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 outlines.

Patreon: https://www.patreon.com/axrpodcast

Ko-fi: https://ko-fi.com/axrpodcast

Transcript: https://axrp.net/episode/2025/07/06/episode-45-samuel-albanie-deepminds-agi-safety-approach.html

Topics we discuss, and timestamps:

0:00:37 DeepMind's Approach to Technical AGI Safety and Security

0:04:29 Current paradigm continuation

0:19:13 No human ceiling

0:21:22 Uncertain timelines

0:23:36 Approximate continuity and the potential for accelerating capability improvement

0:34:29 Misuse and misalignment

0:39:34 Societal readiness

0:43:58 Misuse mitigations

0:52:57 Misalignment mitigations

1:05:20 Samuel's thinking about technical AGI safety

1:14:02 Following Samuel's work

Samuel on Twitter/X: x.com/samuelalbanie

Research we discuss:

An Approach to Technical AGI Safety and Security: https://arxiv.org/abs/2504.01849

Levels of AGI for Operationalizing Progress on the Path to AGI: https://arxiv.org/abs/2311.02462

The Checklist: What Succeeding at AI Safety Will Involve: https://sleepinyourhat.github.io/checklist/

Measuring AI Ability to Complete Long Tasks: https://arxiv.org/abs/2503.14499

Episode art by Hamish Doodles: hamishdoodles.com

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 also tells me how law reviews work, in the face of my incredulity.

Patreon: https://www.patreon.com/axrpodcast

Ko-fi: https://ko-fi.com/axrpodcast

Transcript: https://axrp.net/episode/2025/06/28/episode-44-peter-salib-ai-rights-human-safety.html

Topics we discuss, and timestamps:

0:00:40 Why AI rights

0:18:34 Why not reputation

0:27:10 Do AI rights lead to AI war?

0:36:42 Scope for human-AI trade

0:44:25 Concerns with comparative advantage

0:53:42 Proxy AI wars

0:57:56 Can companies profitably make AIs with rights?

1:09:43 Can we have AI rights and AI safety measures?

1:24:31 Liability for AIs with rights

1:38:29 Which AIs get rights?

1:43:36 AI rights and stochastic gradient descent

1:54:54 Individuating "AIs"

2:03:28 Social institutions for AI safety

2:08:20 Outer misalignment and trading with AIs

2:15:27 Why statutes of limitations should exist

2:18:39 Starting AI x-risk research in legal academia

2:24:18 How law reviews and AI conferences work

2:41:49 More on Peter moving to AI x-risk research

2:45:37 Reception of the paper

2:53:24 What publishing in law reviews does

3:04:48 Which parts of legal academia focus on AI

3:18:03 Following Peter's research

Links for Peter:

Personal website: https://www.peternsalib.com/

Writings at Lawfare: https://www.lawfaremedia.org/contributors/psalib

CLAIR: https://clair-ai.org/

Research we discuss:

AI Rights for Human Safety: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4913167

Will humans and AIs go to war? https://philpapers.org/rec/GOLWAA

Infrastructure for AI agents: https://arxiv.org/abs/2501.10114

Governing AI Agents: https://arxiv.org/abs/2501.07913

Episode art by Hamish Doodles: hamishdoodles.com

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 are generally good. Does this work? Can we get smarter-than-human AI this way? How does this compare to approaches like conservativism? Listen to find out.

Patreon: https://www.patreon.com/axrpodcast

Ko-fi: https://ko-fi.com/axrpodcast

Transcript: https://axrp.net/episode/2025/06/15/episode-43-david-lindner-mona.html

Topics we discuss, and timestamps:

0:00:29 What MONA is

0:06:33 How MONA deals with reward hacking

0:23:15 Failure cases for MONA

0:36:25 MONA's capability

0:55:40 MONA vs other approaches

1:05:03 Follow-up work

1:10:17 Other MONA test cases

1:33:47 When increasing time horizon doesn't increase capability

1:39:04 Following David's research

Links for David:

Website: https://www.davidlindner.me

Twitter / X: https://x.com/davlindner

DeepMind Medium: https://deepmindsafetyresearch.medium.com

David on the Alignment Forum: https://www.alignmentforum.org/users/david-lindner

Research we discuss:

MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking: https://arxiv.org/abs/2501.13011

Arguments Against Myopic Training: https://www.alignmentforum.org/posts/GqxuDtZvfgL2bEQ5v/arguments-against-myopic-training

Episode art by Hamish Doodles: hamishdoodles.com

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 questions. In this episode, I chat with one of the authors of that paper, Owain Evans, about that research as well as other work he's done to understand the psychology of large language models.

