We talk with Mengye Ren, Assistant Professor at NYU's Center for Data Science, about what intelligence actually means once you step outside a benchmark, and why scaling a single centralized model isn't the whole story.We get into why intelligence has to be defined in open environments, not closed ones, and what that means for how we measure progress. We push on the creativity question: today's models sample bottom-up from a softmax or a Gaussian, with no internal loop of consideration, and as Mengye puts it, we haven't understood creativity yet and we're already prepared to hand it over.We also talk about what's missing for the next paradigm: continual learning, memory, embodied grounding, and smaller models that actually accumulate experience instead of re-deriving everything from scratch each call. Along the way, we get into JEPA and latent variables, biology as inspiration vs. blueprint, why frontier labs don't lean on explicit latents, the limits of synthetic data and world models, agent-to-agent communication, model uncertainty and forecasting, and whether ML education still matters when AI writes the experiments.A grounded, contrarian conversation about where AI research should be looking next, beyond benchmarks, beyond scale.Timeline00:00 — Intro and welcome01:24 — What is intelligence? Defining it relative to objectives and open environments04:19 — Is intelligence really the path to human flourishing, or is it productivity?04:57 — Safety, scalable oversight, and whether stronger models help or hurt06:09 — What does "alignment" actually mean?07:18 — Centralized vs. decentralized models: objectivity vs. personal meaning08:50 — Hinton vs. LeCun: where Mengye stands on AI risk10:29 — Bottom-up vs. top-down architectures and feedback loops21:28 — Biology and AI: inspiration, not blueprint24:14 — Biological plausibility, spiking nets, and where the analogy breaks25:39 — JEPA, Mamba, and architectures beyond the transformer27:31 — Language as a special modality: abstraction built for communication29:04 — Are we too locked into the current paradigm? Risk of creativity collapse30:09 — Synthetic data, simulation, and the brain's own generative models31:43 — World models and physical AI: how babies actually learn 33:03 — The case for smaller, continually learning models37:02 — The role of academic research in a frontier-lab world39:47 — Why LLMs aren't funny: the creativity gap40:35 — What research areas matter most: embodiment, continual learning, creativity42:05 — Creativity is bounded by experience — and why bottom-up sampling isn't enough45:35 — Agent-to-agent communication and the limits of sub-agents46:39 — Model confidence, epistemic uncertainty, and forecasting49:44 — Tokenization, static vs. dynamic worlds, and always-learning systems52:20 — Latent variables, JEPA, and why frontier models skip them53:40 — The future of ML education when AI writes the experimentsMusic:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

We host Tal Linzen, Associate Professor at NYU and Research Scientist at Google, for a conversation on the intersection of cognitive science and large language models.We discussed why children can learn language from around 100 million words while LLMs need trillions, and the surprising finding that as models get better at predicting the next word, they become worse models of how humans actually process language. Tal walked us through how his lab uses eye-tracking and reading-time data to compare model behavior to human behavior, and what that reveals about prediction, working memory, and the limits of current architectures.We also got into nature versus nurture and how inductive biases can be instilled by pre-training on synthetic languages, world models and whether transformers actually use the geometric structure they encode, the BabyLM challenge and data-efficient language learning, and what mechanistic interpretability can offer cognitive science beyond just fixing model bugs. The conversation closed on academia versus industry, the role of PhDs in the current AI moment, and how AI coding tools are changing the way Tal teaches and evaluates students at NYU.Timeline00:13 — Intro and what cognitive science means02:16 — Using computational simulations to understand how humans learn language05:26 — How children learn language vs. how LLMs are pre-trained07:53 — Why mainstream LLMs are not good models of humans 10:07 — Comparing humans and models with eye-tracking and reading behavior13:52 — Sensory modalities, smell, and how much you can learn from language alone16:03 — Animal cognition and decoding animal communication17:00 — Nature vs. nurture, inductive biases, and what transformers can and can't learn21:21 — Instilling inductive biases through synthetic languages 27:34 — The bouba/kiki effect and cross-linguistic sound symbolism28:33 — Latent causal structure in language and whether models discover it31:13 — Does knowing linguistics help build better models?35:07 — World models: what they mean, and why transformers encode geometry but don't use it39:13 — Tokenization, and why Tal doesn't like it41:35 — Scaling laws and the inverse-U curve of model quality vs. human fit44:34 — Where the human–model mismatch comes from: architecture, memory, and data47:08 — Diffusion language models and sentence planning48:21 — Data quality, synthetic data, and curriculum effects50:54 — Comparing models at different training stages to human development; BabyLM54:40 — What level of the model should we actually probe? Representations vs. behavior1:01:04 — Mechanistic interpretability, Deep Dream, and human dreaming1:02:11 — Cognitive neuroscience, intracranial recordings, and working memory1:10:31 — Should you still do a PhD in 2026?1:12:31 — Will software engineers lose their jobs to AI?1:17:43 — Teaching in the age of coding agents: what changes in the classroom1:20:54 — What's next: human-like LLMs as user simulators, and recruitingMusic:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

We host Chieh-Hsin (Jesse) Lai, Staff Research Scientist at Sony AI and visiting professor at National Yang Ming Chiao Tung University, Taiwan, for a conversation about diffusion models, the technology behind tools like Stable Diffusion, and most of the AI image and video generators you've seen in the last few years. Jesse recently co-authored The Principles of Diffusion Models with Stefano Ermon, and the book is quickly becoming a go-to reference in the field.We start with what a generative model actually is, and what it means to "generate" an image or a sound. Jesse explains the core idea behind diffusion in plain terms. You start with pure noise, and a neural network gradually cleans it up, step by step, until a realistic image emerges.From there, we talk about why diffusion has come to dominate so much of generative AI. Because the model builds an image gradually, you can guide it along the way, nudging the output toward what you actually want, refining details, or combining it with other controls. We also discuss the common critique that diffusion is slow and how the field has largely addressed it through new techniques.We zoom out to the bigger picture, too. Jesse shares his view on world models and whether diffusion is the right foundation for them. We talk about what makes a generative model genuinely good versus just good at gaming benchmarks, and why evaluating creativity and realism is so much harder than scoring a multiple-choice test.Timeline00:12 — Intro and welcoming Jesse00:47 — Why Jesse wrote the book, and who it's for03:29 — The three families of diffusion models, and why they're really one idea05:14 — What makes a good generative model07:39 — How do you even measure if a generated image is good08:59 — Why diffusion beats autoregressive models for images10:33 — Is diffusion still slow? How fast generation got fast11:12 — A simple intuition for what a "score" is14:12 — How the different flavors of diffusion connect under the hood14:42 — Diffusion for text and proteins17:12 — Consistency models and the push for one-step generation22:12 — Diffusion for world models: simulating reality in real time26:12 — Do world models need to understand language35:12 — Is diffusion the right tool, or just a convenient one38:12 — What benchmarks actually tell us, and what they miss46:12 — Closing thoughts and where to find the bookMusic:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

