Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Chai Discovery's BioAI Phase Shift: Chai-3, Photoshop for Molecules, One-Shot Drug Design, & Engineering Biology Chai Discovery cofounder Matt McPartlon and product lead Neil Patil explain why AI drug design has crossed the threshold from impressive demos to pharma-trusted tools, how Chai-2 and Chai-3 are pushing toward one-shot therapeutic-grade... show more

Latent.Space

31,388 subscribers

20,438 views • 17 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🆕!! AI and atomic-level structure prediction are accelerating drug discovery — turning a slow, empirical search process into something closer to molecular engineering. Joshua Meier @_jackdent co-founders Chai Discovery chat their new bio foundation model, Chai-2. It enables zero-shot antibody discovery in a single 24-well plate — with a ~20% hit rate, compressing years of lab work into weeks. They talk what's next for Chai, what's still challenging, and why they're 𝐛𝐮𝐥𝐥𝐢𝐬𝐡 𝐨𝐧 𝐛𝐢𝐨𝐭𝐞𝐜𝐡

🆕!! AI and atomic-level structure prediction are accelerating drug discovery — turning a slow, empirical search process into something closer to molecular engineering. Joshua Meier @_jackdent co-founders Chai Discovery chat their new bio foundation model, Chai-2. It enables zero-shot antibody discovery in a single 24-well plate — with a ~20% hit rate, compressing years of lab work into weeks. They talk what's next for Chai, what's still challenging, and why they're 𝐛𝐮𝐥𝐥𝐢𝐬𝐡 𝐨𝐧 𝐛𝐢𝐨𝐭𝐞𝐜𝐡

No Priors

14,840 views • 1 year ago

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 views • 1 month ago

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 views • 24 days ago

"We have this long term vision of turning biology from something which is trial and error and experimental and make it something that looks more like an engineering discipline in the next century." New Episode with Jack Dent ! 0:00 Intro 02:28 Inside Stripe w/ Patrick Collison, at <100 People 08:45 Sam Altman role in Chai Discovery origin 16:20 Chai-2 Antibody Breakthrough 19:24 Approaching biology as an engineering problem 24:45 Using AI models to treat people on an individual scale 26:52 Robotics in labs 27:22 Pharma industry today 29:49 The clinical trial bottleneck 32:53 Personalized biology models & cancer vaccines 36:24 Longevity, peptides, and trillion-dollar drugs 39:02 Does it matter that the government cut exploratory science grants? 41:00 What next-gen Chai models will do 42:08 Can frontier AI labs build this themselves? 43:26 Biology is hard

"We have this long term vision of turning biology from something which is trial and error and experimental and make it something that looks more like an engineering discipline in the next century." New Episode with Jack Dent ! 0:00 Intro 02:28 Inside Stripe w/ Patrick Collison, at <100 People 08:45 Sam Altman role in Chai Discovery origin 16:20 Chai-2 Antibody Breakthrough 19:24 Approaching biology as an engineering problem 24:45 Using AI models to treat people on an individual scale 26:52 Robotics in labs 27:22 Pharma industry today 29:49 The clinical trial bottleneck 32:53 Personalized biology models & cancer vaccines 36:24 Longevity, peptides, and trillion-dollar drugs 39:02 Does it matter that the government cut exploratory science grants? 41:00 What next-gen Chai models will do 42:08 Can frontier AI labs build this themselves? 43:26 Biology is hard

Sabrina Halper

39,755 views • 3 months ago

Chai Discovery cofounder Jack Dent says AI drug discovery hit a major inflection point in 2025. As a result, it's now being deployed at the biggest pharma companies as part of their core discovery engines. "Over the course of 2025, these models went from being research curiosities... to being able to design molecules without needing to fine-tune them on a lot of data." "You can really just prompt them in the way that you'd prompt an LLM with a target, maybe some disease you're going after. And they will design a number of candidates that would help do that, essentially." "A year, year and a half ago, basically none of this stuff worked." "In 2025 we really crossed the Rubicon. And now these technologies are actively being deployed in companies like Eli Lilly, Novartis, Pfizer. These are some of the most scientific, highest-tech companies in the world. And they're putting them into real drug programs and making them part of their core discovery engines."

