正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

FULL EXPLANATION: Works In Progress' Ruxandra Teslo 🧬 on Anthropic's Protein Binding, Drug Design, The Methodology, RF Diffusion, Alpha Fold, Generative AI & Biology, Curing All Diseases in 10 Years, Mini Research Assistants, Automating Science: 2:00 - How To Design A Drug 3:30 - Bottle Neck's To Molecule Design... show more

etn.

12,864 subscribers

18,514 次观看 • 12 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Exclusive: Inside $3.8B Chai Discovery After leaving OpenAI & Stripe, co-founders Josh Meier (Joshua Meier) and Jack Dent (Jack Dent) built a pioneering AI drug design model called Chai-1. Now? Their models are used by giants like Eli Lilly, Pfizer and Novartis. Their models design antibodies in hours, not years - with atomic-level accuracy confirmed in the lab. If they're right, we're closer than ever to curing complex diseases. We went to San Francisco to find out. They've raised $600M + from sarah guo Lachy Groom Fred Ehrsam Thrive Capital Sequoia Capital General Catalyst OpenAI Menlo Ventures Index Ventures Kleiner Perkins + more. 0:00 AI drug design - how is it possible? 1:32 Josh: Leaving OpenAI for biology 2:34 90% of drugs used to fail 3:24 An outside scientist's honest take 4:40 Chai-3: Drug design in hours not years 5:30 Why Eli Lilly bet on Chai 6:20 When will this reach patients? 8:56 A hopeful future: Alzheimer's & aging

Exclusive: Inside $3.8B Chai Discovery After leaving OpenAI & Stripe, co-founders Josh Meier (Joshua Meier) and Jack Dent (Jack Dent) built a pioneering AI drug design model called Chai-1. Now? Their models are used by giants like Eli Lilly, Pfizer and Novartis. Their models design antibodies in hours, not years - with atomic-level accuracy confirmed in the lab. If they're right, we're closer than ever to curing complex diseases. We went to San Francisco to find out. They've raised $600M + from sarah guo Lachy Groom Fred Ehrsam Thrive Capital Sequoia Capital General Catalyst OpenAI Menlo Ventures Index Ventures Kleiner Perkins + more. 0:00 AI drug design - how is it possible? 1:32 Josh: Leaving OpenAI for biology 2:34 90% of drugs used to fail 3:24 An outside scientist's honest take 4:40 Chai-3: Drug design in hours not years 5:30 Why Eli Lilly bet on Chai 6:20 When will this reach patients? 8:56 A hopeful future: Alzheimer's & aging

Sachin and Adam

97,252 次观看 • 1 个月前

To date, finding a drug has been a process of guess & check… screening millions of molecules hoping one binds. Chai Discovery is changing the paradigm… describe the molecule you want, and the model designs it. Joshua Meier and Matt McPartlon took antibody hit rates from roughly 1 in 1,000 to 1 in 7. That's the jump from search to engineering. On this episode of Training Data, they get into where the field actually is, why 2024 was the moment to start, what drug discovery looks like when the computer does the design, and more. 00:00 Introduction 01:52 From Discovery to Design 03:25 Protein AI Breakthroughs Timeline 06:04 Why Start in 2024 10:13 Diffusion Models Intuition 11:41 Building the Avengers Team 15:22 Hit Rates and Scaling Laws 25:01 Molecular CAD Vision 25:24 Faster Design Loops 26:32 Future Drug Discovery 28:37 Platform Business Model 31:14 Partnering Reality Check 33:44 Data Flywheel Explained 37:16 Staying Ahead at Scale 39:44 Culture and What's Next

To date, finding a drug has been a process of guess & check… screening millions of molecules hoping one binds. Chai Discovery is changing the paradigm… describe the molecule you want, and the model designs it. Joshua Meier and Matt McPartlon took antibody hit rates from roughly 1 in 1,000 to 1 in 7. That's the jump from search to engineering. On this episode of Training Data, they get into where the field actually is, why 2024 was the moment to start, what drug discovery looks like when the computer does the design, and more. 00:00 Introduction 01:52 From Discovery to Design 03:25 Protein AI Breakthroughs Timeline 06:04 Why Start in 2024 10:13 Diffusion Models Intuition 11:41 Building the Avengers Team 15:22 Hit Rates and Scaling Laws 25:01 Molecular CAD Vision 25:24 Faster Design Loops 26:32 Future Drug Discovery 28:37 Platform Business Model 31:14 Partnering Reality Check 33:44 Data Flywheel Explained 37:16 Staying Ahead at Scale 39:44 Culture and What's Next

Pat Grady

33,637 次观看 • 27 天前

NEW EPISODE of HARD DRUGS! AlphaFold, ProteinMPNN and other AI tools are transforming biology and drug design. But how do they work? What can’t they do (yet)? And can we use them to make a vaccine against Strep A for the very first time? In this episode, Jacob and I talk about hacking proteins with AI. 03:21 What makes proteins cool 05:29 Can we make a vaccine against Strep A? 10:12 Proteins in nature aren’t enough, and we can improve them with AI 21:12 ProteinMPNN and AlphaFold are transforming drug design 29:52 A short history of protein structure prediction from physical models to deep learning 34:48 Using AI to design a Strep A vaccine 39:27 Validating an AI-designed Strep A vaccine 43:09 Recent AI protein breakthroughs 49:30 Why we don’t already have a Strep A vaccine and the future of optimizing protein drugs

