The Inside View
Activity Overview
Episode publication activity over the past year
Episodes
Owain Evans - AI Situational Awareness, Out-of-Context Reasoning
23 Aug 2024
Contributed by Lukas
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 r...
[Crosspost] Adam Gleave on Vulnerabilities in GPT-4 APIs (+ extra Nathan Labenz interview)
17 May 2024
Contributed by Lukas
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 discussi...
Ethan Perez on Selecting Alignment Research Projects (ft. Mikita Balesni & Henry Sleight)
09 Apr 2024
Contributed by Lukas
Ethan Perez is a Research Scientist at Anthropic, where he leads a team working on developing model organisms of misalignment. Youtube: https://yo...
Emil Wallner on Sora, Generative AI Startups and AI optimism
20 Feb 2024
Contributed by Lukas
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 &...
Evan Hubinger on Sleeper Agents, Deception and Responsible Scaling Policies
12 Feb 2024
Contributed by Lukas
Evan Hubinger leads the Alignment stress-testing at Anthropic and recently published "Sleeper Agents: Training Deceptive LLMs That Persist Throug...
[Jan 2023] Jeffrey Ladish on AI Augmented Cyberwarfare and compute monitoring
27 Jan 2024
Contributed by Lukas
Jeffrey Ladish is the Executive Director of Palisade Research which aimes so "study the offensive capabilities or AI systems today to better unde...
Holly Elmore on pausing AI
22 Jan 2024
Contributed by Lukas
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...
Podcast Retrospective and Next Steps
09 Jan 2024
Contributed by Lukas
https://youtu.be/Fk2MrpuWinc
Paul Christiano's views on "doom" (ft. Robert Miles)
29 Sep 2023
Contributed by Lukas
Youtube: https://youtu.be/JXYcLQItZsk Paul Christiano's post: https://www.lesswrong.com/posts/xWMqsvHapP3nwdSW8/my-views-on-doom
Neel Nanda on mechanistic interpretability, superposition and grokking
21 Sep 2023
Contributed by Lukas
Neel Nanda is a researcher at Google DeepMind working on mechanistic interpretability. He is also known for his YouTube channel where he explains what...
Joscha Bach on how to stop worrying and love AI
08 Sep 2023
Contributed by Lukas
Joscha Bach (who defines himself as an AI researcher/cognitive scientist) has recently been debating existential risk from AI with Connor Leahy (previ...
Erik Jones on Automatically Auditing Large Language Models
11 Aug 2023
Contributed by Lukas
Erik is a Phd at Berkeley working with Jacob Steinhardt, interested in making generative machine learning systems more robust, reliable, and aligned, ...
Dylan Patel on the GPU Shortage, Nvidia and the Deep Learning Supply Chain
09 Aug 2023
Contributed by Lukas
Dylan Patel is Chief Analyst at SemiAnalysis a boutique semiconductor research and consulting firm specializing in the semiconductor supply chain fro...
Tony Wang on Beating Superhuman Go AIs with Advesarial Policies
04 Aug 2023
Contributed by Lukas
Tony is a PhD student at MIT, and author of "Advesarial Policies Beat Superhuman Go AIs", accepted as Oral at the International Conference o...
David Bau on Editing Facts in GPT, AI Safety and Interpretability
01 Aug 2023
Contributed by Lukas
David Bau is an Assistant Professor studying the structure and interpretation of deep networks, and the co-author on "Locating and Editing Factua...
Alexander Pan on the MACHIAVELLI benchmark
26 Jul 2023
Contributed by Lukas
I've talked to Alexander Pan, 1st year at Berkeley working with Jacob Steinhardt about his paper "Measuring Trade-Offs Between Rewards and Et...
Vincent Weisser on Funding AI Alignment Research
24 Jul 2023
Contributed by Lukas
Vincent is currently spending his time supporting AI alignment efforts, as well as investing across AI, semi, energy, crypto, bio and deeptech. His mi...
[JUNE 2022] Aran Komatsuzaki on Scaling, GPT-J and Alignment
19 Jul 2023
Contributed by Lukas
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...