Chai Discovery cofounder Jack Dent says AI drug discovery hit a major inflection point in 2025. As a result, it's now being deployed at the biggest pharma companies as part of their core discovery engines. "Over the course of 2025, these models went from being research curiosities... to being able to design molecules without needing to fine-tune them on a lot of data." "You can really just prompt them in the way that you'd prompt an LLM with a target, maybe some disease you're going after. And they will design a number of candidates that would help do that, essentially." "A year, year and a half ago, basically none of this stuff worked." "In 2025 we really crossed the Rubicon. And now these technologies are actively being deployed in companies like Eli Lilly, Novartis, Pfizer. These are some of the most scientific, highest-tech companies in the world. And they're putting them into real drug programs and making them part of their core discovery engines."

TBPN

29,322 views • 1 month ago

🚀 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 views • 1 month ago

Today, we expand zero-shot drug design beyond binding to the design of multifunctional medicines, the intracellular proteome, and state-of-the-art atomic precision with our model, JAM-2. In a new report (below), we show: 1. The first drug-grade, fully computationally designed multispecific antibodies against five peptide-MHCs: Routine picomolar T-cell activation/cell-killing EC50s, >100-fold selectivity, and drug-like developability 2. The first fully generatively designed, drug-grade dual-variant KRAS G12 multispecifics: They recruit primary T-cells from human donors to kill G12V and G12C presenting cells at pM to single-digit-nM potency, completely sparing wild-type. 3. Atomic accuracy, from sequence alone: Angstrom-level agreement between Cryo-EM and JAM-2 de novo designs, requiring only target sequences (not structure) as input. 4. Unrivaled speed with an AI-native in-house wet lab: Designed, built, and tested five programs in one parallelized campaign, end-to-end in-house in ~6 weeks. 5. A higher validation bar for AI-generated drug candidates: In a field increasingly rife with hype and uneven standards of proof, we provide the highest quality public wet-lab validation of AI-designed antibodies to date. We share experimental methods in full, and invite folks to adopt and build on these standards. Truly individualized therapies will be the most important contribution of AI in drug design. These advances help accelerate this future.

Today, we expand zero-shot drug design beyond binding to the design of multifunctional medicines, the intracellular proteome, and state-of-the-art atomic precision with our model, JAM-2. In a new report (below), we show: 1. The first drug-grade, fully computationally designed multispecific antibodies against five peptide-MHCs: Routine picomolar T-cell activation/cell-killing EC50s, >100-fold selectivity, and drug-like developability 2. The first fully generatively designed, drug-grade dual-variant KRAS G12 multispecifics: They recruit primary T-cells from human donors to kill G12V and G12C presenting cells at pM to single-digit-nM potency, completely sparing wild-type. 3. Atomic accuracy, from sequence alone: Angstrom-level agreement between Cryo-EM and JAM-2 de novo designs, requiring only target sequences (not structure) as input. 4. Unrivaled speed with an AI-native in-house wet lab: Designed, built, and tested five programs in one parallelized campaign, end-to-end in-house in ~6 weeks. 5. A higher validation bar for AI-generated drug candidates: In a field increasingly rife with hype and uneven standards of proof, we provide the highest quality public wet-lab validation of AI-designed antibodies to date. We share experimental methods in full, and invite folks to adopt and build on these standards. Truly individualized therapies will be the most important contribution of AI in drug design. These advances help accelerate this future.