We talked with Christian Szegedy, co-inventor of Inception and Batch Normalization, founding scientist at xAI, now at Math Inc, about what it takes to build a frontier lab, and why he left xAI to work on formal mathematics. Christian thinks Lean and auto-formalization are the missing piece for trustworthy AI: a machine-checkable layer underneath all reasoning, where proofs are guaranteed correct without anyone having to read them.We got into his bet with François Chollet that AI will hit superhuman mathematician level by 2026, and what that actually unlocks beyond math itself: verified software instead of vibe-coded apps that break when you refactor, AI systems you can actually trust because their reasoning is checkable, and a path to handling protein folding, chemistry, and parts of biology with real guarantees instead of hand-waving. Christian also walked us through how Math Inc's Gauss system pulled off a proof in two weeks that human experts had estimated would take another year.We also covered xAI's first 12-person year, why Christian no longer buys the original batch normalization story, why he's sure transformers won't be the dominant architecture in five years, what mathematicians do in a world of cheap proofs, and his take on whether humanity will handle AI well. He distrusts humanity more than he distrusts AI.Timeline00:12 — Intros: Christian's background (Inception, Batch Norm, xAI, Math Inc)01:29 — Building a frontier lab from scratch: the first 12 people at xAI04:15 — Hiring for proven track records when 200K GPUs are at stake06:07 — Elon's "dependency graph" and balancing long-term vision with investor demos07:28 — Gauss formalizes the strong prime number theorem in 2 weeks12:25 — What "formalization" actually means (and why it's not what most people think)14:39 — Why Lean gives 100% certainty and why that matters for RL15:26 — ProofBridge and joint embeddings across mathematical subfields 18:07 — Does math formalization transfer to coding and other fields?21:44 — Can every domain be mathematized? 23:14 — Verified software, chip design, and why vibe-coded apps are dangerous26:35 — Scaling Mathlib by 100–1000x28:27 — Artisan formalizers vs. invisible machine-language formalists33:26 — Can verification generalize?45:19 — Revisiting Batch Norm: covariate shift, loss landscape, and what really happens48:22 — Is normalization even necessary? 50:10 — What's actually fundamental in modern AI architectures51:41 — Why Christian thinks transformers won't last 5 years52:38 — The 2026 superhuman AI mathematician bet55:15 — What's missing: better verification + a much larger formalized math repository56:13 — Lean vs. Coq vs. HOL Light -  does the proof assistant actually matter?59:26 — The role of mathematicians in 5–10 years1:02:00 — A human element to mathematics: Newton, Leibniz, and competitive proving1:03:25 — The telescope analogy: AI as the instrument that lets us see the math universe1:05:19 — Job apocalypse or Jevons paradox? 1:08:41 — Advice for students1:09:50 — Can we formally verify AI alignment? 1:11:52 — Closing thanksMusic:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

We sat down with Rao Kambhampati, a Professor of CS at Arizona State University and former President of AAAI, to talk about reasoning models: what they are, when they work, and when they break.Rao has been working on planning and decision-making since long before deep learning, which makes him one of the most grounded voices on what today's reasoning systems actually do. We start with definitions of what reasoning is, why planning is the hard subset of it, and what changed when systems like o1 and DeepSeek R1 moved the verifier from inference into post-training. From there we get into where these models generalize, where they don't, and why benchmarks can be misleading about both.A big chunk of the conversation is on chain-of-thought: what intermediate tokens are actually doing, why they help the model more than they help the reader, and what outcome-based RL does to whatever semantic content was there to begin with. We also cover world models and why Rao thinks the video-only framing is the wrong bet, the difference between agentic safety and existential risk, and what the planning community figured out decades ago that the LLM community keeps rediscovering.Timeline(00:12) Intros(01:32) Defining "reasoning" and the System 1 / System 2 framing(04:12) Blocksworld vs Sokoban, and non-ergodicity(06:42) Pre-o1: PlanBench and "LLMs are zero-shot X" papers(07:42) LLM-Modulo and moving the verifier into post-training(10:12) Is RL post-training reasoning, or case-based retrieval?(13:12) τ-Bench and benchmarks that avoid action interactions(14:12) OOD generalization and what we don't know about post-training data(19:02) Does it matter how they work if they answer the questions we care about?(21:27) Architecture lotteries and why no one tries different designs(23:42) Intermediate tokens and the "reduce thinking effort" cottage industry(26:12) The 30×30 maze experiment(27:42) Sokoban, NetHack, and Mystery Blocksworld(34:58) Stop Anthropomorphizing Intermediate Tokens — the swapped-trace experiment(46:12) Latent reasoning, Coconut, and why R0 beat R1(50:12) How outcome-based RL erodes CoT semantics(52:12) Dot-dot-dot and Anthropic's CoT monitoring paper(53:42) Safety: Hinton, Bengio, LeCun(57:12) Existential risk vs real safety work(59:42) World models, transition models, and video-only approaches(1:03:12) Why linguistic abstractions matter — pick and roll(1:05:42) What the planning community knew in 2005(1:08:12) Multi-agent LLMs(1:09:57) Closing thoughts: the bridge analogyMusic:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

In this episode, we hosted Zhuang Liu, Assistant Professor at Princeton and former researcher at Meta, for a conversation about what actually matters in modern AI and what turns out to be a historical accident.Zhuang is behind some of the most important papers in recent years (with more than 100k citations): ConvNeXt (showing ConvNets can match Transformers if you get the details right), Transformers Without Normalization (replacing LayerNorm with dynamic tanh), ImageBind, Eyes Wide Shut on CLIP's blind spots, the dataset bias work showing that even our biggest "diverse" datasets are still distinguishable from each other, and more.We got into whether architecture research is even worth doing anymore, what "good data" actually means, why vision is the natural bridge across modalities but language drove the adoption wave, whether we need per-lab RL environments or better continual learning, whether LLMs have world models (and for which tasks you'd need one), why LLM outputs carry fingerprints that survive paraphrasing, and where coding agents like Claude Code fit into research workflows today and where they still fall short.Timeline00:13 — Intro01:15 — ConvNeXt and whether architecture still matters06:35 — What actually drove the jump from GPT-1 to  GPT-308:24 — Setting the bar for architecture papers today11:14 — Dataset bias: why "diverse" datasets still aren't22:52 — What good data actually looks like26:49 — ImageBind and vision as the bridge across modalities29:09 — Why language drove the adoption wave, not vision32:24 — Eyes Wide Shut: CLIP's blind spots34:57 — RL environments, continual learning, and memory as the real bottleneck43:06 — Are inductive biases just historical accidents?44:30 — Do LLMs have world models?48:15 — Which tasks actually need a vision world model50:14 — Idiosyncrasy in LLMs: pre-training vs post-training fingerprints53:39 — The future of pre-training, mid-training, and post-training57:57 — Claude Code, Codex, and coding agents in research59:11 — Do we still need students in the age of autonomous research?1:04:19 — Transformers Without Normalization and the four pillars that survived1:06:53 — MetaMorph: Does generation help understanding, or the other way around?1:09:17 — WrapMusic:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

We talked with Sasha Rush, researcher at Cursor and professor at Cornell, about what it actually feels like to we in the heart of the AI revolution and build coding agents right now. Sasha shared how these systems are changing day-to-day work and how it feels to develop these systems.A big part of the conversation was about why coding has become such a powerful setting for these tools. We discussed what makes code different from other domains, why agents seem to work especially well there, and how much of today’s progress comes not just from better models, but from better ways of using them. Sasha also gave an inside look at how Cursor thinks about training coding models, long-running agents, context limits, bug finding, and the balance between autonomy and human oversight.We also talked about the broader shift happening in software engineering. Are developers moving to a higher level of abstraction? Is this just a phase where we “babysit” models, or the beginning of a deeper change in how software gets built? Sasha had a very thoughtful perspective here, including what he’s seeing from students, researchers, and engineers who are growing up native to these tools.More broadly, this episode is about what it means to do serious technical work in a moment when the tools are changing incredibly fast. Sasha brought both optimism and skepticism to the discussion, and that made this a really grounded conversation about where coding agents are today, what they are already surprisingly good at, and where all of this might be going next.Timeline00:00 Intro and Sasha joins us01:11 What “coding agents” actually mean02:34 Why coding became the breakout use case08:56 Long-running agents and autonomous workflows15:08 How these tools are changing the work of engineers17:15 Are people just babysitting models right now?22:11 How Cursor builds its coding models26:29 Rewards, training, and what makes agents work34:53 Memory, continual learning, and agent communication38:00 How context compaction works in practice41:29 Why coding agents recently got much better50:31 Refactoring, maintenance, and self-improving codebases52:16 Bug finding, oversight, and verification54:43 Will this pace of progress continue?56:42 Can this spread beyond coding?58:27 The future of Cursor and coding agents1:03:08 Model architectures beyond standard transformers1:05:37 World models, diffusion, and what may come nextMusic:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

