Best Jason Lehman Podcasts (2025)

1
40 - Jason Gross on Compact Proofs and Interpretability 2:36:05

2M ago2:36:05

2:36:05

How do we figure out whether interpretability is doing its job? One way is to see if it helps us prove things about models that we care about knowing. In this episode, I speak with Jason Gross about his agenda to benchmark interpretability in this way, and his exploration of the intersection of proofs and modern machine learning. Patreon: https://w…

1
38.8 - David Duvenaud on Sabotage Evaluations and the Post-AGI Future 20:42

3M ago20:42

20:42

In this episode, I chat with David Duvenaud about two topics he's been thinking about: firstly, a paper he wrote about evaluating whether or not frontier models can sabotage human decision-making or monitoring of the same models; and secondly, the difficult situation humans find themselves in in a post-AGI future, even if AI is aligned with human i…

1
38.7 - Anthony Aguirre on the Future of Life Institute 22:39

3M ago22:39

22:39

The Future of Life Institute is one of the oldest and most prominant organizations in the AI existential safety space, working on such topics as the AI pause open letter and how the EU AI Act can be improved. Metaculus is one of the premier forecasting sites on the internet. Behind both of them lie one man: Anthony Aguirre, who I talk with in this …

1
38.6 - Joel Lehman on Positive Visions of AI 15:28

4M ago15:28

15:28

Typically this podcast talks about how to avert destruction from AI. But what would it take to ensure AI promotes human flourishing as well as it can? Is alignment to individuals enough, and if not, where do we go form here? In this episode, I talk with Joel Lehman about these questions. Patreon: https://www.patreon.com/axrpodcast Ko-fi: https://ko…

1
38.5 - Adrià Garriga-Alonso on Detecting AI Scheming 27:41

4M ago27:41

27:41

Suppose we're worried about AIs engaging in long-term plans that they don't tell us about. If we were to peek inside their brains, what should we look for to check whether this was happening? In this episode Adrià Garriga-Alonso talks about his work trying to answer this question. Patreon: https://www.patreon.com/axrpodcast Ko-fi: https://ko-fi.com…

1
38.4 - Shakeel Hashim on AI Journalism 24:14

4M ago24:14

24:14

AI researchers often complain about the poor coverage of their work in the news media. But why is this happening, and how can it be fixed? In this episode, I speak with Shakeel Hashim about the resource constraints facing AI journalism, the disconnect between journalists' and AI researchers' views on transformative AI, and efforts to improve the st…

1
38.3 - Erik Jenner on Learned Look-Ahead 23:46

5M ago23:46

23:46

Lots of people in the AI safety space worry about models being able to make deliberate, multi-step plans. But can we already see this in existing neural nets? In this episode, I talk with Erik Jenner about his work looking at internal look-ahead within chess-playing neural networks. Patreon: https://www.patreon.com/axrpodcast Ko-fi: https://ko-fi.c…

1
39 - Evan Hubinger on Model Organisms of Misalignment 1:45:47

6M ago1:45:47

1:45:47

The 'model organisms of misalignment' line of research creates AI models that exhibit various types of misalignment, and studies them to try to understand how the misalignment occurs and whether it can be somehow removed. In this episode, Evan Hubinger talks about two papers he's worked on at Anthropic under this agenda: "Sleeper Agents" and "Sycop…

1
38.2 - Jesse Hoogland on Singular Learning Theory 18:18

6M ago18:18

18:18

You may have heard of singular learning theory, and its "local learning coefficient", or LLC - but have you heard of the refined LLC? In this episode, I chat with Jesse Hoogland about his work on SLT, and using the refined LLC to find a new circuit in language models. Patreon: https://www.patreon.com/axrpodcast Ko-fi: https://ko-fi.com/axrpodcast T…

