AXRP - the AI X-risk Research Podcast
de Daniel Filan
50 - Eli Lifland on AI 2027
Sobre este podcast
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.
Episódios
Os 20 episódios mais recentes de 63
- 50 - Eli Lifland on AI 2027 · 2 h 40 minRemember 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!…
- 49 - Caspar Oesterheld on Program Equilibrium · 2 h 32 minHow 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…
- 48 - Guive Assadi on AI Property Rights · 2 h 5 minIn 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…
- 47 - David Rein on METR Time Horizons · 1 h 47 minWhen 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…
- 46 - Tom Davidson on AI-enabled Coups · 2 h 5 minCould 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…
- 45 - Samuel Albanie on DeepMind's AGI Safety Approach · 1 h 15 minIn 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…
- 44 - Peter Salib on AI Rights for Human Safety · 3 h 21 minIn 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…
- 43 - David Lindner on Myopic Optimization with Non-myopic Approval · 1 h 40 minIn 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…
- 42 - Owain Evans on LLM Psychology · 2 h 14 minEarlier 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…
- 41 - Lee Sharkey on Attribution-based Parameter Decomposition · 2 h 16 minWhat'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…
- 40 - Jason Gross on Compact Proofs and Interpretability · 2 h 36 minHow 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…
- 38.8 - David Duvenaud on Sabotage Evaluations and the Post-AGI Future · 21 minIn 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…
- 38.7 - Anthony Aguirre on the Future of Life Institute · 23 minThe 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…
- 38.6 - Joel Lehman on Positive Visions of AI · 15 minTypically 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…
- 38.5 - Adrià Garriga-Alonso on Detecting AI Scheming · 28 minSuppose 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…
- 38.4 - Shakeel Hashim on AI Journalism · 24 minAI 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…
- 38.3 - Erik Jenner on Learned Look-Ahead · 24 minLots 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…
- 39 - Evan Hubinger on Model Organisms of Misalignment · 1 h 45 minThe '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…
- 38.2 - Jesse Hoogland on Singular Learning Theory · 18 minYou 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…
- 38.1 - Alan Chan on Agent Infrastructure · 25 minRoad 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…








