Joe Carlsmith 30:52

1M ago30:52

30:52

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: A framework for thinking about AI power-seeking, published by Joe Carlsmith on July 24, 2024 on The AI Alignment Forum.This post lays out a framework I'm currently u…

1
Martin's Must-Reads: 'Don't Make Me Pull Over!' 1:44

1M ago1:44

1:44

Richard Raytay’s book “Don’t Make Me Pull Over!: An Informal History of the Family Road Trip” is a great read for any of you listeners who had a similar childhood. It is a mix of memoir, history lesson and travelogue.

1
AF - ML Safety Research Advice - GabeM by Gabe M 24:35

1M ago24:35

24:35

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: ML Safety Research Advice - GabeM, published by Gabe M on July 23, 2024 on The AI Alignment Forum.This is my advice for careers in empirical ML research that might h…

1
AF - Analyzing DeepMind's Probabilistic Methods for Evaluating Agent Capabilities by Axel Højmark 32:07

1M ago32:07

32:07

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Analyzing DeepMind's Probabilistic Methods for Evaluating Agent Capabilities, published by Axel Højmark on July 22, 2024 on The AI Alignment Forum.Produced as part o…

1
AF - Auto-Enhance: Developing a meta-benchmark to measure LLM agents' ability to improve other agents by Sam Brown 26:02

1M ago26:02

26:02

Link to original article Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Auto-Enhance: Developing a meta-benchmark to measure LLM agents' ability to improve other agents, published by Sam Brown on July 22, 2024 on The AI Alignment Forum.S…

Podcasts Worth a Listen

Atomic Library Podcasts

Podcasts Worth a Listen

Quick Reference Guide