1
38.1 - Alan Chan on Agent Infrastructure 24:48

6M ago24:48

24:48

Road lines, street lights, and licence plates are examples of infrastructure used to ensure that roads operate smoothly. In this episode, Alan Chan talks about using similar interventions to help avoid bad outcomes from the deployment of AI agents. Patreon: https://www.patreon.com/axrpodcast Ko-fi: https://ko-fi.com/axrpodcast The transcript: https…

1
38.0 - Zhijing Jin on LLMs, Causality, and Multi-Agent Systems 22:42

6M ago22:42

22:42

Do language models understand the causal structure of the world, or do they merely note correlations? And what happens when you build a big AI society out of them? In this brief episode, recorded at the Bay Area Alignment Workshop, I chat with Zhijing Jin about her research on these questions. Patreon: https://www.patreon.com/axrpodcast Ko-fi: http…

1
37 - Jaime Sevilla on AI Forecasting 1:44:25

8M ago1:44:25

1:44:25

Epoch AI is the premier organization that tracks the trajectory of AI - how much compute is used, the role of algorithmic improvements, the growth in data used, and when the above trends might hit an end. In this episode, I speak with the director of Epoch AI, Jaime Sevilla, about how compute, data, and algorithmic improvements are impacting AI, an…

1
36 - Adam Shai and Paul Riechers on Computational Mechanics 1:48:27

8M ago1:48:27

1:48:27

Sometimes, people talk about transformers as having "world models" as a result of being trained to predict text data on the internet. But what does this even mean? In this episode, I talk with Adam Shai and Paul Riechers about their work applying computational mechanics, a sub-field of physics studying how to predict random processes, to neural net…

1
New Patreon tiers + MATS applications 5:32

8M ago5:32

5:32

Patreon: https://www.patreon.com/axrpodcast MATS: https://www.matsprogram.org Note: I'm employed by MATS, but they're not paying me to make this video.

1
35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization 2:17:24

9M ago2:17:24

2:17:24

How do we figure out what large language models believe? In fact, do they even have beliefs? Do those beliefs have locations, and if so, can we edit those locations to change the beliefs? Also, how are we going to get AI to perform tasks so hard that we can't figure out if they succeeded at them? In this episode, I chat with Peter Hase about his re…

1
34 - AI Evaluations with Beth Barnes 2:14:02

10M ago2:14:02

2:14:02

How can we figure out if AIs are capable enough to pose a threat to humans? When should we make a big effort to mitigate risks of catastrophic AI misbehaviour? In this episode, I chat with Beth Barnes, founder of and head of research at METR, about these questions and more. Patreon: patreon.com/axrpodcast Ko-fi: ko-fi.com/axrpodcast The transcript:…

1
33 - RLHF Problems with Scott Emmons 1:41:24

11M ago1:41:24

1:41:24

Reinforcement Learning from Human Feedback, or RLHF, is one of the main ways that makers of large language models make them 'aligned'. But people have long noted that there are difficulties with this approach when the models are smarter than the humans providing feedback. In this episode, I talk with Scott Emmons about his work categorizing the pro…

1
32 - Understanding Agency with Jan Kulveit 2:22:29

12M ago2:22:29

2:22:29

What's the difference between a large language model and the human brain? And what's wrong with our theories of agency? In this episode, I chat about these questions with Jan Kulveit, who leads the Alignment of Complex Systems research group. Patreon: patreon.com/axrpodcast Ko-fi: ko-fi.com/axrpodcast The transcript: axrp.net/episode/2024/05/30/epi…

1
31 - Singular Learning Theory with Daniel Murfet 2:32:07

1y ago2:32:07

2:32:07

What's going on with deep learning? What sorts of models get learned, and what are the learning dynamics? Singular learning theory is a theory of Bayesian statistics broad enough in scope to encompass deep neural networks that may help answer these questions. In this episode, I speak with Daniel Murfet about this research program and what it tells …