Nabla Bio

179,567 views • 2 months ago

Ex-Google engineer just compressed the shift from AI agents to "graphs" and "loops" into one 2h47m lecture: • 00:00 - understanding the different layers of AI memory • 30:00 - moving from simple LLM calls to AI agents • 50:00 - why agent systems are becoming a graph engineering problem • 1:12:00 - connecting context, tools and agent state • 1:24:00 - building a minimal agent harness from scratch • 1:46:00 - breaking down the architecture behind Hermes Agent • 2:08:00 - turning agent concepts into working systems 167-minute deep dive, and one of the clearest ways to understand how AI engineering is moving beyond prompts The progression: Prompt → Context → Memory → Agent → Loop → Graph → Agent Harness Watch it today, then read the full roadmap below

Ex-Google engineer just compressed the shift from AI agents to "graphs" and "loops" into one 2h47m lecture: • 00:00 - understanding the different layers of AI memory • 30:00 - moving from simple LLM calls to AI agents • 50:00 - why agent systems are becoming a graph engineering problem • 1:12:00 - connecting context, tools and agent state • 1:24:00 - building a minimal agent harness from scratch • 1:46:00 - breaking down the architecture behind Hermes Agent • 2:08:00 - turning agent concepts into working systems 167-minute deep dive, and one of the clearest ways to understand how AI engineering is moving beyond prompts The progression: Prompt → Context → Memory → Agent → Loop → Graph → Agent Harness Watch it today, then read the full roadmap below

Morlex

50,478 views • 12 days ago

Free 3-hour course from an ex-Google engineer. AI agents, graph engineering, harness, agent loops. Covers more than most $500 paid courses. This is the exact playbook to learn how to actually build and monetize AI agents. Don't miss your shot, save it now. • 0:00 - Design an AI agent system from scratch • 7:38 - When your agent should hand off to a human • 19:27 - RAG and vector databases explained simply • 52:38 - Deploy your AI agent to Google Cloud • 1:25:57 - Turn AI agents into a paid business via WhatsApp • 1:33:00 - Turn conversations into real leads automatically • 2:24:01 - Loop engineering vs graphs, the real difference • 2:33:08 - Build your own multi-tool agent graph Save this video, because it's the only one that can actually take you to your $2,000+ profit.

Free 3-hour course from an ex-Google engineer. AI agents, graph engineering, harness, agent loops. Covers more than most $500 paid courses. This is the exact playbook to learn how to actually build and monetize AI agents. Don't miss your shot, save it now. • 0:00 - Design an AI agent system from scratch • 7:38 - When your agent should hand off to a human • 19:27 - RAG and vector databases explained simply • 52:38 - Deploy your AI agent to Google Cloud • 1:25:57 - Turn AI agents into a paid business via WhatsApp • 1:33:00 - Turn conversations into real leads automatically • 2:24:01 - Loop engineering vs graphs, the real difference • 2:33:08 - Build your own multi-tool agent graph Save this video, because it's the only one that can actually take you to your $2,000+ profit.

unicode

142,418 views • 25 days ago

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 views • 2 months ago

AI isn't just changing the tools designers use. It's changing the way they think, prototype, and build. In this episode of Design Review, YC Head of Design eve joins Aaron Epstein to share the AI-first workflow she uses to design products, websites, and events. Using projects like Paxel, STATE OF THE ART, and YC Startup School as examples, she explains how coding agents are transforming everything from rapid prototyping and branding to design systems, and why the biggest bottleneck is no longer software. It's imagination. 00:00 - Eve's AI-First Design Workflow 01:27 - Why She Designs With Her Voice 03:44 - Paxel: Spotify Wrapped for Coding Sessions 07:13 - Building Tools for Yourself 11:01 - Turning Coding Transcripts Into Feedback 12:53 - The Story Behind SOTA Zine 16:57 - Designing With Context, Not Prompts 21:07 - How to Get Better AI Design Outputs 23:20 - Building an Interactive Map of San Francisco 25:17 - Behind Startup School's Visual Identity 29:59 - The Future of Design