NEW EPISODE of HARD DRUGS! AlphaFold, ProteinMPNN and other AI tools are transforming biology and drug design. But how do they work? What can’t they do (yet)? And can we use them to make a vaccine against Strep A for the very first time? In this episode, Jacob and I talk about hacking proteins with AI. 03:21 What makes proteins cool 05:29 Can we make a vaccine against Strep A? 10:12 Proteins in nature aren’t enough, and we can improve them with AI 21:12 ProteinMPNN and AlphaFold are transforming drug design 29:52 A short history of protein structure prediction from physical models to deep learning 34:48 Using AI to design a Strep A vaccine 39:27 Validating an AI-designed Strep A vaccine 43:09 Recent AI protein breakthroughs 49:30 Why we don’t already have a Strep A vaccine and the future of optimizing protein drugs

Saloni

72,565 次观看 • 11 个月前

A talk on verifiable environments for agents in biology 0:00 Where does experimental data come from? 1:41 Modern bio research organized around measurement 2:44 Data analysis is an executable substrate for science 3:23 Five years of learnings building products for pharma 4:13 Trying to use coding models for biology workflows 5:40 Why frontier models can't be trusted (yet) 6:44 Sequencing based spatial analysis 7:38 SpatialBench design principles 8:26 Anatomy of a single evaluation 9:40 Human verification and early long horizon extensions 13:12 Grading functions and the case against rubrics 14:07 New work in multi-omics, therapeutics, biosecurity

A talk on verifiable environments for agents in biology 0:00 Where does experimental data come from? 1:41 Modern bio research organized around measurement 2:44 Data analysis is an executable substrate for science 3:23 Five years of learnings building products for pharma 4:13 Trying to use coding models for biology workflows 5:40 Why frontier models can't be trusted (yet) 6:44 Sequencing based spatial analysis 7:38 SpatialBench design principles 8:26 Anatomy of a single evaluation 9:40 Human verification and early long horizon extensions 13:12 Grading functions and the case against rubrics 14:07 New work in multi-omics, therapeutics, biosecurity

Kenny Workman

90,536 次观看 • 1 个月前

Even the most successful websites eventually need a redesign. Take Stripe for example. After six years with the same homepage, Stripe recently unveiled a brand new site that reflects how the company has evolved over the past few years. So when is the time right for a new landing page? And what should you prioritize in the redesign? In this episode of Design Review, YC’s Aaron Epstein sat down Stripe’s Head of Design Katie Dill (Katie Dill) to pull the curtain back on their high profile redesign and to discuss how their team is evolving in a world dominated by new AI design tools. 00:30 - The Old Site 05:30 - “What is the point of a website?” 06:00 - Breaking down the new homepage 07:10 - The GDP counter (and how Stripe builds trust) 08:45 - The Bento Box that fixed the homepage 11:37 - Why great design feels effortless 15:40 - Craft, iteration, and getting it right 19:11 - Inside Stripe’s design process 27:10 - How AI is changing design 35:00 - The fight against mediocrity 40:00 - Walking the Store: Stripe’s Secret to Better Product Design

Y Combinator

86,552 次观看 • 4 个月前

NEW episode! Drug development has never been more expensive, in terms of output per dollar spent. This trend, called Eroom’s law, is surprising, considering the incredible technological advances in drug discovery, from genome sequencing to engineering to microscopy. On a new episode of the Works in Progress podcast, Ben Southwood and I talk to Ruxandra Teslo 🧬 about why this has happened and what can be done about it. We discuss how: • AI isn’t a magic bullet for drug discovery. Predictive models lack the physical human data, like individual variation and rare side effects, that can only be generated by actually running real-world clinical trials. • As scientists invent more effective drugs, it becomes harder to discover new treatments that can surpass past successes. This is known as the "Better than the Beatles" problem. • Biotech companies are increasingly moving their "first-in-human" trials to Australia because its simpler regulations allow researchers to test drug safety faster and cheaper than in the US. • Clinical trials can be made more efficient with various reforms including: embracing platform trials, allowing researchers to select from independent ethics boards, expanding the funding and validation of surrogate endpoints, increasing transparency by releasing regulatory correspondence from failed companies, and much more. Timestamps: 00:00:00 Eroom’s law and the paradox of drug development 00:08:03 How clinical trials actually work 00:10:23 The power and controversy of surrogate endpoints 00:14:01 How historical patent laws influenced trial timelines 00:22:46 The Australia advantage and regulatory drag 00:29:08 Institutional review boards (IRBs) and bureaucratic drag 00:32:21 Open science and successful reforms 00:41:49 Our wishlist for clinical trial reforms, and which reforms we *don’t* like 00:53:48 Why AI isn’t a magic bullet for drug discovery