1
30 - AI Security with Jeffrey Ladish 2:15:44

1y ago2:15:44

2:15:44

Top labs use various forms of "safety training" on models before their release to make sure they don't do nasty stuff - but how robust is that? How can we ensure that the weights of powerful AIs don't get leaked or stolen? And what can AI even do these days? In this episode, I speak with Jeffrey Ladish about security and AI. Patreon: patreon.com/ax…

1
29 - Science of Deep Learning with Vikrant Varma 2:13:46

1y ago2:13:46

2:13:46

In 2022, it was announced that a fairly simple method can be used to extract the true beliefs of a language model on any given topic, without having to actually understand the topic at hand. Earlier, in 2021, it was announced that neural networks sometimes 'grok': that is, when training them on certain tasks, they initially memorize their training …

1
28 - Suing Labs for AI Risk with Gabriel Weil 1:57:30

1y ago1:57:30

1:57:30

How should the law govern AI? Those concerned about existential risks often push either for bans or for regulations meant to ensure that AI is developed safely - but another approach is possible. In this episode, Gabriel Weil talks about his proposal to modify tort law to enable people to sue AI companies for disasters that are "nearly catastrophic…

1
27 - AI Control with Buck Shlegeris and Ryan Greenblatt 2:56:05

1y ago2:56:05

2:56:05

A lot of work to prevent AI existential risk takes the form of ensuring that AIs don't want to cause harm or take over the world---or in other words, ensuring that they're aligned. In this episode, I talk with Buck Shlegeris and Ryan Greenblatt about a different approach, called "AI control": ensuring that AI systems couldn't take over the world, e…

1
26 - AI Governance with Elizabeth Seger 1:57:13

1+ y ago1:57:13

1:57:13

The events of this year have highlighted important questions about the governance of artificial intelligence. For instance, what does it mean to democratize AI? And how should we balance benefits and dangers of open-sourcing powerful AI systems such as large language models? In this episode, I speak with Elizabeth Seger about her research on these …

1
25 - Cooperative AI with Caspar Oesterheld 3:02:09

1+ y ago3:02:09

3:02:09

Imagine a world where there are many powerful AI systems, working at cross purposes. You could suppose that different governments use AIs to manage their militaries, or simply that many powerful AIs have their own wills. At any rate, it seems valuable for them to be able to cooperatively work together and minimize pointless conflict. How do we ensu…

1
24 - Superalignment with Jan Leike 2:08:29

2y ago2:08:29

2:08:29

Recently, OpenAI made a splash by announcing a new "Superalignment" team. Lead by Jan Leike and Ilya Sutskever, the team would consist of top researchers, attempting to solve alignment for superintelligent AIs in four years by figuring out how to build a trustworthy human-level AI alignment researcher, and then using it to solve the rest of the pro…

1
23 - Mechanistic Anomaly Detection with Mark Xu 2:05:52

2y ago2:05:52

2:05:52

Is there some way we can detect bad behaviour in our AI system without having to know exactly what it looks like? In this episode, I speak with Mark Xu about mechanistic anomaly detection: a research direction based on the idea of detecting strange things happening in neural networks, in the hope that that will alert us of potential treacherous tur…

1
Survey, store closing, Patreon 4:26

2y ago4:26

4:26

Very brief survey: bit.ly/axrpsurvey2023 Store is closing in a week! Link: store.axrp.net/ Patreon: patreon.com/axrpodcast Ko-fi: ko-fi.com/axrpodcast

1
22 - Shard Theory with Quintin Pope 3:28:21

2y ago3:28:21

3:28:21

What can we learn about advanced deep learning systems by understanding how humans learn and form values over their lifetimes? Will superhuman AI look like ruthless coherent utility optimization, or more like a mishmash of contextually activated desires? This episode's guest, Quintin Pope, has been thinking about these questions as a leading resear…