AI isn't just changing the tools designers use. It's changing the way they think, prototype, and build. In this episode of Design Review, YC Head of Design eve joins Aaron Epstein to share the AI-first workflow she uses to design products, websites, and events. Using projects like Paxel, STATE OF THE ART, and YC Startup School as examples, she explains how coding agents are transforming everything from rapid prototyping and branding to design systems, and why the biggest bottleneck is no longer software. It's imagination. 00:00 - Eve's AI-First Design Workflow 01:27 - Why She Designs With Her Voice 03:44 - Paxel: Spotify Wrapped for Coding Sessions 07:13 - Building Tools for Yourself 11:01 - Turning Coding Transcripts Into Feedback 12:53 - The Story Behind SOTA Zine 16:57 - Designing With Context, Not Prompts 21:07 - How to Get Better AI Design Outputs 23:20 - Building an Interactive Map of San Francisco 25:17 - Behind Startup School's Visual Identity 29:59 - The Future of Design

Y Combinator

102,871 views • 1 month ago

Jensen Huang just called the exact top of the pharmaceutical industry. Not a pivot. Not a disruption. An extinction event. Huang: “Where do I think the next amazing revolution is going to come? And this is going to be flat out one of the biggest ones ever. There’s no question that digital biology is going to be it.” The medical establishment has spent centuries playing a chaotic game of trial and error. We’re about to mathematically engineer the human operating system. Huang: “For the very first time in human history, biology has the opportunity to be engineering, not science. When something becomes engineering, not science, it becomes less sporadic and exponentially improving.” Biology is no longer the dark art of random discovery. It’s a predictable, compounding execution loop. Translate the chaotic variables of chemistry into the laws of computer science and you stop waiting for accidental breakthroughs. You simply compute the cure. That line should terrify every pharmaceutical executive alive. Huang: “It can compound on the benefits of the previous years. And every researcher’s contributions compound on each other.” For decades, drug discovery has been an isolated, artisanal process. One lab. One team. One molecule. Years of blind iteration. The algorithm just shattered that entire bottleneck. Every failed protein fold, every successful synthetic molecule instantly trains the foundational model. Makes the next iteration mathematically smarter. Huang: “We’re going to have incredible tools that bring the world of biology, which is very chaotic and constantly changing and diverse and complex, into the world of computer science. And that is going to be profound.” Incumbent pharma looks at the human body and sees an unmanageable wall of variables. Engineers look at that exact same body and see raw data waiting to be compiled. No longer guessing how a molecule will react in the physical world. Running millions of zero-cost simulated iterations before a single test tube is ever touched. Rip the chaotic friction out of the physical lab and drop it directly into a massive GPU cluster? The timeline to map, edit, and optimize the biological machine doesn’t shrink. It collapses.

Jensen Huang just called the exact top of the pharmaceutical industry. Not a pivot. Not a disruption. An extinction event. Huang: “Where do I think the next amazing revolution is going to come? And this is going to be flat out one of the biggest ones ever. There’s no question that digital biology is going to be it.” The medical establishment has spent centuries playing a chaotic game of trial and error. We’re about to mathematically engineer the human operating system. Huang: “For the very first time in human history, biology has the opportunity to be engineering, not science. When something becomes engineering, not science, it becomes less sporadic and exponentially improving.” Biology is no longer the dark art of random discovery. It’s a predictable, compounding execution loop. Translate the chaotic variables of chemistry into the laws of computer science and you stop waiting for accidental breakthroughs. You simply compute the cure. That line should terrify every pharmaceutical executive alive. Huang: “It can compound on the benefits of the previous years. And every researcher’s contributions compound on each other.” For decades, drug discovery has been an isolated, artisanal process. One lab. One team. One molecule. Years of blind iteration. The algorithm just shattered that entire bottleneck. Every failed protein fold, every successful synthetic molecule instantly trains the foundational model. Makes the next iteration mathematically smarter. Huang: “We’re going to have incredible tools that bring the world of biology, which is very chaotic and constantly changing and diverse and complex, into the world of computer science. And that is going to be profound.” Incumbent pharma looks at the human body and sees an unmanageable wall of variables. Engineers look at that exact same body and see raw data waiting to be compiled. No longer guessing how a molecule will react in the physical world. Running millions of zero-cost simulated iterations before a single test tube is ever touched. Rip the chaotic friction out of the physical lab and drop it directly into a massive GPU cluster? The timeline to map, edit, and optimize the biological machine doesn’t shrink. It collapses.

