The Inside View

Owain Evans is an AI Alignment researcher, research associate at the  Center of Human Compatible AI  at UC Berkeley, and now leading a new AI safety research group. In this episode we discuss two of his recent papers, “ Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs ” and “ Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data ”, alon...

This is a special crosspost episode where Adam Gleave is interviewed by Nathan Labenz from the Cognitive Revolution. At the end I also have a discussion with Nathan Labenz about his takes on AI. Adam Gleave is the founder of Far AI, and with Nathan they discuss finding vulnerabilities in GPT-4's fine-tuning and Assistant PIs, Far AI's work exposing exploitable flaws in "superhuman&quo...

Ethan Perez is a Research Scientist at Anthropic, where he leads a team working on developing model organisms of misalignment. Youtube: ⁠https://youtu.be/XDtDljh44DM Ethan is interviewed by Mikita Balesni (Apollo Research) and Henry Sleight (Astra Fellowship)) about his approach in selecting projects for doing AI Alignment research. A transcript & write-up will be available soon on the alignme...

Emil is the co-founder of palette.fm (colorizing B&W pictures with generative AI) and was previously working in deep learning for Google Arts & Culture. We were talking about Sora on a daily basis, so I decided to record our conversation, and then proceeded to confront him about AI risk. Patreon: https://www.patreon.com/theinsideview Sora: https://openai.com/sora Palette: https://palette.f...

Evan Hubinger leads the Alignment stress-testing at Anthropic and recently published "Sleeper Agents: Training Deceptive LLMs That Persist Through Safety Training". In this interview we mostly discuss the Sleeper Agents paper, but also how this line of work relates to his work with Alignment Stress-testing, Model Organisms of Misalignment, Deceptive Instrumental Alignment or Responsible...

Jeffrey Ladish is the Executive Director of Palisade Research which aimes so "study the offensive capabilities or AI systems today to better understand the risk of losing control to AI systems forever". He previously helped build out the information security program at Anthropic. Audio is a edit & re-master of the Twitter Space on "AI Governance and cyberwarfare" that happe...

Holly Elmore is an AI Pause Advocate who has organized two protests in the past few months (against Meta's open sourcing of LLMs and before the UK AI Summit), and is currently running the US front of the Pause AI Movement. Prior to that, Holly previously worked at a think thank and has a PhD in evolutionary biology from Harvard. [Deleted & re-uploaded because there were issues with the aud...

https://youtu.be/Fk2MrpuWinc

Youtube: https://youtu.be/JXYcLQItZsk Paul Christiano's post: https://www.lesswrong.com/posts/xWMqsvHapP3nwdSW8/my-views-on-doom

Neel Nanda is a researcher at Google DeepMind working on mechanistic interpretability. He is also known for his YouTube channel where he explains what is going on inside of neural networks to a large audience. In this conversation, we discuss what is mechanistic interpretability, how Neel got into it, his research methodology, his advice for people who want to get started, but also papers around s...

Joscha Bach (who defines himself as an AI researcher/cognitive scientist) has recently been debating existential risk from AI with Connor Leahy (previous guest of the podcast), and since their conversation was quite short I wanted to continue the debate in more depth. The resulting conversation ended up being quite long (over 3h of recording), with a lot of tangents, but I think this gives a somew...

Erik is a Phd at Berkeley working with Jacob Steinhardt, interested in making generative machine learning systems more robust, reliable, and aligned, with a focus on large language models. In this interview we talk about his paper "Automatically Auditing Large Language Models via Discrete Optimization" that he presented at ICML. Youtube: https://youtu.be/bhE5Zs3Y1n8 Paper: https://arxiv....

Dylan Patel  is Chief Analyst at SemiAnalysis a boutique semiconductor research and consulting firm specializing in the semiconductor supply chain from chemical inputs to fabs to design IP and strategy. The SemiAnalysis  substack  has ~50,000 subscribers and is the second biggest tech substack in the world. In this interview we discuss the current GPU shortage, why hardware is a multi-month proces...