How Denoising Secretly Powers Everything in AIPeyman Milanfar is a Distinguished Scientist at Google, leading its Computational Imaging team. He's a member of the National Academy of Engineering, an IEEE Fellow, and one of the key people behind the Pixel camera pipeline. Before Google, he was a professor at UC Santa Cruz for 15 years and helped build the imaging pipeline for Google Glass at Google X. Over 35,000 citations.Peyman makes a provocative case that denoising, long dismissed as a boring cleanup task, is actually one of the most fundamental operations in modern ML, on par with SGD and backprop. Knowing how to remove noise from a signal basically means you have a map of the manifold that signals live on, and that insight connects everything from classical inverse problems to diffusion models.We go from early patch-based denoisers to his 2010 "Is Denoising Dead?" paper, and then to the question that redirected his research: if denoising is nearly solved, what else can denoisers do? That led to Regularization by Denoising (RED), which, if you unroll it, looks a lot like a diffusion process, years before diffusion models existed. We also cover how his team shipped a one-step diffusion model on the Pixel phone for 100x ProRes Zoom, the perception-distortion-authenticity tradeoff in generative imaging, and a new paper on why diffusion models don't actually need noise conditioning. The conversation wraps with a debate on why language has dominated the AI spotlight while vision lags, and Peyman's argument that visual intelligence, grounded in physics and robotics, is coming next.Timeline0:00 Intro and Peyman's background1:22 Why denoising matters more than you think Sensor diversity and Tesla's vision-only bet15:04 BM3D and why it was secretly an MMSE estimator17:02 "Is Denoising Dead?" then what else can denoisers do?18:07 Plug-and-play methods and Regularization by Denoising (RED)26:18 Denoising, manifolds, and the compression connection28:12 Energy-based models vs. diffusion: "The Geometry of Noise"31:40 Natural gradient descent and why flow models work34:48 Gradient-free optimization and high-dimensional noise45:13 Image quality and the perception-distortion tradeoff48:39 Information theory, rate-distortion, and generative models52:57 Denoising vs. editing54:25 The changing role of theory57:07 Hobbyist tools vs. shipping consumer products59:40 Coding agents, vibe coding, and domain expertise1:05:00 Vision and more complex-dimensional signals1:09:31 Do models need to interact with the physical world?1:11:28 Continual learning and novelty-driven updates1:13:00 On-device learning and privacy1:15:01 Why has language dominated AI? Is vision next?1:17:14 How kids learn: vision first, language later1:19:36 Academia vs. industry1:22:28 10,000 citations vs. shipping to millions, why choose?Music:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

Yaroslav Bulatov helped build the AI era from the inside, as one of the earliest researchers at both OpenAI and Google Brain. Now he wants to tear it all down and start over. Modern deep learning, he argues, is up to 100x more wasteful than it needs to be  -  a Frankenstein of hacks designed for the wrong hardware. With a power wall approaching in two years, Yaroslav is leading an open effort to reinvent AI from scratch: no backprop, no legacy assumptions, just the benefit of hindsight and AI agents that compress decades of research into months. Along the way, we dig into why AGI is a "religious question," how a sales guy with no ML background became one of his most productive contributors, and why the Muon optimizer, one of the biggest recent breakthroughs, could only have been discovered by a non-expert.Timeline00:12 — Introduction and Yaroslav's background at OpenAI and Google Brain01:16 — Why deep learning isn't such a good idea02:03 — The three definitions of AGI: religious, financial, and vibes-based07:52 — The SAI framework: do we need the term AGI at all?10:58 — What matters more than AGI: efficiency and refactoring the AI stack13:28 — Jevons paradox and the coming energy wall14:49 — The recipe: replaying 70 years of AI with hindsight17:23 — Memory, energy, and gradient checkpointing18:34 — Why you can't just optimize the current stack (the recurrent laryngeal nerve analogy)21:05 — What a redesigned AI might look like: hierarchical message passing22:31 — Can a small team replicate decades of research?24:23 — Why non-experts outperform domain specialists27:42 — The GPT-2 benchmark: what success looks like29:01 — Ian Goodfellow, Theano, and the origins of TensorFlow30:12 — The Muon optimizer origin story and beating Google on ImageNet36:16 — AI coding agents for software engineering and research40:12 — 10-year outlook and the voice-first workflow42:23 — Why start with text over multimodality45:13 — Are AI labs like SSI on the right track?48:52 — Getting rid of backprop — and maybe math itself53:57 — The state of ML academia and NeurIPS culture56:41 — The Sutra group challenge: inventing better learning algorithmsMusic:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

We talk with Kyunghyun Cho, who is a Professor of Health Statistics and a Professor of Computer Science and Data Science at New York University, and a former Executive Director at Genentech, about why healthcare might be the most important and most difficult domain for AI to transform. Kyunghyun shares his vision for a future where patients own their own medical records, proposes a provocative idea for running continuous society-level clinical trials by having doctors "toss a coin" between plausible diagnoses, and explains why drug discovery's stage-wise pipeline has hit a wall that only end-to-end AI thinking can break through. We also get into GLP-1 drugs and why they're more mysterious than people realize, the brutal economics of antibiotic research, how language models trained across scientific literature and clinical data could compress 50 years of drug development into five, and what Kyunghyun would do with $10 billion (spoiler: buy a hospital network in the Midwest). We wrap up with a great discussion on the rise of professor-founded "neo-labs," why academia got spoiled during the deep learning boom, and an encouraging message for PhD students who feel lost right now.Timeline:(00:00) Intro and welcome(01:25) Why healthcare is uniquely hard(04:46) Who owns your medical records? — The case for patient-controlled data and tapping your phone at the doctor's office(06:43) Centralized vs. decentralized healthcare — comparing Israel, Korea, and the US(13:19) Why most existing health data isn't as useful as we think — selection bias and the lack of randomization(16:53) The "toss a coin" proposal — continuous clinical trials through automated randomization, and the surprising connection to LLM sampling.(23:07) Drug discovery's broken pipeline — why stage-wise optimization is failing, and we need end-to-end thinking(28:30) Why the current system is already failing society — wearables, preventive care, and the case for urgency(31:13) Allen's personal healthcare journey and the GLP-1 conversation(33:13) GLP-1 deep dive — 40 years from discovery to weight loss drugs, brain receptors, and embracing uncertainty(36:28) Why antibiotic R&D is "economic suicide" and how AI can help(42:52) Language models in the clinic and the lab — from clinical notes to back-propagating clinical outcomes, all the way to molecular design(48:04) Do you need domain expertise, or can you throw compute at it?(54:30) The $10 billion question — distributed GPU clouds and a patient-in-the-loop drug discovery system(58:28) Vertical scaling vs. horizontal scaling for healthcare AI(1:01:06) AI regulation — who's missing from the conversation and why regulation should follow deployment(1:06:52) Professors as founders and the "neo-lab" phenomenon — how Ilya cracked the code(1:11:18) Can neo-labs actually ship products? Why researchers should do research(1:13:09) Academia got spoiled — the deep learning anomaly is ending, and that's okay(1:16:07) Closing message — why it's a great time to be a PhD student and researcherMusic:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

In this episode, we talk with Stefano Ermon,  Stanford professor, co-founder & CEO of Inception AI, and co-inventor of DDIM, FlashAttention, DPO, and score-based/diffusion models, about why diffusion-based language models may overtake the autoregressive paradigm that dominates today's LLMs.We start with the fundamental topics, such as what diffusion models actually are, and why iterative refinement (starting from noise, progressively denoising) offers structural advantages over autoregressive generation.From there,  we dive into the technical core of diffusion LLMs. Stefano explains how discrete diffusion works on text, why masking is just one of many possible noise processes, and how the mathematics of score matching carries over from the continuous image setting with surprising elegance.A major theme is the inference advantage. Because diffusion models produce multiple tokens in parallel, they can be dramatically faster than autoregressive models at inference time. Stefano argues this fundamentally changes the cost-quality Pareto frontier, and becomes especially powerful in RL-based post-training.We also discuss Inception AI's Mercury II model, which Stefano describes as best-in-class for latency-constrained tasks like voice agents and code completion.In the final part, we get into broader questions  - why transformers work so well, research advice for PhD students, whether recursive self-improvement is imminent, the real state of AI coding tools, and Stefano's journey from academia to startup founder.TIMESTAMPS0:12 – Introduction1:08 – Origins of diffusion models: from GANs to score-based models in 20193:13 – Diffusion vs. autoregressive: the typewriter vs. editor analogy4:43 – Speed, creativity, and quality trade-offs between the two approaches7:44 – Temperature and sampling in diffusion LLMs — why it's more subtle than you think9:56 – Can diffusion LLMs scale? Inception AI and Gemini Diffusion as proof points11:50 – State space models and hybrid transformer architectures13:03 – Scaling laws for diffusion: pre-training, post-training, and test-time compute14:33 – Ecosystem and tooling: what transfers and what doesn't16:58 – From images to text: how discrete diffusion actually works19:59 – Theory vs. practice in deep learning21:50 – Loss functions and scoring rules for generative models23:12 – Mercury II and where diffusion LLMs already win26:20 – Creativity, slop, and output diversity in parallel generation28:43 – Hardware for diffusion models: why current GPUs favor autoregressive workloads30:56 – Optimization algorithms and managing technical risk at a startup32:46 – Why do transformers work so well?33:30 – Research advice for PhD students: focus on inference34:57 – Recursive self-improvement and AGI timelines35:56 – Will AI replace software engineers? Real-world experience at Inception37:54 – Professor vs. startup founder: different execution, similar mission39:56 – The founding story of Inception AI — from ICML Best Paper to company42:30 – The researcher-to-founder pipeline and big funding rounds45:02 – PhD vs. industry in 2026: the widening financial gap47:30 – The industry in 5-10 years: Stefano's outlookMusic:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