Curtis Huebner on Doom, AI Timelines and Alignment at EleutherAI
16 Jul 2023
Contributed by Lukas
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 di...
Eric Michaud on scaling, grokking and quantum interpretability
12 Jul 2023
Contributed by Lukas
Eric is a PhD student in the Department of Physics at MIT working with Max Tegmark on improving our scientific/theoretical understanding of deep learn...
Jesse Hoogland on Developmental Interpretability and Singular Learning Theory
06 Jul 2023
Contributed by Lukas
Jesse Hoogland is a research assistant at David Krueger's lab in Cambridge studying AI Safety. More recently, Jesse has been thinking about Singul...
Clarifying and predicting AGI by Richard Ngo
09 May 2023
Contributed by Lukas
Explainer podcast for Richard Ngo's "Clarifying and predicting AGI" post on Lesswrong, which introduces the t-AGI framework to evaluate ...
Alan Chan And Max Kauffman on Model Evaluations, Coordination and AI Safety
06 May 2023
Contributed by Lukas
Max Kaufmann and Alan Chan discuss the evaluation of large language models, AI Governance and more generally the impact of the deployment of founda...
Breandan Considine on Neuro Symbolic AI, Coding AIs and AI Timelines
04 May 2023
Contributed by Lukas
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 ...
Christoph Schuhmann on Open Source AI, Misuse and Existential risk
01 May 2023
Contributed by Lukas
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 ...
Simeon Campos on Short Timelines, AI Governance and AI Alignment Field Building
29 Apr 2023
Contributed by Lukas
Siméon Campos is the founder of EffiSciences and SaferAI, mostly focusing on alignment field building and AI Governance. More recently, he started th...
Collin Burns On Discovering Latent Knowledge In Language Models Without Supervision
17 Jan 2023
Contributed by Lukas
Collin Burns is a second-year ML PhD at Berkeley, working with Jacob Steinhardt on making language models honest, interpretable, and aligned. In 2015 ...
Victoria Krakovna–AGI Ruin, Sharp Left Turn, Paradigms of AI Alignment
12 Jan 2023
Contributed by Lukas
Victoria Krakovna is a Research Scientist at DeepMind working on AGI safety and a co-founder of the Future of Life Institute, a non-profit organizatio...
David Krueger–Coordination, Alignment, Academia
07 Jan 2023
Contributed by Lukas
David Krueger is an assistant professor at the University of Cambridge and got his PhD from Mila. His research group focuses on aligning deep learning...
Ethan Caballero–Broken Neural Scaling Laws
03 Nov 2022
Contributed by Lukas
Ethan Caballero is a PhD student at Mila interested in how to best scale Deep Learning models according to all downstream evaluations that matter. He ...
Irina Rish–AGI, Scaling and Alignment
18 Oct 2022
Contributed by Lukas
Irina Rish a professor at the Université de Montréal, a core member of Mila (Quebec AI Institute), and the organizer of the neural scaling laws work...
Shahar Avin–Intelligence Rising, AI Governance
23 Sep 2022
Contributed by Lukas
Shahar is a senior researcher at the Center for the Study of Existential Risk in Cambridge. In his past life, he was a Google Engineer, though right n...
Katja Grace on Slowing Down AI, AI Expert Surveys And Estimating AI Risk
16 Sep 2022
Contributed by Lukas
Katja runs AI Impacts, a research project trying to incrementally answer decision-relevant questions about the future of AI. She is well known for a s...
Markus Anderljung–AI Policy
09 Sep 2022
Contributed by Lukas
Markus Anderljung is the Head of AI Policy at the Centre for Governance of AI in Oxford and was previously seconded to the UK government office ...
Alex Lawsen—Forecasting AI Progress
06 Sep 2022
Contributed by Lukas
Alex Lawsen is an advisor at 80,000 hours, released an Introduction to Forecasting Youtube Series and has recently been thinking about forecasting AI ...