NEW episode! Drug development has never been more expensive, in terms of output per dollar spent. This trend, called Eroom’s law, is surprising, considering the incredible technological advances in drug discovery, from genome sequencing to engineering to microscopy. On a new episode of the Works in Progress podcast, Ben Southwood and I talk to Ruxandra Teslo 🧬 about why this has happened and what can be done about it. We discuss how: • AI isn’t a magic bullet for drug discovery. Predictive models lack the physical human data, like individual variation and rare side effects, that can only be generated by actually running real-world clinical trials. • As scientists invent more effective drugs, it becomes harder to discover new treatments that can surpass past successes. This is known as the "Better than the Beatles" problem. • Biotech companies are increasingly moving their "first-in-human" trials to Australia because its simpler regulations allow researchers to test drug safety faster and cheaper than in the US. • Clinical trials can be made more efficient with various reforms including: embracing platform trials, allowing researchers to select from independent ethics boards, expanding the funding and validation of surrogate endpoints, increasing transparency by releasing regulatory correspondence from failed companies, and much more. Timestamps: 00:00:00 Eroom’s law and the paradox of drug development 00:08:03 How clinical trials actually work 00:10:23 The power and controversy of surrogate endpoints 00:14:01 How historical patent laws influenced trial timelines 00:22:46 The Australia advantage and regulatory drag 00:29:08 Institutional review boards (IRBs) and bureaucratic drag 00:32:21 Open science and successful reforms 00:41:49 Our wishlist for clinical trial reforms, and which reforms we don’t like 00:53:48 Why AI isn’t a magic bullet for drug discovery

Saloni

109,256 次观看 • 4 个月前

capability != learning new benchtalks with Parth Asawa on continual learning, where we discuss teaching models to learn from experience, measuring learning ability, the bet on parametric models, and more 01:06 What is continual learning? 04:10 Why capability and learning are different 06:13 Why build a benchmark? 08:07 Continual Learning Bench launch and reception 09:13 Anthropic's Fable release and Continual Learning Bench 11:02 How to design tasks for continual learning 18:41 The gain metric 24:01 What good looks like on the leaderboard 29:13 Failure modes: why models can't update their beliefs 31:12 Parametric systems and future architectures 34:30 Open science and AI safety 45:42 Lightning round 49:08 How to contribute to Continual Learning Bench

capability != learning new benchtalks with Parth Asawa on continual learning, where we discuss teaching models to learn from experience, measuring learning ability, the bet on parametric models, and more 01:06 What is continual learning? 04:10 Why capability and learning are different 06:13 Why build a benchmark? 08:07 Continual Learning Bench launch and reception 09:13 Anthropic's Fable release and Continual Learning Bench 11:02 How to design tasks for continual learning 18:41 The gain metric 24:01 What good looks like on the leaderboard 29:13 Failure modes: why models can't update their beliefs 31:12 Parametric systems and future architectures 34:30 Open science and AI safety 45:42 Lightning round 49:08 How to contribute to Continual Learning Bench

vincent sunn chen

41,143 次观看 • 2 个月前

How to Make An Entire iOS App That Doesn't Look Like AI Slop (1 Hour Full Walkthrough) Let's go through how to use Claude Code, Claude Design, Seedance 2.0, GPT Image 2.0 and a few other tools to make sure this iOS app is as far from AI slop as possible while also having a completely functioning backend with pay walls 00:00 Building an App Overview 01:19 How I Made Merl in One Week 03:16 Market Research for Ideas 07:04 Choosing the Wrapper Concept 08:51 Pinterest UI Inspiration 11:16 Define Style + Mascot Plan 12:00 Create Mascots in GPT Image 2.0 17:04 Animate Mascots with Seedance 2.0 (!!) 23:41 Design Onboarding in Claude Design 29:01 Getting Some API Keys 30:35 Onboarding Video Choices 32:30 Build Full App Screens on Claude Design 33:28 Setup Supabase + Railway 35:31 Claude Code GitHub Setup 38:57 Multi Terminal + Simulator Workflow 43:17 Fixing Errors 44:00 Backend Keys Integration 46:23 Landing Page Generation 53:52 Test Generation 57:40 RevenueCat + Pricing Strategy 01:00:54 Final Wrap

How to Make An Entire iOS App That Doesn't Look Like AI Slop (1 Hour Full Walkthrough) Let's go through how to use Claude Code, Claude Design, Seedance 2.0, GPT Image 2.0 and a few other tools to make sure this iOS app is as far from AI slop as possible while also having a completely functioning backend with pay walls 00:00 Building an App Overview 01:19 How I Made Merl in One Week 03:16 Market Research for Ideas 07:04 Choosing the Wrapper Concept 08:51 Pinterest UI Inspiration 11:16 Define Style + Mascot Plan 12:00 Create Mascots in GPT Image 2.0 17:04 Animate Mascots with Seedance 2.0 (!!) 23:41 Design Onboarding in Claude Design 29:01 Getting Some API Keys 30:35 Onboarding Video Choices 32:30 Build Full App Screens on Claude Design 33:28 Setup Supabase + Railway 35:31 Claude Code GitHub Setup 38:57 Multi Terminal + Simulator Workflow 43:17 Fixing Errors 44:00 Backend Keys Integration 46:23 Landing Page Generation 53:52 Test Generation 57:40 RevenueCat + Pricing Strategy 01:00:54 Final Wrap