Naomi Saphra, Kempner Research Fellow at Harvard and incoming Assistant Professor at Boston University, joins us to explain why you can't do interpretability without understanding training dynamics,  in the same way you can't do biology without evolution.Naomi argues that many structures researchers find inside trained models are vestigial, they mattered early in training but are meaningless by the end. Grokking is one case of a broader phenomenon: models go through multiple consecutive phase transitions during training, driven by symmetry breaking and head specialization, but the smooth loss curve hides all of it. We talk about why training is nothing like human learning, and why our intuitions about what's hard for models are consistently wrong  -  code in pretraining helps language reasoning, tokenization drives behaviors people attribute to deeper cognition, and language already encodes everything humans care about. We also get into why SAEs are basically topic models, the Platonic representation hypothesis, using AI to decode animal communication, and why non-determinism across training runs is a real problem that RL and MoE might be making worse.Timeline: (00:12) Introduction and guest welcome (01:01) Why training dynamics matter - the evolutionary biology analogy (03:05) Jennifer Aniston neurons and the danger of biological parallels (04:48) What is grokking and why it's one instance of a broader phenomenon (08:25) Phase transitions, symmetry breaking, and head specialization (11:53) Double descent, overfitting, and the death of classical train-test splits (15:10) Training is nothing like learning (16:08) Scaling axes - data, model size, compute, and why they're not interchangeable (19:29) Data quality, code as reasoning fuel, and GPT-2's real contribution (20:43) Multilingual models and the interlingua hypothesis (25:58) The Platonic representation hypothesis and why image classification was always multimodal (29:12) Sparse autoencoders, interpretability, and Marr's levels (37:32) Can we ever truly understand what models know? (43:59) The language modality chauvinist argument (51:55) Vision, redundancy, and self-supervised learning (57:18) World models - measurable capabilities over philosophical definitions (1:00:14) Is coding really a solved task? (1:04:18) Non-determinism, scaling laws, and why one training run isn't enough (1:10:12) Naomi's new lab at BU and recruitingMusic:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0. Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

Stefano Soatto, VP for AI at AWS and Professor at UCLA, the person responsible for agentic AI at AWS, joins us to explain why building reliable AI agents is fundamentally a control theory problem.Stefano sees LLMs as stochastic dynamical systems that need to be controlled, not just prompted. He introduces "strands coding," a new framework AWS is building that sits between vibe coding and spec coding, you write a skeleton with AI functions constrained by pre- and post-conditions, verifying intent before a single line of code is generated. The surprising part: even as AI coding adoption goes up, developer trust in the output is going down.We go deep into the philosophy of models and the world. Stefano argues that the dichotomy between "language models" and "world models" doesn't really exist, where a reasoning engine trained on rich enough data is a world model. He walks us through why naive realism is indefensible, how reverse diffusion was originally intended to show that models can't be identical to reality, and why that matters now.We also discuss three types of information, Shannon, algorithmic, and conceptual, and why algorithmic information is the one that actually matters to agents. Synthetic data doesn't add Shannon information, but it adds algorithmic information, which is why it works. Intelligence isn't about scaling to Solomonov's universal induction; it's about learning to solve new problems fast.Takeaways:Vibe coding is local feedback control with high cognitive load; spec coding is open-loop global control with silent failures, neither scales well alone.Trust in AI-generated code is declining even as adoption rises.The distinction between next-token prediction and world model is mostly nomenclature - reasoning engines operating on multimodal data are world models.Algorithmic information, not Shannon information, is what matters in the agentic setting.Intelligence isn't minimizing inference uncertainty - it's minimizing time to solve unforeseen tasks.The intent gap between user and model cannot be fully automated or delegated.Timeline(00:13) Introduction and guest welcome(01:12) How the agentic era changed machine learning(06:11) Vibe coding one year later(07:23) Vibe vs. spec vs. strands coding(14:30) Why English is not a programming language(16:36) Constrained generation and agent choreography(20:44) Diffusion models vs. autoregressive models (25:59) The platonic representation hypothesis and naive realism(31:14) Synthetic data and the information bottleneck(36:22) Three types of information: Shannon, algorithmic, conceptual(38:47) Scaling laws and Solomonov induction(42:14) World models and the Goethian vs. Marrian approach(49:00) Encoding vs. generation and JEPA-style training(55:50) Are language models already world models?(59:13) Closing thoughts on trust, education, and responsibility.Music:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0. Changes: trimmedAboutThe Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

Tanishq Abraham, CEO and co-founder of Sophont.ai, joins us to talk about building foundation models specifically for medicine.Sophont is trying to be something like an OpenAI or Anthropic but for healthcare  - training models across pathology, neuroimaging, and clinical text, to eventually fuse them into one multimodal system. The surprising part: their pathology model trained on 12,000 public slides performs on par with models trained on millions of private ones. Data quality beats data quantity.We talk about what actually excites Tanishq, which is not replacing doctors, but finding things doctors can't see. AI predicting gene mutations from a tissue slide, or cardiovascular risk from an eye scan.We also talk about the regulation and how the picture is less scary than people assume. Text-based clinical decision support can ship without FDA approval. Pharma partnerships offer near-term impact. The five-to-ten-year timeline people fear is really about drug discovery, not all of medical AI.Takeaways:The real promise of medical AI is finding hidden signals in existing data, not just automating doctorsSmall, curated public datasets can rival massive private onesMultimodal fusion is the goal, but you need strong individual encoders firstAI research itself might get automated sooner than biology or chemistryFDA regulation has more flexibility than most people thinkTimeline(00:12) Introduction and guest welcome(02:32) Anthropic's ad about ChatGPT ads(07:26) XAI merging into SpaceX(13:32) Vibe coding one year later(17:00) Claude Code and agentic workflows(21:52) Can AI automate AI research?(26:57) What is medical AI(31:06) Sofont as a frontier medical AI lab(33:52) Public vs. private data - 12K slides vs. millions(36:43) Domain expertise vs. scaling(41:54) Cancer, diabetes, and personal stakes(47:52) Classification vs. prediction in medicine(50:36) When doctors disagree(54:43) Quackery and AI(57:15) Uncertainty in medical AI(1:03:11) Will AI replace doctors?(1:07:24) Self-supervised learning on sleep data(1:10:10) Aligning modalities(1:13:17) FDA regulation(1:22:28) Closing Music:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.Changes: trimmedAbout The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