Patreon: https://www.patreon.com/axrpodcast

Ko-fi: https://ko-fi.com/axrpodcast

Transcript: https://axrp.net/episode/2025/06/06/episode-42-owain-evans-llm-psychology.html

Topics we discuss, and timestamps:

0:00:37 Why introspection?

0:06:24 Experiments in "Looking Inward"

0:15:11 Why fine-tune for introspection?

0:22:32 Does "Looking Inward" test introspection, or something else?

0:34:14 Interpreting the results of "Looking Inward"

0:44:56 Limitations to introspection?

0:49:54 "Tell me about yourself", and its relation to other papers

1:05:45 Backdoor results

1:12:01 Emergent Misalignment

1:22:13 Why so hammy, and so infrequently evil?

1:36:31 Why emergent misalignment?

1:46:45 Emergent misalignment and other types of misalignment

1:53:57 Is emergent misalignment good news?

2:00:01 Follow-up work to "Emergent Misalignment"

2:03:10 Reception of "Emergent Misalignment" vs other papers

2:07:43 Evil numbers

2:12:20 Following Owain's research

Links for Owain:

Truthful AI: https://www.truthfulai.org

Owain's website: https://owainevans.github.io/

Owain's twitter/X account: https://twitter.com/OwainEvans_UK

Research we discuss:

Looking Inward: Language Models Can Learn About Themselves by Introspection: https://arxiv.org/abs/2410.13787

Tell me about yourself: LLMs are aware of their learned behaviors: https://arxiv.org/abs/2501.11120

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data: https://arxiv.org/abs/2406.14546

Emergent Misalignment: Narrow fine-tuning can produce broadly misaligned LLMs: https://arxiv.org/abs/2502.17424

X/Twitter thread of GPT-4.1 emergent misalignment results: https://x.com/OwainEvans_UK/status/1912701650051190852

Taken out of context: On measuring situational awareness in LLMs: https://arxiv.org/abs/2309.00667

Episode art by Hamish Doodles: hamishdoodles.com

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.

Patreon: https://www.patreon.com/axrpodcast

Ko-fi: https://ko-fi.com/axrpodcast

Transcript: https://axrp.net/episode/2025/06/03/episode-41-lee-sharkey-attribution-based-parameter-decomposition.html

Topics we discuss, and timestamps:

0:00:41 APD basics

0:07:57 Faithfulness

0:11:10 Minimality

0:28:44 Simplicity

0:34:50 Concrete-ish examples of APD

0:52:00 Which parts of APD are canonical

0:58:10 Hyperparameter selection

1:06:40 APD in toy models of superposition

1:14:40 APD and compressed computation

1:25:43 Mechanisms vs representations

1:34:41 Future applications of APD?

1:44:19 How costly is APD?

1:49:14 More on minimality training

1:51:49 Follow-up work

2:05:24 APD on giant chain-of-thought models?

2:11:27 APD and "features"

2:14:11 Following Lee's work

Lee links (Leenks):

X/Twitter: https://twitter.com/leedsharkey

Alignment Forum: https://www.alignmentforum.org/users/lee_sharkey

Research we discuss:

Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-Based Parameter Decomposition: https://arxiv.org/abs/2501.14926

Toy Models of Superposition: https://transformer-circuits.pub/2022/toy_model/index.html

Towards a unified and verified understanding of group-operation networks: https://arxiv.org/abs/2410.07476

Feature geometry is outside the superposition hypothesis: https://www.alignmentforum.org/posts/MFBTjb2qf3ziWmzz6/sae-feature-geometry-is-outside-the-superposition-hypothesis

Episode art by Hamish Doodles: hamishdoodles.com

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://www.patreon.com/axrpodcast

Ko-fi: https://ko-fi.com/axrpodcast

Transcript: https://axrp.net/episode/2025/03/28/episode-40-jason-gross-compact-proofs-interpretability.html

Topics we discuss, and timestamps:

0:00:40 - Why compact proofs

0:07:25 - Compact Proofs of Model Performance via Mechanistic Interpretability

0:14:19 - What compact proofs look like

0:32:43 - Structureless noise, and why proofs

0:48:23 - What we've learned about compact proofs in general

0:59:02 - Generalizing 'symmetry'

1:11:24 - Grading mechanistic interpretability

1:43:34 - What helps compact proofs

1:51:08 - The limits of compact proofs

2:07:33 - Guaranteed safe AI, and AI for guaranteed safety

2:27:44 - Jason and Rajashree's start-up

2:34:19 - Following Jason's work

Links to Jason:

Github: https://github.com/jasongross

Website: https://jasongross.github.io

Alignment Forum: https://www.alignmentforum.org/users/jason-gross

Links to work we discuss:

Compact Proofs of Model Performance via Mechanistic Interpretability: https://arxiv.org/abs/2406.11779

Unifying and Verifying Mechanistic Interpretability: A Case Study with Group Operations: https://arxiv.org/abs/2410.07476

