AILatent Space
This episode delves into Zera Therapeutics' AI drug discovery platform, focusing on their X-Cell model. Guests Bo Wang and Ci Chu explain how X-Cell leverages high-throughput causal data generation (Perturb-seq) and a novel diffusion model architecture with biological priors to predict cellular responses to interventions. They discuss the model's generalization capabilities to unseen biological contexts, the current bottlenecks in virtual cell modeling, and the evolving roles of academia and industry in AI for science.
- Academic freedom isn't a luxury, it's a speed advantage. Bo Wang argues university labs, free from immediate profit pressures, are the wellspring for radically new concepts, like the biological priors behind Zera Therapeutics' X-Cell model. This deep, unconstrained thinking is hard to replicate in… Read →
- Even with advanced AI drug discovery platforms like Zera Therapeutics’ X-Cell model, the current bottleneck for virtual cell modeling isn't just compute power or algorithms, but the type of data we can actually collect. Read →
- Zera Therapeutics' X-Cell model uses a diffusion language model architecture to predict cellular responses, departing from traditional auto-regressive (GPT-like) methods. Read →
- Zera Therapeutics' X-Cell AI, a novel diffusion model, predicts how cells respond to interventions using high-throughput causal data (Perturb-seq). Read →
AILatent Space
This episode explores how Genesis Molecular AI is leveraging advanced AI, particularly diffusion models, to revolutionize drug discovery by achieving unprecedented accuracy in protein-ligand structure prediction. Guests Evan Fineberg and Sergey Udov discuss their Pearl model, the critical 1 angstrom resolution threshold, and their vision for AI agents automating drug discovery. They also delve into the challenges and opportunities of integrating wet lab data and reinforcement learning into their cutting-edge AI pipelines.
- The highest leverage for AI in healthcare isn't identifying new disease targets or optimizing clinical trials; it's in the drug discovery and design process itself. Read →
- The 1 Angstrom Cliff: Genesis Molecular AI's Pearl model demonstrates that for drug discovery, 1 angstrom (Å) resolution isn't just nice-to-have; it's the absolute minimum threshold to reliably predict protein-ligand interactions. Anything less, and your drug fails. Read →
AILatent Space
This episode features Carina Hong, CEO of Axiom Math, discussing her company's vision for formal verification as the foundation for superintelligence and AGI, backed by a significant Series A funding round. Hong details Axiom's use of Lean to achieve superhuman performance in mathematics, tackles the challenges of specification and mathematical discovery in AI-driven proofs, and introduces the AXL API to foster collaborative formal verification. She also outlines the broad commercial applications of verified AI, particularly in mission-critical hardware and evolving software domains.
- AI, particularly Lean-based systems, struggles with highly creative mathematical domains like combinatorics because the necessary steps are often too intuitive and "quite creative," according to Carina Hong. Read →
- Axiom Math secured a $200 million Series A funding round, valuing the company at $1.6 billion, to advance "verified AI." Read →
- Axiom Math, fresh off a $200 million Series A, aims to move formal verification beyond mere error correction, focusing instead on scaling "brilliance" to achieve superhuman math performance. Read →
- AI, particularly formal systems like those based on Lean, struggles with true mathematical discovery—the creative process of formulating conjectures and constructing examples before a formal proof begins. Read →
- Axiom Math's AI achieved a perfect 120 score on the challenging Putnam exam in December 2025, outperforming the best human (110 points) and leading LLM Deepseek (103 points). Read →