Anastasios Angelopoulos, Co-Founder and CEO of Arena AI (formerly LMArena), joins us to talk about why static benchmarks are failing, how human preference data actually works under the hood, and what it takes to be the "gold standard" of AI evaluation.Anastasios sits at a fascinating intersection -   a theoretical statistician running the platform that every major lab watches when they release a model. We talk about the messiness of AI-generated code slop (yes, he hides Claude's commits too), then dig into the statistical machinery that powers Arena's leaderboards and why getting evaluation right is harder than most people think.We explore why style control is both necessary and philosophically tricky, where you can regress away markdown headers and response length, but separating style from substance is a genuinely unsolved causal inference problem. We also get into why users are surprisingly good judges of model quality, how Arena serves as a pre-release testing ground for labs shipping stealth models under codenames, and whether the fragmentation of the AI market (Anthropic going enterprise, OpenAI going consumer, everyone going multimodal) is actually a feature, not a bug. Plus, we discuss the role of rigorous statistics in the age of "just run it again," why structured decoding can hurt model performance, and what Arena's 2026 roadmap looks like.Timeline:(00:12) Introduction and Anastasios's Background(00:55) What Arena Does and Why Static Benchmarks Aren't Enough(02:26) Coverage of Use Cases - Is There Enough?(04:22) Style Control and the Bradley-Terry Methodology(08:35) Can You Actually Separate Style from Substance?(10:24) Measuring Slop - And the Anti-Slop Paper Plug(11:52) Can Users Judge Factual Correctness?(13:31) Tool Use and Agentic Evaluation on Arena(14:14) Intermediate Feedback Signals Beyond Final Preference(15:30) Tool Calling Accuracy and Code Arena(17:42) AI-Generated Code Slop and Hiding Claude's Commits(19:49) Do We Need Separate Code Streams for Humans and LLMs?(20:01) RL Flywheels and Arena's Preference Data(21:16) Focus as a Startup - Being the Evaluation Company(22:16) Structured vs. Unconstrained Generation(25:00) The Role of Rigorous Statistics in the Age of AI(29:23) LLM Sampling Parameters and Evaluation Complexity(30:56) Model Versioning and the Frequentist Approach to Fairness(32:12) Quantization and Its Effects on Model Quality(33:10) Pre-Release Testing and Stealth Models (34:23) Transparency - What to Share with the Public vs. Labs(36:27) When Winning Models Don't Get Released(36:59) Why Users Keep Coming Back to Arena(38:19) Market Fragmentation and Arena's Future Value(39:37) Custom Evaluation Frameworks for Specific Users(40:03) Arena's 2026 Roadmap - Science, Methodology, and New Paradigms(42:15) The Economics of Free Inference(43:13) Hiring and Closing ThoughtsMusic:"Kid Kodi" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0."Palms Down" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0.Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

Fred Sala, Assistant Professor at UW-Madison and Chief Scientist at Snorkel AI, joins us to talk about why personalization might be the next frontier for LLMs, why data still matters more than architecture, and how weak supervision refuses to die.Fred sits at a rare intersection,  building the theory of data-centric AI in academia while shipping it to enterprise clients at Snorkel. We talk about the chaos of OpenClaw (the personal AI assistant that's getting people hacked the old-fashioned way, via open ports), then focus on one of the most important questions: how do you make a model truly yours?We dig into why prompting your preferences doesn't scale, why even LoRA might be too expensive for per-user personalization, and why activation steering methods like REFT could be the sweet spot. We also explore self-distillation for continual learning, the unsolved problem of building realistic personas for evaluation, and Fred's take on the data vs. architecture debate (spoiler: data is still undervalued). Plus, we discuss why the internet's "Ouroboros effect" might not doom pre-training as much as people fear, and what happens when models become smarter than the humans who generate their training data.Takeaways:Personalization requires ultra-efficient methods - even one LoRA per user is probably too expensive. Activation steering is the promising middle ground.The "pink elephant problem" makes prompt-based personalization fundamentally limited - telling a model what not to do often makes it do it more.Self-distillation can enable on-policy continual learning without expensive RL reward functions, dramatically reducing catastrophic forgetting.Data is still undervalued relative to architecture and compute, especially high-quality post-training data, which is actually improving, not getting worse.Weak supervision principles are alive and well inside modern LLM data pipelines, even if people don't call it that anymore.Timeline:(00:13) Introduction and Fred's Background(00:39) OpenClaw — The Personal AI Assistant Taking Over Macs(03:43) Agent Security Risks and the Privacy Problem(05:13) Cloud Code, Permissions, and Living Dangerously(07:47) AI Social Media and Agents Talking to Each Other(08:56) AI Persuasion and Competitive Debate(09:51) Self-Distillation for Continual Learning(12:43) What Does Continual Learning Actually Mean?(14:12) Updating Weights on the Fly — A Grand Challenge(15:09) The Personalization Problem — Motivation and Use Cases(17:41) The Pink Elephant Problem with Prompt-Based Personalization(19:58) Taxonomy of Personalization — Preferences vs. Tone vs. Style(21:31) Activation Steering, REFT, and Parameter-Efficient Fine-Tuning(27:00) Evaluating Personalization — Benchmarks and Personas(31:14) Unlearning and Un-Personalization(31:51) Cultural Alignment as Group-Level Personalization(41:00) Can LLM Personas Replace Surveys and Polling?(44:32) Is Continued Pre-Training Still Relevant?(46:28) Data vs. Architecture — What Matters More?(52:25) Multi-Epoch Training — Is It Over?(54:53) What Makes Good Data? Matching Real-World Usage(59:23) Decomposing Uncertainty for Better Data Selection(1:01:52) Mapping Human Difficulty to Model Difficulty(1:04:49) Scaling Small Ideas — From Academic Proof to Frontier Models(1:12:01) What Happens When Models Surpass Human Training Data?(1:15:24) Closing ThoughtsMusic:"Kid Kodi" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0."Palms Down" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0.Changes: trimmed

Bayan Bruss, VP of Applied AI at Capital One, joins us to talk about building AI systems that can make autonomous financial decisions, and why money might be the hardest problem in machine learning.Bayan leads Capital One's AI Foundations team, where they're working toward a destination most people don't associate with banking: getting AI systems to perceive financial ecosystems, form beliefs about the future, and take actions based on those beliefs. It's a framework that sounds simple until you realize you're asking a model to predict whether someone will pay back a loan over 30 years while the world changes around them.We get into why LLMs are a bad fit for ingesting 5,000 credit card transactions, why synthetic data works surprisingly well for time series, and the tension between end-to-end learning and regulatory requirements that demand you know exactly what your model learned. We also discuss reasoning in language vs. in latent space - if you wouldn't trust a self-driving car that translated images to words before deciding to turn, should you trust a financial system that does all its reasoning in token space?Takeaways:Money is a behavioral science problem - AI in finance requires understanding people, not just numbers.Foundation models pre-trained on web text don't outperform purpose-built models for financial tasks. You're better off building a standalone encoder for financial data.Synthetic data works surprisingly well for time series - possibly because real-world time series lives on a simpler manifold than we assume.Explainability in ML is fundamentally unsatisfying because people want causality from non-causal models.Financial AI needs world models that can imagine alternative futures, not just fit historical data.Timeline:(00:24) Introduction and Bayan's Background(00:42) Claude Code, Vibe Coding - Hype or AGI?(05:59) The Future of Software Engineering and Abstraction(11:20) Abstraction Layers and Karpathy's Take(13:54) Hamming, Kuhn, and Scientific Revolutions in AI(19:24) Stack Overflow's Decline and Proof of Humanity(23:07) Why We Still Trust Humans Over LLMs(30:45) Deep Dive: AI in Banking and Consumer Finance(34:17) Are Markets Efficient? Behavioral Economics vs. Classical Views(37:14) The Components of a Financial Decision: Perception, Belief, Action(42:15) Protected Variables, Proxy Features, and Fairness in Lending(45:05) Explainability: Roller Skating on Marbles(47:55) Sparse Autoencoders, Interpretability, and Turtles All the Way Down(51:57) Foundation Models for Finance — Web Text vs. Purpose-Built(53:09) Time Series, Synthetic Data, and TabPFN(59:44) Feeding Tabular Data to VLMs - Graphs Beat Raw Numbers(1:03:35) Reasoning in Language vs. Latent Space(1:08:24) Is Language the Optimal Representation? Chinese Compression and Information Density(1:13:37) Personalization and Predicting Human Behavior(1:21:36) World Models, Uncertainty, and Professional Worrying(1:24:07) Prediction Markets and Insider Betting(1:26:33) Can LLMs Predict Stocks?(1:29:11) Multi-Agent Systems for Financial DecisionsMusic:"Kid Kodi" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0."Palms Down" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0. Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