Dustin

780,611 views • 5 months ago

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 views • 4 months ago

How can generative AI and Robotics help advance drug discovery？ 🚀 Excited to introduce LUMI-lab! A foundation model-driven Self-Driving Lab (SDL) for autonomous ionizable lipid discovery in mRNA delivery 🤖🔍 🔬 What is LUMI-lab? LUMI-lab integrates molecular foundation models with autonomous robotic experiments to efficiently explore new LNPs (lipid nanoparticles, mRNA delivery vehicles) with minimal wet-lab data. 🔥 Key Highlights: - 🧠 Foundation model trained on 28M molecules using a three-step strategy: - Unsupervised pretraining to capture broad molecular knowledge - Continual pretraining to specialize in lipid-like molecules - Active learning fine-tuning within a closed-loop experimental system - 🤖 1,700+ new LNPs synthesized & tested across 10 iterative cycles - 🧪 Brominated lipids autonomously identified as a novel structural feature that enhances mRNA transfection—an insight previously unrecognized in LNP design - 🏆 20.3% in vivo CRISPR gene editing efficiency in lung epithelial cells—the highest reported for inhaled LNPs 🚀 Why it matters? LNPs are the backbone of mRNA therapeutics, yet discovery has been slow due to data scarcity. LUMI-lab shows that AI-powered autonomous labs can accelerate mRNA delivery innovation🚀💡 🌐 Beyond mRNA drugs, LUMI-lab exemplifies a scalable framework for AI-driven molecular discovery, pushing boundaries in material science & drug delivery. 📜 Read the preprint: 🔗 💻 Code available on GitHub: 🔗 #AI #DrugDiscovery #mRNA #LNP #SyntheticBiology 🙏 A huge team effort behind this work, with special appreciation to Bowen LI for driving the project. Kudos to Haotian Cui, @YueXu1995, Kuan Pang, Gen Li, and Bettycat567!

How can generative AI and Robotics help advance drug discovery？ 🚀 Excited to introduce LUMI-lab! A foundation model-driven Self-Driving Lab (SDL) for autonomous ionizable lipid discovery in mRNA delivery 🤖🔍 🔬 What is LUMI-lab? LUMI-lab integrates molecular foundation models with autonomous robotic experiments to efficiently explore new LNPs (lipid nanoparticles, mRNA delivery vehicles) with minimal wet-lab data. 🔥 Key Highlights: - 🧠 Foundation model trained on 28M molecules using a three-step strategy: - Unsupervised pretraining to capture broad molecular knowledge - Continual pretraining to specialize in lipid-like molecules - Active learning fine-tuning within a closed-loop experimental system - 🤖 1,700+ new LNPs synthesized & tested across 10 iterative cycles - 🧪 Brominated lipids autonomously identified as a novel structural feature that enhances mRNA transfection—an insight previously unrecognized in LNP design - 🏆 20.3% in vivo CRISPR gene editing efficiency in lung epithelial cells—the highest reported for inhaled LNPs 🚀 Why it matters? LNPs are the backbone of mRNA therapeutics, yet discovery has been slow due to data scarcity. LUMI-lab shows that AI-powered autonomous labs can accelerate mRNA delivery innovation🚀💡 🌐 Beyond mRNA drugs, LUMI-lab exemplifies a scalable framework for AI-driven molecular discovery, pushing boundaries in material science & drug delivery. 📜 Read the preprint: 🔗 💻 Code available on GitHub: 🔗 #AI #DrugDiscovery #mRNA #LNP #SyntheticBiology 🙏 A huge team effort behind this work, with special appreciation to Bowen LI for driving the project. Kudos to Haotian Cui, @YueXu1995, Kuan Pang, Gen Li, and Bettycat567!