Tony is a PhD student at MIT, and author of "Advesarial Policies Beat Superhuman Go AIs", accepted as Oral at the International Conference on Machine Learning (ICML). Paper: https://arxiv.org/abs/2211.00241 Youtube: https://youtu.be/Tip1Ztjd-so

David Bau is an Assistant Professor studying the structure and interpretation of deep networks, and the co-author on "Locating and Editing Factual Associations in GPT" which introduced Rank-One Model Editing (ROME), a method that allows users to alter the weights of a GPT model, for instance by forcing it to output that the Eiffel Tower is in Rome. David is a leading researcher in interp...

I've talked to Alexander Pan, 1st year at Berkeley working with Jacob Steinhardt about his paper "Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark" accepted as oral at ICML. Youtube: https://youtu.be/MjkSETpoFlY Paper: https://arxiv.org/abs/2304.03279

Vincent is currently spending his time supporting AI alignment efforts, as well as investing across AI, semi, energy, crypto, bio and deeptech. His mission is to improve science, augment human capabilities, have a positive impact, help reduce existential risks and extend healthy human lifespan. Youtube: https://youtu.be/weRoJ8KN2f0 Outline (00:00) Why Is Vincent Excited About the ICML Conference (...

Aran Komatsuzaki is a ML PhD student at GaTech and lead researcher at EleutherAI where he was one of the authors on GPT-J. In June 2022 we recorded an episode on scaling following up on the first Ethan Caballero episode (where we mentioned Aran as an influence on how Ethan started thinking about scaling). Note: For some reason I procrastinated on editing the podcast, then had a lot of in-person po...

Curtis, also known on the internet as AI_WAIFU, is the head of Alignment at EleutherAI. In this episode we discuss the massive orders of H100s from different actors, why he thinks AGI is 4-5 years away, why he thinks we're 90% "toast", his comment on Eliezer Yudkwosky's Death with Dignity, and what kind of Alignment projects is currently going on at EleutherAI, especially a proje...

Eric is a PhD student in the Department of Physics at MIT working with Max Tegmark on improving our scientific/theoretical understanding of deep learning -- understanding what deep neural networks do internally and why they work so well. This is part of a broader interest in the nature of intelligent systems, which previously led him to work with SETI astronomers, with Stuart Russell's AI alig...

Jesse Hoogland is a research assistant at David Krueger's lab in Cambridge studying AI Safety. More recently, Jesse has been thinking about Singular Learning Theory and Developmental Interpretability, which we discuss in this episode. Before he came to grips with existential risk from AI, he co-founded a health-tech startup automating bariatric surgery patient journeys. (00:00) Intro (03:57) J...

Explainer podcast for Richard Ngo's "Clarifying and predicting AGI" post on Lesswrong, which introduces the t-AGI framework to evaluate AI progress. A system is considered t-AGI if it can outperform most human experts, given time t, on most cognitive tasks. This is a new format, quite different from the interviews and podcasts I have been recording in the past. If you enjoyed this, l...

Max Kaufmann⁠ and Alan Chan discuss the evaluation of large language models, AI Governance and more generally the impact of the deployment of foundational models. is currently a Research Assistant to Owain Evans, mainly thinking about (and fixing) issues that might arise as we scale up our current ML systems, but also interested in issues arising from multi-agent failures and situational awareness...

Breandan Considine is a PhD student at the School of Computer Science at McGill University, under the supervision of Jin Guo and Xujie Si). There, he is building tools to help developers locate and reason about software artifacts, by learning to read and write code. I met Breandan while doing my "scale is all you need" series of interviews at Mila, where he surprised me by sitting down f...

Christoph Schuhmann is the co-founder and organizational lead at LAION, the non-profit who released LAION-5B, a dataset of 5,85 billion CLIP-filtered image-text pairs, 14x bigger than LAION-400M, previously the biggest openly accessible image-text dataset in the world. Christoph is being interviewed by Alan Chan, PhD in Machine Learning at Mila, and friend of the podcast, in the context of the Neu...