David Mezzetti, creator of TxtAI, joins us to talk about building open source AI frameworks as a solo developer - and why local-first AI still matters in the age of API-everything.David's path from running a 50-person IT company through acquisition to building one of the most well-regarded AI orchestration libraries tells you how sometimes constraints breed better design. TextAI started during COVID when he was doing coronavirus literature research and realized semantic search could transform how we find information.We get into the evolution of the AI framework landscape - from the early days of vector embeddings to RAG to LLM orchestration. David was initially stubborn about not supporting OpenAI's API, wanting to keep everything local. He admits that probably cost him some early traction compared to LangChain, but it also shaped TextAI's philosophy: you shouldn't need permission to build with AI.We also talk about small models and some genuinely practical insights: a 20-million parameter model running on CPU might be all you need. On the future of coding with AI, David's come around on "vibe coding" and notes that well-documented frameworks with lots of examples are perfectly positioned for this new world.Takeaways:Local-first AI gives you control, reproducibility, and often better performance for your domainSmall models (even 20M parameters) can solve real problems on CPUGood documentation and examples make your framework AI-coding friendlyOpen source should mean actually contributing - not just publishing codeSolo developers can compete by staying focused and being willing to evolveTimeline:(00:14) Introduction and David's Background(07:44) TextAI History and Evolution(12:04) Framework Landscape: LangChain, LlamaIndex, Haystack(15:16) Can AI Re-implement Frameworks?(24:14) API Specs: OpenAI vs Anthropic(26:46) Running an Open Source Consulting Business(32:51) Origin Story: COVID, Kaggle, and Medical Literature(43:08) Open Source Philosophy and Giving Back(47:16) Ethics of Local AI and Developer Freedom(01:06:44) Human in the Loop and AI-Generated Code(01:09:31) The Future of Work and AutomationMusic:"Kid Kodi" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0."Palms Down" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0. Changes: trimmedAbout:The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

Cody Blakeney from Datology AI joins us to talk about data curation - the unglamorous but critical work of figuring out what to actually train models on.Cody's path from writing CUDA kernels to spending his days staring at weird internet text tells you something important: data quality can account for half or more of a model's final performance. That's on par with major architectural breakthroughs.We get into the differences between pre-training, mid-training, and post-training data. Mid-training in particular has become a key technique for squeezing value out of rare, high-quality datasets. Cody's team stumbled onto it while solving a practical problem: how do you figure out if a 5-billion-token dataset is actually useful when you can't afford hundreds of experimental runs?We also talk about data filtering and some genuinely surprising findings: the documents that make the best training data are often short and dense with information. Those nicely written blog posts with personal anecdotes? Turns out models don't learn as well from them.On synthetic data, Cody thinks pre-training is still in its early days, where most techniques are variations on a few core ideas, but there's huge potential. He's excited about connecting RL failures back to mid-training: when models fail at tasks, use that signal to generate targeted training data.Takeaways:Data work is high-leverage but underappreciatedMid-training helps extract signal from small, valuable datasetsGood filters favor dense, factual text over polished prose.Synthetic data for pre-training works surprisingly well, but remains primitive.Optimal data mixtures depend on model scale, where smaller models need more aggressive distribution shifts.Timeline(00:12) Introduction to Data Correlation in LLMs(05:14) The Importance of Data Quality(10:15) Pre-training vs Post-training Data(15:22) Strategies for Effective Data Utilization(20:15) Benchmarking and Model Evaluation(28:28) Maximizing Perplexity and Coherence(30:27) Measuring Quality in Data(32:56) The Role of Filters in Data Selection(34:19) Understanding High-Quality Data(39:15) Mid-Training and Its Importance(46:51) Future of Data Sources(48:13) Synthetic Data's Role in Pre-Training(53:10) Creating Effective Synthetic Data(57:39) The Debate on Pure Synthetic Data(01:00:25) Navigating AI Training and Legal Challenges(01:02:34) The Controversy of AI in the Art Community(01:05:29) Exploring Synthetic Data and Its Efficiency(01:11:21) The Future of Domain-Specific vs. General Models(01:22:06) Bias in Pre-trained Models and Data Selection(01:28:27) The Potential of Synthetic Data Over Human DataMusic:"Kid Kodi" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0."Palms Down" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0.Changes: trimmedAboutThe Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

Guest: Niloofar Mireshghallah (Incoming Assistant Professor at CMU, Member of Technical Staff at Humans and AI)In this episode, we dive into AI privacy, frontier model capabilities, and why academia still matters.We kick off by discussing GPT-5.2 and whether models rely more on parametric knowledge or context. Niloofar shares how reasoning models actually defer to context, even accepting obviously false information to "roll with it."On privacy, Niloofar challenges conventional wisdom: memorization isn't the problem anymore. The real threats are aggregation attacks (finding someone's pet name in HTML metadata), inference attacks (models are expert geoguessers), and input-output leakage in agentic workflows.We also explore linguistic colonialism in AI, or how models fail for non-English languages, sometimes inventing cultural traditions.The episode wraps with a call for researchers to tackle problems industry ignores: AI for science, education tools that preserve the struggle of learning, and privacy-preserving collaboration between small local models and large commercial ones.Timeline[0:00] Intro[1:03] GPT-5.2 first impressions and skepticism about the data cutoff claims[4:17] Parametric vs. context memory—when do models trust training vs. the prompt?[9:28] The messy problem of memory, weights, and online learning[16:12] Tool use changes model behavior in unexpected ways[17:15] OpenAI's "Advances in Sciences" paper and human-AI collaboration[24:17] Why deep research is getting less useful[28:17] Pre-training vs. post-training—which matters more?[30:35] Non-English languages and AI failures[33:23] Hilarious Farsi bugs: "I'll get back to you in a few days" and invented traditions[37:56] Linguistic colonialism—ChatGPT changed how we write[41:20] Why memorization isn't the real privacy threat[47:14] The three actual privacy problems: inference, aggregation, input-output leakage[54:33] Deep research stalking experiment—finding a cat's name in HTML[1:01:13] Privacy solutions for agentic systems[1:03:23] What Niloofar's excited about: AI for scientists, small models, niche problems[1:08:31] AI for education without killing the learning process[1:09:15] Closing: underrated life advice on health and sustainable habitsMusic:"Kid Kodi" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0."Palms Down" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0.Changes: trimmedAboutThe Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

Yann LeCun – Why LLMs Will Never Get Us to AGI"The path to superintelligence - just train up the LLMs, train on more synthetic data, hire thousands of people to school your system in post-training, invent new tweaks on RL-I think is complete bullshit. It's just never going to work."After 12 years at Meta, Turing Award winner Yann LeCun is betting his legacy on a radically different vision of AI. In this conversation, he explains why Silicon Valley's obsession with scaling language models is a dead end, why the hardest problem in AI is reaching dog-level intelligence (not human-level), and why his new company AMI is building world models that predict in abstract representation space rather than generating pixels.Timestamps(00:00:14) – Intro and welcome(00:01:12) – AMI: Why start a company now?(00:04:46) – Will AMI do research in the open?(00:06:44) – World models vs LLMs(00:09:44) – History of self-supervised learning(00:16:55) – Siamese networks and contrastive learning(00:25:14) – JEPA and learning in representation space(00:30:14) – Abstraction hierarchies in physics and AI(00:34:01) – World models as abstract simulators(00:38:14) – Object permanence and learning basic physics(00:40:35) – Game AI: Why NetHack is still impossible(00:44:22) – Moravec's Paradox and chess(00:55:14) – AI safety by construction, not fine-tuning(01:02:52) – Constrained generation techniques(01:04:20) – Meta's reorganization and FAIR's future(01:07:31) – SSI, Physical Intelligence, and Wayve(01:10:14) – Silicon Valley's "LLM-pilled" monoculture(01:15:56) – China vs US: The open source paradox(01:18:14) – Why start a company at 65?(01:25:14) – The AGI hype cycle has happened 6 times before(01:33:18) – Family and personal background(01:36:13) – Career advice: Learn things with a long shelf life(01:40:14) – Neuroscience and machine learning connections(01:48:17) – Continual learning: Is catastrophic forgetting solved?Music:"Kid Kodi" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0."Palms Down" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0.Changes: trimmedAboutThe Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.