1
Episode 4: Nostalgia might be hurting your ministry 10:24

2y ago10:24

10:24

We know what it's like to have a nostalgic moment and be taken back to a memory years ago. The emotion of that memory has a powerful effect on us. While there are a lot of good things about nostalgia, it can influence how a ministry makes decisions if we are not careful.By Jason Lehman

1
21 - Interpretability for Engineers with Stephen Casper 1:56:02

2y ago1:56:02

1:56:02

Lots of people in the field of machine learning study 'interpretability', developing tools that they say give us useful information about neural networks. But how do we know if meaningful progress is actually being made? What should we want out of these tools? In this episode, I speak to Stephen Casper about these questions, as well as about a benc…

1
20 - 'Reform' AI Alignment with Scott Aaronson 2:27:35

2y ago2:27:35

2:27:35

How should we scientifically think about the impact of AI on human civilization, and whether or not it will doom us all? In this episode, I speak with Scott Aaronson about his views on how to make progress in AI alignment, as well as his work on watermarking the output of language models, and how he moved from a background in quantum complexity the…

1
Episode 3: E3... An approach to simplify your communication 10:27

2y ago10:27

10:27

We've all been there. We are in a moment to share what we do or what our ministry is about and we find ourselves feeling unprepared. The E3 approach is a simple way to structure a presentation into 3 steps that are easy to remember.By Jason Lehman

1
Episode 2: Perspective - Our very own vantage point 12:03

2y ago12:03

12:03

We all see things a different way. That unique point of view can be a help or a barrier to good communication in your ministry.By Jason Lehman

1
Episode 1: An Introduction - The story and heart behind Ministry Edge 12:54

2y ago12:54

12:54

Hear from Jason Lehman on his ministry journey, observations about ministry challenges and hopes for Ministry Edge and the tools and resources planned in the coming season.By Jason Lehman

1
Store, Patreon, Video 2:39

2+ y ago2:39

2:39

Store: https://store.axrp.net/ Patreon: https://www.patreon.com/axrpodcast Ko-fi: https://ko-fi.com/axrpodcast Video: https://www.youtube.com/watch?v=kmPFjpEibu0

1
19 - Mechanistic Interpretability with Neel Nanda 3:52:47

2+ y ago3:52:47

3:52:47

How good are we at understanding the internal computation of advanced machine learning models, and do we have a hope at getting better? In this episode, Neel Nanda talks about the sub-field of mechanistic interpretability research, as well as papers he's contributed to that explore the basics of transformer circuits, induction heads, and grokking. …

1
New podcast - The Filan Cabinet 1:18

2+ y ago1:18

1:18

I have a new podcast, where I interview whoever I want about whatever I want. It's called "The Filan Cabinet", and you can find it wherever you listen to podcasts. The first three episodes are about pandemic preparedness, God, and cryptocurrency. For more details, check out the podcast website (thefilancabinet.com), or search "The Filan Cabinet" in…

1
18 - Concept Extrapolation with Stuart Armstrong 1:46:19

2+ y ago1:46:19

1:46:19

Concept extrapolation is the idea of taking concepts an AI has about the world - say, "mass" or "does this picture contain a hot dog" - and extending them sensibly to situations where things are different - like learning that the world works via special relativity, or seeing a picture of a novel sausage-bread combination. For a while, Stuart Armstr…

1
17 - Training for Very High Reliability with Daniel Ziegler 1:00:59

2+ y ago1:00:59

1:00:59

Sometimes, people talk about making AI systems safe by taking examples where they fail and training them to do well on those. But how can we actually do this well, especially when we can't use a computer program to say what a 'failure' is? In this episode, I speak with Daniel Ziegler about his research group's efforts to try doing this with present…

1
16 - Preparing for Debate AI with Geoffrey Irving 1:04:49

3y ago1:04:49

1:04:49

Many people in the AI alignment space have heard of AI safety via debate - check out AXRP episode 6 (axrp.net/episode/2021/04/08/episode-6-debate-beth-barnes.html) if you need a primer. But how do we get language models to the stage where they can usefully implement debate? In this episode, I talk to Geoffrey Irving about the role of language model…