Bo Wang

27,626 views • 1 year ago

Demis Hassabis explains Isomorphic Labs' 10x drug discovery engine, and why solving disease could also create a multi-hundred-billion-dollar business "If you ask me, the number one thing AI can do for humanity, it would be to solve hundreds of terrible diseases. I can't imagine a better use case for AI." "If you could revolutionize the drug discovery process, make it 10x faster and more efficient, and more likely to pass through the clinical trials because you can predict the properties better, that has to also be of enormous commercial value too." "I hope to do both with Isomorphic." "Build a multi-hundred-billion-dollar business. I think it has that potential, as well as being incredibly beneficial for society and humanity." The real health AI prize is not another chatbot. It is compressing the path from a predicted drug property to a clinical trial, then turning that speed into treatments for hundreds of diseases. Demis is making a rare dual bet: the most valuable AI company in biology may also deliver AI's most valuable public benefit. - Demis Hassabis (Demis Hassabis), CEO of Google DeepMind and founder of Isomorphic Labs, on Bloomberg TV

Demis Hassabis explains Isomorphic Labs' 10x drug discovery engine, and why solving disease could also create a multi-hundred-billion-dollar business "If you ask me, the number one thing AI can do for humanity, it would be to solve hundreds of terrible diseases. I can't imagine a better use case for AI." "If you could revolutionize the drug discovery process, make it 10x faster and more efficient, and more likely to pass through the clinical trials because you can predict the properties better, that has to also be of enormous commercial value too." "I hope to do both with Isomorphic." "Build a multi-hundred-billion-dollar business. I think it has that potential, as well as being incredibly beneficial for society and humanity." The real health AI prize is not another chatbot. It is compressing the path from a predicted drug property to a clinical trial, then turning that speed into treatments for hundreds of diseases. Demis is making a rare dual bet: the most valuable AI company in biology may also deliver AI's most valuable public benefit. - Demis Hassabis (Demis Hassabis), CEO of Google DeepMind and founder of Isomorphic Labs, on Bloomberg TV

Karl Mehta

46,918 views • 1 month ago

$Super proud and excited to finally present LiteMol-1. This is our first foundation model from LiteFold, pre-trained from scratch. Today, LiteMol-1 can generate small molecules, peptides, cyclic peptides, depsipeptides, peptides with ncAAs, macrocycles, and PROTACs. Across our peptide and small-molecule evaluations, the model shows competitive results. In several settings, we are on-par with or better than frontier structure-based models, at a fraction of the generation cost. But the part I find most interesting is that this is a model for agents. We have seen ourselves how much compute, and how many tokens it can take to generate good binders using frontier structure-based models. Sometimes you need to generate tens of thousands of designs just to get a handful worth taking forward. Now put this inside an AutoResearch loop. The agent has to continuously parse structures, inspect PDB/CIF files, compare candidates, run evaluations, modify the design, and repeat the whole thing again. It becomes extremely expensive very quickly. Sequence space gives us a very different interface. LLMs are much more efficient at inspecting and manipulating compact molecular representations like SMILES than repeatedly operating over full structural files. So LiteMol-1 becomes something like an infinite molecular canvas for the agent. For a given target and objective, the model can continuously propose what a biomolecule could look like. The agent can inspect those generations, take inspiration from them, preserve certain regions, edit others, optimize them, score them, and generate again. Generate → inspect → evaluate → edit → generate again. There is another problem I care a lot about. Most molecule design models today are heavily optimized around binding. But binding is only one part of whether something eventually becomes a therapeutic. What about ADME? Toxicity? Selectivity? Solubility? Membrane permeability? Synthesizability? For this, we also built a Monte Carlo Tree Search-based multi-objective generation framework around LiteMol-1. Instead of combining everything into one score, the search keeps multiple strong candidates, each balancing the desired properties in a different way. As our scoring functions and verifiers get better, the generation system gets better too. We can start steering molecules not just toward “binds well”, but toward a broader therapeutic design specification. The bottleneck slowly moves from simply generating molecules to having sufficiently good verifiers and scoring functions to tell us what is actually worth generating. Check out our technical research blog post for all the details. At LiteFold, our research is focused on engineering biomolecules and building systems that can carefully forecast their pre-clinical success. To stay updated on our research, follow LiteFold. Cheers!$