Atlas Wang (UT Austin faculty, XTX Research Director) joins us to explore two fascinating frontiers: the foundations of symbolic AI and the practical challenges of building AI systems for quantitative finance.On the symbolic AI side, Atlas shares his recent work proving that neural networks can learn symbolic equations through gradient descent, a surprising result given that gradient descent is continuous while symbolic structures are discrete. We talked about why neural nets learn clean, compositional mathematical structures at all, what the mathematical tools involved are, and the broader implications for understanding reasoning in AI systems.The conversation then turns to neuro-symbolic approaches in practice: agents that discover rules through continued learning, propose them symbolically, verify them against domain-specific checkers, and refine their understanding.On the finance side, Atlas pulls back the curtain on what AI research looks like at a high-frequency trading firm. The core problem sounds simple (predict future prices from past data). Still, the challenge is extreme: markets are dominated by noise, predictions hover near zero correlation, and success means eking out tiny margins across astronomical numbers of trades. He explains why synthetic data techniques that work elsewhere don't translate easily, and why XTX is building time series foundation models rather than adapting language models.We also discuss the convergence of hiring between frontier AI labs and quantitative finance, and why this is an exceptional moment for ML researchers to consider the finance industry.Links:Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation for Neurosymbolic Reasoning - arxiv.org/abs/2506.21797Atlas website - https://www.vita-group.space/Guest: Atlas Wang (UT Austin / XTX)Hosts: Ravid Shwartz-Ziv & Allen RoushMusic: “Kid Kodi” — Blue Dot Sessions. Source: Free Music Archive. Licensed CC BY-NC 4.0.

In this episode, we hosted Judah Goldfeder, a PhD candidate at Columbia University and student researcher at Google, to discuss robotics, reproducibility in ML, and smart buildings.Key topics covered:Robotics challenges: We discussed why robotics remains harder than many expected, compared to LLMs. The real world is unpredictable and unforgiving, and mistakes have physical consequences. Sim-to-real transfer remains a major bottleneck because simulators are tedious to configure accurately for each robot and environment. Unlike text, robotics lacks foundation models, partly due to limited clean, annotated datasets and the difficulty of collecting diverse real-world data.Reproducibility crisis: We discussed how self-reported benchmarks can lead to p-hacking and irreproducible results. Centralized evaluation systems (such as Kaggle or ImageNet challenges), where researchers submit algorithms for testing on hidden test sets, seem to drive faster progress.Smart buildings: Judah's work at Google focuses on using ML to optimize HVAC systems, potentially reducing energy costs and carbon emissions significantly. The challenge is that every building is different. It makes the simulation configuration extremely labor-intensive. Generative AI could help by automating the process of converting floor plans or images into accurate building simulations.Links:Judah website - https://judahgoldfeder.com/Music:"Kid Kodi" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0."Palms Down" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0.Changes: trimmed

In this episode, we talk with Will Brown, a research lead at Prime Intellect, about his journey into reinforcement learning (RL) and multi-agent systems, exploring their theoretical foundations and practical applications. We discuss the importance of RL in the current LLMs pipeline and the challenges it faces. We also discuss applying agentic workflows to real-world applications and the ongoing evolution of AI development.Chapters00:00 Introduction to Reinforcement Learning and Will's Journey03:10 Theoretical Foundations of Multi-Agent Systems06:09 Transitioning from Theory to Practical Applications09:01 The Role of Game Theory in AI11:55 Exploring the Complexity of Games and AI14:56 Optimization Techniques in Reinforcement Learning17:58 The Evolution of RL in LLMs21:04 Challenges and Opportunities in RL for LLMs23:56 Key Components for Successful RL Implementation27:00 Future Directions in Reinforcement Learning36:29 Exploring Agentic Reinforcement Learning Paradigms38:45 The Role of Intermediate Results in RL41:16 Multi-Agent Systems: Challenges and Opportunities45:08 Distributed Environments and Decentralized RL49:31 Prompt Optimization Techniques in RL52:25 Statistical Rigor in Evaluations55:49 Future Directions in Reinforcement Learning59:50 Task-Specific Models vs. General Models01:02:04 Insights on Random Verifiers and Learning Dynamics01:04:39 Real-World Applications of RL and Evaluation Challenges01:05:58 Prime RL Framework: Goals and Trade-offs01:10:38 Open Source vs. Closed Source Models01:13:08 Continuous Learning and Knowledge ImprovementMusic:"Kid Kodi" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0."Palms Down" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0.Changes: trimmed

In this episode, we discuss various topics in AI, including the challenges of the conference review process, the capabilities of Kimi K2 thinking, the advancements in TPU technology, the significance of real-world data in robotics, and recent innovations in AI research. We also talk about the cool "Chain of Thought Hijacking" paper, how to use simple ideas to scale RL, and the implications of the Cosmos project, which aims to enable autonomous scientific discovery through AI.Papers and links:Chain-of-Thought Hijacking - https://arxiv.org/pdf/2510.26418Kosmos: An AI Scientist for Autonomous Discovery - https://t.co/9pCr6AUXAeJustRL: Scaling a 1.5B LLM with a Simple RL Recipe - https://relieved-cafe-fe1.notion.site/JustRL-Scaling-a-1-5B-LLM-with-a-Simple-RL-Recipe-24f6198b0b6b80e48e74f519bfdaf0a8Chapters00:00 Navigating the Peer Review Process04:17 Kimi K2 Thinking: A New Era in AI12:27 The Future of Tool Calls in AI17:12 Exploring Google's New TPUs22:04 The Importance of Real-World Data in Robotics28:10 World Models: The Next Frontier in AI31:36 Nvidia's Dominance in AI Partnerships32:08 Exploring Recent AI Research Papers37:46 Chain of Thought Hijacking: A New Threat43:05 Simplifying Reinforcement Learning Training54:03 Cosmos: AI for Autonomous Scientific DiscoveryMusic:"Kid Kodi" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0."Palms Down" — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0.Changes: trimmed

In this episode, we sit down with Alex Alemi, an AI researcher at Anthropic (previously at Google Brain and Disney), to explore the powerful framework of the information bottleneck and its profound implications for modern machine learning.We break down what the information bottleneck really means, a principled approach to retaining only the most informative parts of data while compressing away the irrelevant. We discuss why compression is still important in our era of big data, how it prevents overfitting, and why it's essential for building models that generalize well.We also dive into scaling laws: why they matter, what we can learn from them, and what they tell us about the future of AI research.Papers and links:Alex's website - https://www.alexalemi.com/Scaling exponents across parameterizations and optimizers - https://arxiv.org/abs/2407.05872Deep Variational Information Bottleneck - https://arxiv.org/abs/1612.00410Layer by Layer: Uncovering Hidden Representations in Language Models - https://arxiv.org/abs/2502.02013Information in Infinite Ensembles of Infinitely-Wide Neural Networks - https://proceedings.mlr.press/v118/shwartz-ziv20a.htmlMusic:“Kid Kodi” — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0.“Palms Down” — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0.Changes: trimmed

In this episode, we talked about AI news and recent papers. We explored the complexities of using AI models in healthcare (the Nature Medicine paper on GPT-5's fragile intelligence in medical contexts). We discussed the delicate balance between leveraging LLMs as powerful research tools and the risks of over-reliance, touching on issues such as hallucinations, medical disagreements among practitioners, and the need for better education on responsible AI use in healthcare.We also talked about Stanford's "Cartridges" paper, which presents an innovative approach to long-context language models. The paper tackles the expensive computational costs of billion-token context windows by compressing KV caches through a clever "self-study" method using synthetic question-answer pairs and context distillation. We discussed the implications for personalization, composability, and making long-context models more practical.Additionally, we explored the "Continuous Autoregressive Language Models" paper and touched on insights from the Smol Training Playbook.Papers discussed:The fragile intelligence of GPT-5 in medicine: https://www.nature.com/articles/s41591-025-04008-8Cartridges: Lightweight and general-purpose long context representations via self-study: https://arxiv.org/abs/2506.06266Continuous Autoregressive Language Models: https://arxiv.org/abs/2510.27688The Smol Training Playbook: https://huggingface.co/spaces/HuggingFaceTB/smol-training-playbookMusic:“Kid Kodi” — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0.“Palms Down” — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0.Changes: trimmedThis is an experimental format for us, just news and papers without a guest interview. Let us know what you think!