1
15 - Natural Abstractions with John Wentworth 1:36:30

3y ago1:36:30

1:36:30

Why does anybody care about natural abstractions? Do they somehow relate to math, or value learning? How do E. coli bacteria find sources of sugar? All these questions and more will be answered in this interview with John Wentworth, where we talk about his research plan of understanding agency via natural abstractions. Topics we discuss, and timest…

1
14 - Infra-Bayesian Physicalism with Vanessa Kosoy 1:47:31

3y ago1:47:31

1:47:31

Late last year, Vanessa Kosoy and Alexander Appel published some research under the heading of "Infra-Bayesian physicalism". But wait - what was infra-Bayesianism again? Why should we care? And what does any of this have to do with physicalism? In this episode, I talk with Vanessa Kosoy about these questions, and get a technical overview of how inf…

1
13 - First Principles of AGI Safety with Richard Ngo 1:33:53

3y ago1:33:53

1:33:53

How should we think about artificial general intelligence (AGI), and the risks it might pose? What constraints exist on technical solutions to the problem of aligning superhuman AI systems with human intentions? In this episode, I talk to Richard Ngo about his report analyzing AGI safety from first principles, and recent conversations he had with E…

1
12 - AI Existential Risk with Paul Christiano 2:49:36

3+ y ago2:49:36

2:49:36

Why would advanced AI systems pose an existential risk, and what would it look like to develop safer systems? In this episode, I interview Paul Christiano about his views of how AI could be so dangerous, what bad AI scenarios could look like, and what he thinks about various techniques to reduce this risk. Topics we discuss, and timestamps: - 00:00…

1
11 - Attainable Utility and Power with Alex Turner 1:27:36

3+ y ago1:27:36

1:27:36

Many scary stories about AI involve an AI system deceiving and subjugating humans in order to gain the ability to achieve its goals without us stopping it. This episode's guest, Alex Turner, will tell us about his research analyzing the notions of "attainable utility" and "power" that underlie these stories, so that we can better evaluate how likel…

1
10 - AI's Future and Impacts with Katja Grace 2:02:58

4y ago2:02:58

2:02:58

When going about trying to ensure that AI does not cause an existential catastrophe, it's likely important to understand how AI will develop in the future, and why exactly it might or might not cause such a catastrophe. In this episode, I interview Katja Grace, researcher at AI Impacts, who's done work surveying AI researchers about when they expec…

1
9 - Finite Factored Sets with Scott Garrabrant 1:38:59

4y ago1:38:59

1:38:59

Being an agent can get loopy quickly. For instance, imagine that we're playing chess and I'm trying to decide what move to make. Your next move influences the outcome of the game, and my guess of that influences my move, which influences your next move, which influences the outcome of the game. How can we model these dependencies in a general way, …

1
8 - Assistance Games with Dylan Hadfield-Menell 2:23:17

4y ago2:23:17

2:23:17

How should we think about the technical problem of building smarter-than-human AI that does what we want? When and how should AI systems defer to us? Should they have their own goals, and how should those goals be managed? In this episode, Dylan Hadfield-Menell talks about his work on assistance games that formalizes these questions. The first coup…

1
Robo Cop (1987) w/ Peter Lehman from Les Merry Chevaliers 2:19:25

4y ago2:19:25

2:19:25

Kicking off what I'm calling the post pandemic Season 2 today with a long discussion about Paul Verhoeven's action classic Robocop from 1987 w/ Peter Lehman of Les Merry Chevaliers https://www.facebook.com/LesMerryChevaliers https://twitter.com/merrychevaliers https://www.instagram.com/merrychevaliers Check out LMC's new single Anyhow Anyway at the…

Podcasts Worth a Listen

Jason Lehman Podcasts

Podcasts Worth a Listen