ashen

72,791 次观看 • 4 个月前

New Infinite Loops with Saloni Dattani (Saloni)! There may be medical breakthroughs in the pipeline right now that work — but won’t reach patients for another decade. Saloni Dattani joins us to explain the hidden bottleneck slowing the future of medicine and why biology may be one of the most important fields to work in today. Listen now. TIMESTAMPS: 0:00 Intro 2:07 The Problem with Health Data 14:44 Clinical Trials Are the Bottleneck 25:05 AI and Drug Discovery 35:00 Why Science Journalism Fails 45:41 Medicine’s Next Great Leap 50:20 Fixing Medical Market Failures 57:10 The Leukemia Trial Breakthrough 1:06:18 Why Failed Research Matters 1:12:51 Science Is Never Settled

New Infinite Loops with Saloni Dattani (Saloni)! There may be medical breakthroughs in the pipeline right now that work — but won’t reach patients for another decade. Saloni Dattani joins us to explain the hidden bottleneck slowing the future of medicine and why biology may be one of the most important fields to work in today. Listen now. TIMESTAMPS: 0:00 Intro 2:07 The Problem with Health Data 14:44 Clinical Trials Are the Bottleneck 25:05 AI and Drug Discovery 35:00 Why Science Journalism Fails 45:41 Medicine’s Next Great Leap 50:20 Fixing Medical Market Failures 57:10 The Leukemia Trial Breakthrough 1:06:18 Why Failed Research Matters 1:12:51 Science Is Never Settled

Infinite Loops 🎙

11,818 次观看 • 4 个月前

My biggest fear for AI is concentration of power. Open-source is a solution. Watch this video to understand what's going on: 0:00 Intro 0:52 NVIDIA's letter 1:36 What is open-source? 3:53 How open-source works 5:48 Kimi K3 6:38 Closed vs Open 8:39 Open-source in the U.S. 12:10 The AI stack 13:05 What if open source wins? 14:08 Jevon's Paradox 14:56 How the AI stack is affected 18:04 User experience 19:38 AI safety 30:30 China 35:50 Distillation 41:40 Banning Chinese models? 43:38 Anthropic's response

My biggest fear for AI is concentration of power. Open-source is a solution. Watch this video to understand what's going on: 0:00 Intro 0:52 NVIDIA's letter 1:36 What is open-source? 3:53 How open-source works 5:48 Kimi K3 6:38 Closed vs Open 8:39 Open-source in the U.S. 12:10 The AI stack 13:05 What if open source wins? 14:08 Jevon's Paradox 14:56 How the AI stack is affected 18:04 User experience 19:38 AI safety 30:30 China 35:50 Distillation 41:40 Banning Chinese models? 43:38 Anthropic's response

Matthew Berman

13,685 次观看 • 1 个月前

.Poetiq is a new startup that recently achieved a major jump on the ARC-AGI benchmark by layering a recursive self-improvement system on top of existing models. In this episode of the Lightcone Podcast, Poetiq's Founder & CEO Ian Fischer joined us to discuss how small teams can build “reasoning harnesses” that outperform base models, what that means for startups and why automating prompt engineering may be one of the most powerful levers in AI today. 00:00 – Intro 00:40 – What Is Poetiq? 01:07 – Recursive Self-Improvement Explained 02:07 – The Fine-Tuning Trap 02:59 – “Stilts” for LLMs 03:14 – Recursive Self-Improvement vs. Fine-Tuning 05:05 – Taking the Top Spot on ARC-AGI 06:37 – Beating Claude on Humanity’s Last Exam 08:40 – How the Meta-System Works 10:26 – Beyond RL: A New S-Curve 11:32 – Automating Prompt Engineering 13:37 – From 5% to 95% Performance 14:50 – Early Access & Putting Your Agent on Stilts 16:17 – From YC Founder to DeepMind Researcher 18:29 – Advice for Engineers in the AI Era

.Poetiq is a new startup that recently achieved a major jump on the ARC-AGI benchmark by layering a recursive self-improvement system on top of existing models. In this episode of the Lightcone Podcast, Poetiq's Founder & CEO Ian Fischer joined us to discuss how small teams can build “reasoning harnesses” that outperform base models, what that means for startups and why automating prompt engineering may be one of the most powerful levers in AI today. 00:00 – Intro 00:40 – What Is Poetiq? 01:07 – Recursive Self-Improvement Explained 02:07 – The Fine-Tuning Trap 02:59 – “Stilts” for LLMs 03:14 – Recursive Self-Improvement vs. Fine-Tuning 05:05 – Taking the Top Spot on ARC-AGI 06:37 – Beating Claude on Humanity’s Last Exam 08:40 – How the Meta-System Works 10:26 – Beyond RL: A New S-Curve 11:32 – Automating Prompt Engineering 13:37 – From 5% to 95% Performance 14:50 – Early Access & Putting Your Agent on Stilts 16:17 – From YC Founder to DeepMind Researcher 18:29 – Advice for Engineers in the AI Era