Super proud and excited to finally present LiteMol-1. This is our first foundation model from LiteFold, pre-trained from scratch. Today, LiteMol-1 can generate small molecules, peptides, cyclic peptides, depsipeptides, peptides with ncAAs, macrocycles, and PROTACs. Across our peptide and small-molecule evaluations, the model shows competitive results. In several settings, we are on-par with or better than frontier structure-based models, at a fraction of the generation cost. But the part I find most interesting is that this is a model for agents. We have seen ourselves how much compute, and how many tokens it can take to generate good binders using frontier structure-based models. Sometimes you need to generate tens of thousands of designs just to get a handful worth taking forward. Now put this inside an AutoResearch loop. The agent has to continuously parse structures, inspect PDB/CIF files, compare candidates, run evaluations, modify the design, and repeat the whole thing again. It becomes extremely expensive very quickly. Sequence space gives us a very different interface. LLMs are much more efficient at inspecting and manipulating compact molecular representations like SMILES than repeatedly operating over full structural files. So LiteMol-1 becomes something like an infinite molecular canvas for the agent. For a given target and objective, the model can continuously propose what a biomolecule could look like. The agent can inspect those generations, take inspiration from them, preserve certain regions, edit others, optimize them, score them, and generate again. Generate → inspect → evaluate → edit → generate again. There is another problem I care a lot about. Most molecule design models today are heavily optimized around binding. But binding is only one part of whether something eventually becomes a therapeutic. What about ADME? Toxicity? Selectivity? Solubility? Membrane permeability? Synthesizability? For this, we also built a Monte Carlo Tree Search-based multi-objective generation framework around LiteMol-1. Instead of combining everything into one score, the search keeps multiple strong candidates, each balancing the desired properties in a different way. As our scoring functions and verifiers get better, the generation system gets better too. We can start steering molecules not just toward “binds well”, but toward a broader therapeutic design specification. The bottleneck slowly moves from simply generating molecules to having sufficiently good verifiers and scoring functions to tell us what is actually worth generating. Check out our technical research blog post for all the details. At LiteFold, our research is focused on engineering biomolecules and building systems that can carefully forecast their pre-clinical success. To stay updated on our research, follow LiteFold. Cheers!

Anindyadeep

51,436 views • 7 days ago

AI can’t yet one-shot an entire product—but with the rise of vibe coding, supercharged developers are getting close. Part intuition and experimentation, part validation, it's the new frontier of software development. YC's Tom Blomfield (Tom Blomfield) has spent the last month building side projects with tools like Claude Code, Windsurf, and Aqua, seeing just how far you can push modern LLMs. From writing full-stack apps to debugging with a single copy paste of an error message, AI is becoming a legit collaborator in the dev process. With tips from YC founders in the Spring batch, this is a playbook for anyone who wants to get the most out of vibe coding and build faster.