Modular addition without black-boxes: Compressing explanations of MLPs that compute numerical integration: https://arxiv.org/abs/2412.03773

Stage-Wise Model Diffing: https://transformer-circuits.pub/2024/model-diffing/index.html

Causal Scrubbing: a method for rigorously testing interpretability hypotheses: https://www.lesswrong.com/posts/JvZhhzycHu2Yd57RN/causal-scrubbing-a-method-for-rigorously-testing

Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition (aka the Apollo paper on APD): https://arxiv.org/abs/2501.14926

Towards Guaranteed Safe AI: https://www2.eecs.berkeley.edu/Pubs/TechRpts/2024/EECS-2024-45.pdf

Episode art by Hamish Doodles: hamishdoodles.com

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 intentions.

Patreon: https://www.patreon.com/axrpodcast

Ko-fi: https://ko-fi.com/axrpodcast

Transcript: https://axrp.net/episode/2025/03/01/episode-38_8-david-duvenaud-sabotage-evaluations-post-agi-future.html

FAR.AI: https://far.ai/

FAR.AI on X (aka Twitter): https://x.com/farairesearch

FAR.AI on YouTube: @FARAIResearch

The Alignment Workshop: https://www.alignment-workshop.com/

Topics we discuss, and timestamps:

01:42 - The difficulty of sabotage evaluations

05:23 - Types of sabotage evaluation

08:45 - The state of sabotage evaluations

12:26 - What happens after AGI?

Links:

Sabotage Evaluations for Frontier Models: https://arxiv.org/abs/2410.21514

Gradual Disempowerment: https://gradual-disempowerment.ai/

Episode art by Hamish Doodles: hamishdoodles.com

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 episode.

Patreon: https://www.patreon.com/axrpodcast

Ko-fi: https://ko-fi.com/axrpodcast

Transcript: https://axrp.net/episode/2025/02/09/episode-38_7-anthony-aguirre-future-of-life-institute.html

FAR.AI: https://far.ai/

FAR.AI on X (aka Twitter): https://x.com/farairesearch

FAR.AI on YouTube: https://www.youtube.com/@FARAIResearch

The Alignment Workshop: https://www.alignment-workshop.com/

Topics we discuss, and timestamps:

00:33 - Anthony, FLI, and Metaculus

06:46 - The Alignment Workshop

07:15 - FLI's current activity

11:04 - AI policy

17:09 - Work FLI funds

Links:

Future of Life Institute: https://futureoflife.org/

Metaculus: https://www.metaculus.com/

Future of Life Foundation: https://www.flf.org/

Episode art by Hamish Doodles: hamishdoodles.com

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-fi.com/axrpodcast

Transcript: https://axrp.net/episode/2025/01/24/episode-38_6-joel-lehman-positive-visions-of-ai.html

FAR.AI: https://far.ai/

FAR.AI on X (aka Twitter): https://x.com/farairesearch

FAR.AI on YouTube: https://www.youtube.com/@FARAIResearch

The Alignment Workshop: https://www.alignment-workshop.com/

Topics we discuss, and timestamps:

 01:12 - Why aligned AI might not be enough

04:05 - Positive visions of AI

08:27 - Improving recommendation systems

Links:

Why Greatness Cannot Be Planned: https://www.amazon.com/Why-Greatness-Cannot-Planned-Objective/dp/3319155237

We Need Positive Visions of AI Grounded in Wellbeing: https://thegradientpub.substack.com/p/beneficial-ai-wellbeing-lehman-ngo

Machine Love: https://arxiv.org/abs/2302.09248

AI Alignment with Changing and Influenceable Reward Functions: https://arxiv.org/abs/2405.17713

Episode art by Hamish Doodles: hamishdoodles.com

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/axrpodcast

Transcript: https://axrp.net/episode/2025/01/20/episode-38_5-adria-garriga-alonso-detecting-ai-scheming.html

FAR.AI: https://far.ai/

FAR.AI on X (aka Twitter): https://x.com/farairesearch

FAR.AI on YouTube: https://www.youtube.com/@FARAIResearch

The Alignment Workshop: https://www.alignment-workshop.com/

Topics we discuss, and timestamps:

01:04 - The Alignment Workshop

02:49 - How to detect scheming AIs

05:29 - Sokoban-solving networks taking time to think

12:18 - Model organisms of long-term planning

19:44 - How and why to study planning in networks

Links:

Adrià's website: https://agarri.ga/

An investigation of model-free planning: https://arxiv.org/abs/1901.03559

Model-Free Planning: https://tuphs28.github.io/projects/interpplanning/

Planning in a recurrent neural network that plays Sokoban: https://arxiv.org/abs/2407.15421

Episode art by Hamish Doodles: hamishdoodles.com