- monatlichErscheinungsrhythmus
- 2 h 14typische Länge
- 3. Aug.letzte Folge
AXRP (pronounced axe-urp) is the AI X-risk Research Podcast where I, Daniel Filan, have conversations with researchers about their papers. We discuss the paper, and hopefully get a sense of why it's been written and how it might reduce the risk of AI causing an existential catastrophe: that is, permanently and drastically curtailing humanity's future potential. You can visit the website and read transcripts at axrp.net.
Folgen
50 - Eli Lifland on AI 2027
Remember AI 2027? Not AI 2040, the newest coolest thing AI Futures Project has done, but AI 2027, their OG product? At long last, we have an AXRP episode about it. Enjoy! Transcript: https://axrp.net/episode/2026/08/03/episode-50-eli-liflan
49 - Caspar Oesterheld on Program Equilibrium
How does game theory work when everyone is a computer program who can read everyone else's source code? This is the problem of 'program equilibria'. In this episode, I talk with Caspar Oesterheld on work he's done on equilibria of programs
48 - Guive Assadi on AI Property Rights
In this episode, Guive Assadi argues that we should give AIs property rights, so that they are integrated in our system of property and come to rely on it. The claim is that this means that AIs would not kill or steal from humans, because t
47 - David Rein on METR Time Horizons
When METR says something like "Claude Opus 4.5 has a 50% time horizon of 4 hours and 50 minutes", what does that mean? In this episode David Rein, METR researcher and co-author of the paper "Measuring AI ability to complete long tasks", tal
46 - Tom Davidson on AI-enabled Coups
Could AI enable a small group to gain power over a large country, and lock in their power permanently? Often, people worried about catastrophic risks from AI have been concerned with misalignment risks. In this episode, Tom Davidson talks a
45 - Samuel Albanie on DeepMind's AGI Safety Approach
In this episode, I chat with Samuel Albanie about the Google DeepMind paper he co-authored called "An Approach to Technical AGI Safety and Security". It covers the assumptions made by the approach, as well as the types of mitigations it out
44 - Peter Salib on AI Rights for Human Safety
In this episode, I talk with Peter Salib about his paper "AI Rights for Human Safety", arguing that giving AIs the right to contract, hold property, and sue people will reduce the risk of their trying to attack humanity and take over. He al
43 - David Lindner on Myopic Optimization with Non-myopic Approval
In this episode, I talk with David Lindner about Myopic Optimization with Non-myopic Approval, or MONA, which attempts to address (multi-step) reward hacking by myopically optimizing actions against a human's sense of whether those actions
42 - Owain Evans on LLM Psychology
Earlier this year, the paper "Emergent Misalignment" made the rounds on AI x-risk social media for seemingly showing LLMs generalizing from 'misaligned' training data of insecure code to acting comically evil in response to innocuous questi
41 - Lee Sharkey on Attribution-based Parameter Decomposition
What's the next step forward in interpretability? In this episode, I chat with Lee Sharkey about his proposal for detecting computational mechanisms within neural networks: Attribution-based Parameter Decomposition, or APD for short. Patreo
40 - Jason Gross on Compact Proofs and Interpretability
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
38.8 - David Duvenaud on Sabotage Evaluations and the Post-AGI Future
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 second
38.7 - Anthony Aguirre on the Future of Life Institute
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
38.6 - Joel Lehman on Positive Visions of AI
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
38.5 - Adrià Garriga-Alonso on Detecting AI Scheming
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
38.4 - Shakeel Hashim on AI Journalism
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
38.3 - Erik Jenner on Learned Look-Ahead
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-
39 - Evan Hubinger on Model Organisms of Misalignment
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, E
38.2 - Jesse Hoogland on Singular Learning Theory
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
38.1 - Alan Chan on Agent Infrastructure
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
38.0 - Zhijing Jin on LLMs, Causality, and Multi-Agent Systems
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 w
37 - Jaime Sevilla on AI Forecasting
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 d
36 - Adam Shai and Paul Riechers on Computational Mechanics
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 ap
New Patreon tiers + MATS applications
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.
35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization
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
34 - AI Evaluations with Beth Barnes
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 MET
33 - RLHF Problems with Scott Emmons
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 tha
32 - Understanding Agency with Jan Kulveit
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 grou
31 - Singular Learning Theory with Daniel Murfet
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 answ
30 - AI Security with Jeffrey Ladish
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 e