AI can’t yet one-shot an entire product—but with the rise of vibe coding, supercharged developers are getting close. Part intuition and experimentation, part validation, it's the new frontier of software development. YC's Tom Blomfield (Tom Blomfield) has spent the last month building side projects with tools like Claude Code, Windsurf, and Aqua, seeing just how far you can push modern LLMs. From writing full-stack apps to debugging with a single copy paste of an error message, AI is becoming a legit collaborator in the dev process. With tips from YC founders in the Spring batch, this is a playbook for anyone who wants to get the most out of vibe coding and build faster.

Y Combinator

151,446 views • 1 year ago

Alex on why AI + fully autonomous labs will compress drug discovery from five years to two: "If scientists are armed with agentic infrastructure that has an intelligence that's a multiple of Einstein, they will do science faster, with higher probability, for lower cost, and have greater impact." "AI coming into the discovery of medicines is one of the biggest unlocks we will see in history because it means we're no longer constrained by our hands or minds. We can identify all n number of hypotheses that could exist, figure out the best experiment to run, and run those 24/7." "The sheer ability to be more comprehensive in our hypothesis set, and to run experimentation at unprecedented scale, means we're going to speed breakthroughs from timelines that take three to five years to timelines that take less than a couple of years."

Alex on why AI + fully autonomous labs will compress drug discovery from five years to two: "If scientists are armed with agentic infrastructure that has an intelligence that's a multiple of Einstein, they will do science faster, with higher probability, for lower cost, and have greater impact." "AI coming into the discovery of medicines is one of the biggest unlocks we will see in history because it means we're no longer constrained by our hands or minds. We can identify all n number of hypotheses that could exist, figure out the best experiment to run, and run those 24/7." "The sheer ability to be more comprehensive in our hypothesis set, and to run experimentation at unprecedented scale, means we're going to speed breakthroughs from timelines that take three to five years to timelines that take less than a couple of years."

Patrick OShaughnessy

39,883 views • 4 months ago

For the first time in human history, we are teaching a Foundation Model to master the diverse tasks of medicinal chemists, biologists, and computational scientists all in one place. In our latest collaboration with Liquid AI, we are moving away from fragmented, specialized tools toward a single, super-intelligent model. What surprised me most? This model isn't just performing at reasonable levels—it has started outperforming specialist models across physics-based tasks, imaging, and longitudinal data. Why this changes everything: -Synergy over Specialization: Fine-tuning on specific tasks has unlocked unexpected capabilities in synergetic areas, opening a new frontier in multimodal AI research. -Zero-Shot Potential: We are building a model that can perform out-of-scope tasks, moving us closer to an "AI deity" for drug discovery. -Quality First: The goal isn't just to bypass regulations to save time; it’s about using these synergies to develop better, more effective drugs. We are no longer just looking at linear regression or simple text; we are looking at the future of how humanity fights disease. #LiquidAI #InsilicoMedicine #GenerativeAI #DrugDiscovery #DeepTech #BiotechInnovation

For the first time in human history, we are teaching a Foundation Model to master the diverse tasks of medicinal chemists, biologists, and computational scientists all in one place. In our latest collaboration with Liquid AI, we are moving away from fragmented, specialized tools toward a single, super-intelligent model. What surprised me most? This model isn't just performing at reasonable levels—it has started outperforming specialist models across physics-based tasks, imaging, and longitudinal data. Why this changes everything: -Synergy over Specialization: Fine-tuning on specific tasks has unlocked unexpected capabilities in synergetic areas, opening a new frontier in multimodal AI research. -Zero-Shot Potential: We are building a model that can perform out-of-scope tasks, moving us closer to an "AI deity" for drug discovery. -Quality First: The goal isn't just to bypass regulations to save time; it’s about using these synergies to develop better, more effective drugs. We are no longer just looking at linear regression or simple text; we are looking at the future of how humanity fights disease. #LiquidAI #InsilicoMedicine #GenerativeAI #DrugDiscovery #DeepTech #BiotechInnovation

Alex Zhavoronkov, PhD (aka Aleksandrs Zavoronkovs)

10,544 views • 5 months ago