Robert Long–Artificial Sentience
28 Aug 2022
Contributed by Lukas
Robert Long is a research fellow at the Future of Humanity Institute. His work is at the intersection of the philosophy of AI Safety and consciousness...
Ethan Perez–Inverse Scaling, Language Feedback, Red Teaming
24 Aug 2022
Contributed by Lukas
Ethan Perez is a research scientist at Anthropic, working on large language models. He is the second Ethan working with large language models coming o...
Robert Miles–Youtube, AI Progress and Doom
19 Aug 2022
Contributed by Lukas
Robert Miles has been making videos for Computerphile, then decided to create his own Youtube channel about AI Safety. Lately, he's been working on &n...
Connor Leahy–EleutherAI, Conjecture
22 Jul 2022
Contributed by Lukas
Connor was the first guest of this podcast. In the last episode, we talked a lot about EleutherAI, a grassroot collective of researchers he co-founded...
Raphaël Millière Contra Scaling Maximalism
24 Jun 2022
Contributed by Lukas
Raphaël Millière is a Presidential Scholar in Society and Neuroscience at Columbia University. He has previously completed a PhD in philosophy in Ox...
Blake Richards–AGI Does Not Exist
14 Jun 2022
Contributed by Lukas
Blake Richards is an Assistant Professor in the Montreal Neurological Institute and the School of Computer Science at McGill University and a Core Fac...
Ethan Caballero–Scale is All You Need
05 May 2022
Contributed by Lukas
Ethan is known on Twitter as the edgiest person at MILA. We discuss all the gossips around scaling large language models in what will be later known a...
10. Peter Wildeford on Forecasting
13 Apr 2022
Contributed by Lukas
Peter is the co-CEO of Rethink Priorities, a fast-growing non-profit doing research on how to improve the long-term future. On his free time, Peter ma...
9. Emil Wallner on Building a €25000 Machine Learning Rig
23 Mar 2022
Contributed by Lukas
Emil is a resident at the Google Arts & Culture Lab were he explores the intersection between art and machine learning. He recently built his own ...
8. Sonia Joseph on NFTs, Web 3 and AI Safety
22 Dec 2021
Contributed by Lukas
Sonia is a graduate student applying ML to neuroscience at MILA. She was previously applying deep learning to neural data at Janelia, an NLP research ...
7. Phil Trammell on Economic Growth under Transformative AI
24 Oct 2021
Contributed by Lukas
Phil Trammell is an Oxford PhD student in economics and research associate at the Global Priorities Institute. Phil is one of the smartest person I kn...
6. Slava Bobrov on Brain Computer Interfaces
06 Oct 2021
Contributed by Lukas
In this episode I discuss Brain Computer Interfaces with Slava Bobrov, a self-taught Machine Learning Engineer applying AI to neural biosignals to con...
5. Charlie Snell on DALL-E and CLIP
16 Sep 2021
Contributed by Lukas
We talk about AI generated art with Charlie Snell, a Berkeley student who wrote extensively about AI art for ML@Berkeley's blog (https://ml.berkeley.e...
4. Sav Sidorov on Learning, Contrarianism and Robotics
05 Sep 2021
Contributed by Lukas
I interview Sav Sidorov about top-down learning, contrarianism, religion, university, robotics, ego , education, twitter, friends, psychedelics, B-val...
3. Evan Hubinger on Takeoff speeds, Risks from learned optimization & Interpretability
08 Jun 2021
Contributed by Lukas
We talk about Evan’s background @ MIRI & OpenAI, Coconut, homogeneity in AI takeoff, reproducing SoTA & openness in multipolar scenarios, qu...
2. Connor Leahy on GPT3, EleutherAI and AI Alignment
04 May 2021
Contributed by Lukas
In the first part of the podcast we chat about how to speed up GPT-3 training, how Conor updated on recent announcements of large language models, why...
1. Does the world really need another podcast?
25 Apr 2021
Contributed by Lukas
In this first episode I'm the one being interviewed. Questions: - Does the world really needs another podcast? - Why call your podcast superintellige...