Y Combinator

156,357 次观看 • 6 个月前

We're developing and using AI to revolutionize scientific discovery - from predicting protein structures with #AlphaFold, to materials discovery with GNoME. Join our VP Science, Pushmeet Kohli, and Professor Hannah Fry as they explore how AI could lead to a new era of breakthroughs that could benefit humanity in countless ways, on Google DeepMind: The Podcast. Watch now ↓ Timestamps: 00:00 Intro 01:13 AlphaFold 06:13 AlphaFold Database 08:14 Weather forecasting 11:24 Creating new materials with deep learning 25:10 Imposter syndrome, being a generalist, and Nobel prize winners 31:21 Choosing the right projects 32:07 Root node problems 34:32 Large language models for science 36:06 Function search and algorithmic discovery 42:10 Math Olympiad 46:26 What’s coming next 48:35 Reflections from Hannah

We're developing and using AI to revolutionize scientific discovery - from predicting protein structures with #AlphaFold, to materials discovery with GNoME. Join our VP Science, Pushmeet Kohli, and Professor Hannah Fry as they explore how AI could lead to a new era of breakthroughs that could benefit humanity in countless ways, on Google DeepMind: The Podcast. Watch now ↓ Timestamps: 00:00 Intro 01:13 AlphaFold 06:13 AlphaFold Database 08:14 Weather forecasting 11:24 Creating new materials with deep learning 25:10 Imposter syndrome, being a generalist, and Nobel prize winners 31:21 Choosing the right projects 32:07 Root node problems 34:32 Large language models for science 36:06 Function search and algorithmic discovery 42:10 Math Olympiad 46:26 What’s coming next 48:35 Reflections from Hannah

Google DeepMind

197,357 次观看 • 1 年前

This is WILD! Nvidia just launched something that could compress the most expensive process in medicine from 12 years to 12 months. BioNeMo Agent Toolkit is an open, agent-ready platform that turns AI agents into autonomous scientific workers, giving them the ability to run real drug discovery workflows instead of just generating ideas. And more than 50 companies are already using it, including Anthropic, OpenAI, Eli Lilly, Databricks, Snowflake, Dassault Systèmes and Schrödinger. Here is what it actually does. Traditional drug discovery costs an average of $2.6 billion per drug and takes over a decade. Most of that time and money goes into screening millions of compounds, designing proteins that bind to disease targets and running countless lab experiments to validate whether something works. BioNeMo agents now do all of that computationally before a single lab experiment begins. The demo Nvidia shared makes the speed impossible to ignore. An agent was asked to design 10 protein binders for PD-L1, a critical cancer immunotherapy target and it completed the full design, co-folding, scoring, and 3D structural analysis on GPU in under 90 seconds. What used to require weeks of wet lab work and PhD-level expertise now runs as a callable tool inside an AI workflow. The four core capabilities are virtual drug screening, protein binder design, genomic analysis, and medical imaging each one compressing tasks that previously took weeks into minutes. The institutional validation behind this is unusually strong. Nvidia and Eli Lilly announced a joint investment of up to $1 billion over five years to build a co-innovation lab running entirely on BioNeMo. The University of Washington's Institute for Protein Design is already running RosettaFold3 at 2x faster performance than the prior generation. And the market this unlocks is enormous, and Nvidia is sitting right at the center of it. The AI drug discovery market is projected to grow from $2.9 billion in 2026 to $13.8 billion by 2033 and McKinsey estimates generative AI could deliver $60 to $110 billion in annual economic value to pharma. Bullish on drug discovery!

This is WILD! Nvidia just launched something that could compress the most expensive process in medicine from 12 years to 12 months. BioNeMo Agent Toolkit is an open, agent-ready platform that turns AI agents into autonomous scientific workers, giving them the ability to run real drug discovery workflows instead of just generating ideas. And more than 50 companies are already using it, including Anthropic, OpenAI, Eli Lilly, Databricks, Snowflake, Dassault Systèmes and Schrödinger. Here is what it actually does. Traditional drug discovery costs an average of $2.6 billion per drug and takes over a decade. Most of that time and money goes into screening millions of compounds, designing proteins that bind to disease targets and running countless lab experiments to validate whether something works. BioNeMo agents now do all of that computationally before a single lab experiment begins. The demo Nvidia shared makes the speed impossible to ignore. An agent was asked to design 10 protein binders for PD-L1, a critical cancer immunotherapy target and it completed the full design, co-folding, scoring, and 3D structural analysis on GPU in under 90 seconds. What used to require weeks of wet lab work and PhD-level expertise now runs as a callable tool inside an AI workflow. The four core capabilities are virtual drug screening, protein binder design, genomic analysis, and medical imaging each one compressing tasks that previously took weeks into minutes. The institutional validation behind this is unusually strong. Nvidia and Eli Lilly announced a joint investment of up to $1 billion over five years to build a co-innovation lab running entirely on BioNeMo. The University of Washington's Institute for Protein Design is already running RosettaFold3 at 2x faster performance than the prior generation. And the market this unlocks is enormous, and Nvidia is sitting right at the center of it. The AI drug discovery market is projected to grow from $2.9 billion in 2026 to $13.8 billion by 2033 and McKinsey estimates generative AI could deliver $60 to $110 billion in annual economic value to pharma. Bullish on drug discovery!