In this episode, we host Jonas Geiping from ELLIS Institute & Max-Planck Institute for Intelligent Systems, Tübingen AI Center, Germany. We talked about his broad research on Recurrent-Depth Models and latent reasoning in large language models (LLMs). We talked about what these models can and can't do, what are the challenges and next breakthroughs in the field, world models, and the future of developing better models. We also talked about safety and interpretability, and the role of scaling laws in AI development.Chapters00:00 Introduction and Guest Introduction01:03 Peer Review in Preprint Servers06:57 New Developments in Coding Models09:34 Open Source Models in Europe11:00 Dynamic Layers in LLMs26:05 Training Playbook Insights30:05 Recurrent Depth Models and Reasoning Tasks43:59 Exploring Recursive Reasoning Models46:46 The Role of World Models in AI48:41 Innovations in AI Training and Simulation50:39 The Promise of Recurrent Depth Models52:34 Navigating the Future of AI Algorithms54:44 The Bitter Lesson of AI Development59:11 Advising the Next Generation of Researchers01:06:42 Safety and Interpretability in AI Models01:10:46 Scaling Laws and Their Implications01:16:19 The Role of PhDs in AI ResearchLinks and paper:Jonas' website - https://jonasgeiping.github.io/Scaling up test-time compute with latent reasoning: A recurrent depth approach - https://arxiv.org/abs/2502.05171The Smol Training Playbook: The Secrets to Building World-Class LLMs - https://huggingface.co/spaces/HuggingFaceTB/smol-training-playbookVaultGemma: A Differentially Private Gemma Model - https://arxiv.org/abs/2510.15001Music:“Kid Kodi” — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0.“Palms Down” — Blue Dot Sessions — via Free Music Archive — CC BY-NC 4.0.Changes: trimmed

In this episode of the Information Bottleneck Podcast, we host Jack Morris, a PhD student at Cornell, to discuss adversarial examples (Jack created TextAttack, the first software package for LLM jailbreaking), the Platonic representation hypothesis, the implications of inversion techniques, and the role of compression in language models.Links:Jack's Website - https://jxmo.io/TextAttack - https://arxiv.org/abs/2005.05909How much do language models memorize? https://arxiv.org/abs/2505.24832DeepSeek OCR - https://www.arxiv.org/abs/2510.18234Chapters:00:00 Introduction and AI News Highlights04:53 The Importance of Fine-Tuning Models10:01 Challenges in Open Source AI Models14:34 The Future of Model Scaling and Sparsity19:39 Exploring Model Routing and User Experience24:34 Jack's Research: Text Attack and Adversarial Examples29:33 The Platonic Representation Hypothesis34:23 Implications of Inversion and Security in AI39:20 The Role of Compression in Language Models44:10 Future Directions in AI Research and Personalization

In this episode we talk with Randall Balestriero, an assistant professor at Brown University. We discuss the potential and challenges of Joint Embedding Predictive Architectures (JEPA). We explore the concept of JEPA, which aims to learn good data representations without reconstruction-based learning. We talk about the importance of understanding and compressing irrelevant details, the role of prediction tasks, and the challenges of preventing collapse.

In this episode, we talked with Michael Bronstein, a professor of AI at the University of Oxford and a scientific director at AITHYRA, about the fascinating world of geometric deep learning. We explored how understanding the geometric structures in data can enhance the efficiency and accuracy of AI models. Michael shared insights on the limitations of small neural networks and the ongoing debate about the role of scaling in AI. We also talked about the future in scientific discovery, and the potential impact on fields like drug design and mathematics

In this episode we host Tal Kachman, an assistant professor at Radboud University, to explore the fascinating intersection of artificial intelligence and natural sciences. Prof. Kachman's research focuses on multiagent interaction, complex systems, and reinforcement learning. We dive deep into how AI is revolutionizing materials discovery, chemical dynamics modeling, and experimental design through self-driving laboratories. Prof. Kachman shares insights on the challenges of integrating physics and chemistry with AI systems, the critical role of high-throughput experimentation in accelerating scientific discovery, and the transformative potential of generative models to unlock new materials and functionalities.

In this episode, we talked with Ahmad Beirami, an ex-researcher at Google, to discuss various topics. We explored the complexities of reinforcement learning, its applications in LLMs, and the evaluation challenges in AI research. We also discussed the dynamics of academic conferences and the broken review system. Finally, we discussed how to integrate theory and practice in AI research and why the community should prioritize a deeper understanding over surface-level improvements.

In this episode of the "Information Bottleneck" podcast, we hosted Aran Nayeb, an assistant professor at Carnegie Mellon University, to discuss the intersection of computational neuroscience and machine learning. We talked about the challenges and opportunities in understanding intelligence through the lens of both biological and artificial systems. We talked about topics such as the evolution of neural networks, the role of intrinsic motivation in AI, and the future of brain-machine interfaces.

We talked with Ariel Noyman, an urban scientist, working in the intersection of cities and technology. Ariel is a research scientist at the MIT Media Lab, exploring novel methods of urban modeling and simulation using AI. We discussed the potential of virtual environments to enhance urban design processes, the challenges associated with them, and the future of utilizing AI. Links:TravelAgent: Generative agents in the built environment - https://journals.sagepub.com/doi/10.1177/23998083251360458Ariel Neumann's websites -https://www.arielnoyman.com/https://www.media.mit.edu/people/noyman/overview/

We discussed the inference optimization technique known as Speculative Decoding with a world class researcher, expert, and ex-coworker of the podcast hosts: Nadav Timor.Papers and links:Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies, Timor et al, ICML 2025, https://arxiv.org/abs/2502.05202Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference, Timor et al, ICLR, 2025, https://arxiv.org/abs/2405.14105Fast Inference from Transformers via Speculative Decoding, Leviathan et al, 2022, https://arxiv.org/abs/2502.05202FindPDFs - https://huggingface.co/datasets/HuggingFaceFW/finepdfs

In this episode, Ravid and Allen discuss the evolving landscape of AI coding. They explore the rise of AI-assisted development tools, the challenges faced in software engineering, and the potential future of AI in creative fields. The conversation highlights both the benefits and limitations of AI in coding, emphasizing the need for careful consideration of its impact on the industry and society.Chapters00:00Introduction to AI Coding and Recent Developments03:10OpenAI's Paper on Hallucinations in LLMs06:03Critique of OpenAI's Research Approach08:50Copyright Issues in AI Training Data12:00The Value of Data in AI Training14:50Watermarking AI Generated Content17:54The Future of AI Investment and Market Dynamics20:49AI Coding and Its Impact on Software Development31:36The Evolution of AI in Software Development33:54Vibe Coding: The Future or a Fad?38:24Navigating AI Tools: Personal Experiences and Challenges41:53The Limitations of AI in Complex Coding Tasks46:52Security Vulnerabilities in AI-Generated Code50:28The Role of Human Intuition in AI-Assisted Coding53:28The Impact of AI on Developer Productivity56:53The Future of AI in Creative Fields

Allen and Ravid discuss the dynamics associated with the extreme need for GPUs that AI researchers utilize. They also discuss the latest advancements in AI, including Google's Nano Banana and DeepSeek V3.1, exploring the implications of synthetic data, perplexity, and the influence of AI on human communication. They also delve into the challenges faced by AI researchers in the job market, the importance of GPU infrastructure, and a recent papers examining knowledge and reasoning in LLMs.

Allen and Ravid sit down and talk about Parameter Efficient Fine Tuning (PeFT) along with the latest updated in AI/ML news.

Allen and Ravid discuss a topic near and dear to their hearts, LLM Sampling!In this episode of the Information Bottleneck Podcast, Ravid Shwartz-Ziv and Alan Rausch discuss the latest developments in AI, focusing on the controversial release of GPT-5 and its implications for users. They explore the future of large language models and the importance of sampling techniques in AI. Chapters00:00 Introduction to the Information Bottleneck Podcast01:42 The GPT-5 Debacle: Expectations vs. Reality05:48 Shifting Paradigms in AI Research09:46 The Future of Large Language Models12:56 OpenAI's New Model: A Mixed Bag17:55 Corporate Dynamics in AI: Mergers and Acquisitions21:39 The GPU Monopoly: Challenges and Opportunities25:31 Deep Dive into Samplers in AI35:38 Innovations in Sampling Techniques42:31 Dynamic Sampling Methods and Their Implications51:50 Learning Samplers: A New Frontier59:51 Recent Papers and Their Impact on AI Research