Milk Road AI

23,215 次观看 • 2 个月前

Priscilla Chan and Mark Zuckerberg on Curing All Disease We sat down with Dr. Priscilla Chan and Mark Zuckerberg, co-founders of the Chan Zuckerberg Initiative, to discuss their ambitious plan to cure, prevent, and manage all disease by the end of the century. CZI’s Biohub aims to generate vast biological datasets to train new frontier AI models to guide scientists in the lab, creating a feedback loop to accelerate the pace of basic science and take us towards a world without disease. 00:00 Introduction 03:42 Building tools to accelerate scientific discovery 07:03 Biohub = Frontier Biology + Frontier AI 13:32 "Most diseases should be thought of as rare diseases” 15:39 Inspiration: building a periodic table for biology 19:27 Why virtual cells? 21:17 The Biohub master plan 33:36 The importance of interface design in democratizing scientific discovery 35:34 How Biohub encourages cross-functional collaboration 40:38 Looking ahead: the broader impact of AI on biotech benahorowitz.eth Vineeta Agarwala Erik Torenberg

Priscilla Chan and Mark Zuckerberg on Curing All Disease We sat down with Dr. Priscilla Chan and Mark Zuckerberg, co-founders of the Chan Zuckerberg Initiative, to discuss their ambitious plan to cure, prevent, and manage all disease by the end of the century. CZI’s Biohub aims to generate vast biological datasets to train new frontier AI models to guide scientists in the lab, creating a feedback loop to accelerate the pace of basic science and take us towards a world without disease. 00:00 Introduction 03:42 Building tools to accelerate scientific discovery 07:03 Biohub = Frontier Biology + Frontier AI 13:32 "Most diseases should be thought of as rare diseases” 15:39 Inspiration: building a periodic table for biology 19:27 Why virtual cells? 21:17 The Biohub master plan 33:36 The importance of interface design in democratizing scientific discovery 35:34 How Biohub encourages cross-functional collaboration 40:38 Looking ahead: the broader impact of AI on biotech benahorowitz.eth Vineeta Agarwala Erik Torenberg

a16z

377,385 次观看 • 9 个月前

. Jay Bhattacharya joins this NEW episode of Real Talk to discuss COVID, NIH reform, DEI in science, vaccine mandates, and restoring medical innovation. | NIHDirector_Jay 00:00 - Dr. Jay Bhattacharya on COVID, Censorship, and the NIH 01:57 - Why Dr. Jay Spoke Out During COVID 04:07 - Why Public Health Cannot Just “Move On” 06:50 - Can Americans Trust the NIH Again? 10:00 - How Do You Reform a $50 Billion Institution? 11:05 - How Politics Entered the NIH 15:14 - Is the NIH Banning Words and Blocking Research? 17:30 - Is the NIH Funding Safe Science Instead of Breakthrough Ideas? 22:10 - How Dr. Jay Is Changing NIH Grant Funding 26:16 - Is Peer Review Broken? 30:08 - Who Gets to Decide What Is True in Science? 33:45 - Why Replication Matters 35:31 - How the NIH Plans to Fix the Replication Crisis 39:07 - Is America Still Leading Biomedical Innovation? 42:15 - Cancer Research, Immunotherapy, and Medical Breakthroughs 44:01 - Gene Editing, Sickle Cell, and the Future of Cures 47:12 - How Should Parents Think About Vaccines After COVID? 50:04 - Why Do We Still Vaccinate for Rare Diseases?

. Jay Bhattacharya joins this NEW episode of Real Talk to discuss COVID, NIH reform, DEI in science, vaccine mandates, and restoring medical innovation. | NIHDirector_Jay 00:00 - Dr. Jay Bhattacharya on COVID, Censorship, and the NIH 01:57 - Why Dr. Jay Spoke Out During COVID 04:07 - Why Public Health Cannot Just “Move On” 06:50 - Can Americans Trust the NIH Again? 10:00 - How Do You Reform a $50 Billion Institution? 11:05 - How Politics Entered the NIH 15:14 - Is the NIH Banning Words and Blocking Research? 17:30 - Is the NIH Funding Safe Science Instead of Breakthrough Ideas? 22:10 - How Dr. Jay Is Changing NIH Grant Funding 26:16 - Is Peer Review Broken? 30:08 - Who Gets to Decide What Is True in Science? 33:45 - Why Replication Matters 35:31 - How the NIH Plans to Fix the Replication Crisis 39:07 - Is America Still Leading Biomedical Innovation? 42:15 - Cancer Research, Immunotherapy, and Medical Breakthroughs 44:01 - Gene Editing, Sickle Cell, and the Future of Cures 47:12 - How Should Parents Think About Vaccines After COVID? 50:04 - Why Do We Still Vaccinate for Rare Diseases?

Marissa Streit

11,578 次观看 • 1 个月前

What could Alphafold 4 look like? (Sergey Ovchinnikov, Ep #3) 2 hours listening time (links below) To those in the (machine-learning for protein design) space, Dr. Sergey Ovchinnikov (Sergey Ovchinnikov) is a very, very well-recognized name. A recent MIT professor (circa early 2024), he has played a part in a staggering number of recent great papers in the field: ColabFold, RFDiffusion, Bindcraft, automated design of soluble proxies of membrane proteins, elucidating what protein language models are learning, conformational sampling via Alphafold2, and many more. Of course, all these papers were group efforts, but Sergey's name comes up astonishingly frequently! And even beyond the research that have come from his lab in the last few years, the co-evolution work he did during his PhD/fellowship also laid some of the groundwork for the original Alphafold paper, being cited twice in it. This is a two hour conversation with him, asking every question I could think of. We talk about his own journey into biology research, an issue he has with Alphafold3, what Alphafold4-and-beyond models may look like, what research he’d want to spend a hundred million dollars on, and lots more. Topics/institutions we discuss: Arc Institute's Evo models, Hannah Wayment-Steele's work, Isomorphic Labs's AF2/AF3, and EvolutionaryScale's ESM models Also, extremely grateful to Asimov Press (Asimov Press) for helping fund the travel + studio time required for this episode! They are a non-profit publisher dedicated to thoughtful writing on biology and metascience, such as articles over synthetic blood and interviews with plant geneticists. I myself have published within them twice! I highly recommend checking out their essays at or reaching out to editors@asimov.com if you’re interested in contributing. Timestamps: [00:00:00] Highlight clips [00:01:10] Introduction + Sergey's background and how he got into the field [00:18:14] Is conservation all you need? [00:23:26] Ambiguous vs non-ambiguous regions in proteins [00:24:59] What will AlphaFold 4/5/6 look like? [00:36:19] Diffusion vs. inversion for protein design [00:44:52] A problem with Alphafold3 [00:53:41] MSA vs. single sequence models [01:06:52] How Sergey picks research problems [01:21:06] What are DNA models like Evo learning? [01:29:11] The problem with train/test splits in biology [01:49:07] What Sergey would do with $100 million

What could Alphafold 4 look like? (Sergey Ovchinnikov, Ep #3) 2 hours listening time (links below) To those in the (machine-learning for protein design) space, Dr. Sergey Ovchinnikov (Sergey Ovchinnikov) is a very, very well-recognized name. A recent MIT professor (circa early 2024), he has played a part in a staggering number of recent great papers in the field: ColabFold, RFDiffusion, Bindcraft, automated design of soluble proxies of membrane proteins, elucidating what protein language models are learning, conformational sampling via Alphafold2, and many more. Of course, all these papers were group efforts, but Sergey's name comes up astonishingly frequently! And even beyond the research that have come from his lab in the last few years, the co-evolution work he did during his PhD/fellowship also laid some of the groundwork for the original Alphafold paper, being cited twice in it. This is a two hour conversation with him, asking every question I could think of. We talk about his own journey into biology research, an issue he has with Alphafold3, what Alphafold4-and-beyond models may look like, what research he’d want to spend a hundred million dollars on, and lots more. Topics/institutions we discuss: Arc Institute's Evo models, Hannah Wayment-Steele's work, Isomorphic Labs's AF2/AF3, and EvolutionaryScale's ESM models Also, extremely grateful to Asimov Press (Asimov Press) for helping fund the travel + studio time required for this episode! They are a non-profit publisher dedicated to thoughtful writing on biology and metascience, such as articles over synthetic blood and interviews with plant geneticists. I myself have published within them twice! I highly recommend checking out their essays at or reaching out to [email protected] if you’re interested in contributing. Timestamps: [00:00:00] Highlight clips [00:01:10] Introduction + Sergey's background and how he got into the field [00:18:14] Is conservation all you need? [00:23:26] Ambiguous vs non-ambiguous regions in proteins [00:24:59] What will AlphaFold 4/5/6 look like? [00:36:19] Diffusion vs. inversion for protein design [00:44:52] A problem with Alphafold3 [00:53:41] MSA vs. single sequence models [01:06:52] How Sergey picks research problems [01:21:06] What are DNA models like Evo learning? [01:29:11] The problem with train/test splits in biology [01:49:07] What Sergey would do with $100 million

owl

89,153 次观看 • 1 年前

🚀 Reshaping drug discovery – and the future of medicine – with AI. Recursion CFO Ben Taylor joined the Opto Sessions podcast from CMC Aureon to share how Recursion uses AI, lab automation, biological data, and machine learning to improve the way new medicines are discovered and developed. 💠 They discuss: ▪️How pairing AI with lab automation across biology, chemistry, and clinical technology allows us to move beyond the ~10–12% of the genome currently addressed by approved or in-trial medicines and explore the vast realm of untapped biology. ▪️How Recursion is advancing REC-4881 for patients with familial adenomatous polyposis (FAP) — a progressive condition with no approved medical therapies — after achieving Phase 2 proof-of-concept and demonstrating meaningful reductions in polyp burden. ▪️How Recursion is compressing timelines and improving efficiency with high-quality, ML-ready data to design better molecules with ~90% fewer experimental chemistries and to run smarter, faster clinical trials. 👉 Check out the full conversation:

🚀 Reshaping drug discovery – and the future of medicine – with AI. Recursion CFO Ben Taylor joined the Opto Sessions podcast from CMC Aureon to share how Recursion uses AI, lab automation, biological data, and machine learning to improve the way new medicines are discovered and developed. 💠 They discuss: ▪️How pairing AI with lab automation across biology, chemistry, and clinical technology allows us to move beyond the ~10–12% of the genome currently addressed by approved or in-trial medicines and explore the vast realm of untapped biology. ▪️How Recursion is advancing REC-4881 for patients with familial adenomatous polyposis (FAP) — a progressive condition with no approved medical therapies — after achieving Phase 2 proof-of-concept and demonstrating meaningful reductions in polyp burden. ▪️How Recursion is compressing timelines and improving efficiency with high-quality, ML-ready data to design better molecules with ~90% fewer experimental chemistries and to run smarter, faster clinical trials. 👉 Check out the full conversation:

Recursion

98,839 次观看 • 1 个月前

SPECIAL: Tarun Chitra vs. DeSci Debate with Benji Leibowitz In this spicy episode, & @robbie_rollup sat down with Tarun Chitra of Gauntlet and benjels of Pump Science to sound off on: > What is DeSci? > Why Tarun feels strongly about DeSci > The science of new drug creation > How incentive misalignment is problematic > Why onchain rails are needed for DeSci From the risks of mismanaged incentives to building real accountability in science experiments, this debate breaks down what’s working—and what’s not in DeSci. Full episode links below. Timestamps: 00:00 Intro 02:15 DeSci Opening Remarks 10:32 Retail Investor Knowledge Gaps 19:44 Scientific Funding System Redesign 30:29 Outsider’s DeSci Perspective 35:20 Crypto Research Evolution 41:14 Peer Review in AI and Crypto 51:40 Looking Ahead in DeSci

SPECIAL: Tarun Chitra vs. DeSci Debate with Benji Leibowitz In this spicy episode, & @robbie_rollup sat down with Tarun Chitra of Gauntlet and benjels of Pump Science to sound off on: > What is DeSci? > Why Tarun feels strongly about DeSci > The science of new drug creation > How incentive misalignment is problematic > Why onchain rails are needed for DeSci From the risks of mismanaged incentives to building real accountability in science experiments, this debate breaks down what’s working—and what’s not in DeSci. Full episode links below. Timestamps: 00:00 Intro 02:15 DeSci Opening Remarks 10:32 Retail Investor Knowledge Gaps 19:44 Scientific Funding System Redesign 30:29 Outsider’s DeSci Perspective 35:20 Crypto Research Evolution 41:14 Peer Review in AI and Crypto 51:40 Looking Ahead in DeSci

The Rollup

71,811 次观看 • 1 年前

On this Core Memory pod, we go all Weird Science with Coinbase 🛡️ CEO Brian Armstrong and toss in some crypto chat for the masses too. Enjoy! Timestamps 00:00 – Intro 00:27 – Genetic Responsibility Future 00:54 – Armstrong’s Silicon Valley Roots 02:00 – Political Neutrality at Coinbase 03:26 – Libertarian Crypto Foundations 04:31 – Civilizational Acceleration 05:30 – Tech Sparks Moral Panic 06:52 – Neurodivergence 07:55 – Gene Editing Societal Impact 10:50 – The Gattaca Stack Overview 11:36 – Disease vs Enhancement 14:15 – Biological Upgrades Discussion 18:00 – Artificial Wombs Future 19:10 – Womb Research Ethics 21:15 – Learning Biology for NewLimit 22:10 – Armstrong’s Self‑Taught Biology 25:00 – How NewLimit Reprograms Cells 27:30 – Cell Rejuvenation Milestones 31:30 – Regulation and Coinbase Era 33:00 – Coinbase vs NewLimit Leadership 35:00 – Software to Atoms Transition 37:30 – Stablecoins and Tokenized Assets 39:00 – Crypto Legislation Momentum 41:00 – Layer 2 Stablecoin Breakthrough

On this Core Memory pod, we go all Weird Science with Coinbase 🛡️ CEO Brian Armstrong and toss in some crypto chat for the masses too. Enjoy! Timestamps 00:00 – Intro 00:27 – Genetic Responsibility Future 00:54 – Armstrong’s Silicon Valley Roots 02:00 – Political Neutrality at Coinbase 03:26 – Libertarian Crypto Foundations 04:31 – Civilizational Acceleration 05:30 – Tech Sparks Moral Panic 06:52 – Neurodivergence 07:55 – Gene Editing Societal Impact 10:50 – The Gattaca Stack Overview 11:36 – Disease vs Enhancement 14:15 – Biological Upgrades Discussion 18:00 – Artificial Wombs Future 19:10 – Womb Research Ethics 21:15 – Learning Biology for NewLimit 22:10 – Armstrong’s Self‑Taught Biology 25:00 – How NewLimit Reprograms Cells 27:30 – Cell Rejuvenation Milestones 31:30 – Regulation and Coinbase Era 33:00 – Coinbase vs NewLimit Leadership 35:00 – Software to Atoms Transition 37:30 – Stablecoins and Tokenized Assets 39:00 – Crypto Legislation Momentum 41:00 – Layer 2 Stablecoin Breakthrough

Ashlee Vance

302,831 次观看 • 1 年前