{"podcast":{"title":"Latent Space: The AI Engineer Podcast","slug":"latent-space-ai-engineer","podcast_index_feed_id":6058902,"rss_url":"https://api.substack.com/feed/podcast/1084089.rss","website_url":"https://www.latent.space/podcast","image_url":"https://substackcdn.com/feed/podcast/1084089/ca7468da5614a246d2906ee8926f6de7.jpg","author":"Latent.Space","episode_count":204,"summary":"The AI Engineer newsletter + Top technical AI podcast. How leading labs build Agents, Models, Infra, & AI for Science. See https://latent.space/about for highlights from Greg Brockman, Andrej Karpathy, George Hotz, Simon Willison, Soumith Chintala et al!","last_synced_at":null,"page_url":"https://stenobird.com/podcast/latent-space-ai-engineer"},"episode":{"title":"🔬Doing Vibe Physics — Alex Lupsasca, OpenAI","slug":"doing-vibe-physics-alex-lupsasca-openai","published_at":"2026-05-05T20:34:11+00:00","page_url":"https://stenobird.com/podcast/latent-space-ai-engineer/doing-vibe-physics-alex-lupsasca-openai","show_page_url":"https://stenobird.com/podcast/latent-space-ai-engineer","url":"https://www.latent.space/p/lupsasca","audio_url":"https://api.substack.com/feed/podcast/196292432/c069e965927403857341ef50a53384b8.mp3","summary":"Theoretical physicist Alex Lupsasca describes the shift from using AI for administrative tasks to using it for frontier-level scientific discovery. He details how advanced reasoning models can now reproduce complex research papers and solve unsolved problems in quantum field theory in minutes.","meta_description":"Alex Lupsasca (OpenAI) discusses how LLMs are moving beyond writing emails to solving complex theoretical physics problems and accelerating scientific dis…","key_points":["Main idea: The 'Jagged Frontier' of AI has moved from simple text generation to performing high-level mathematical reasoning in physics","Practical takeaway: Using 'priming' techniques—such as providing textbook warmup problems—can unlock advanced reasoning capabilities in models like GPT-5","Failure mode: As models become capable of generating complex calculations, the primary bottleneck shifts from computation to human verification","Main idea: AI-driven acceleration is significantly shortening the gap between the discovery of a mathematical truth and its formal publication","Practical takeaway: Future research workflows will likely rely on automating the verification of AI-generated proofs to keep pace with rapid discovery"],"chapters":[{"start_ms":60000,"title":"The Breakthrough Prize Winner","summary":"Introduction to Alex Lupsasca, his background in theoretical physics, and his recent recognition with the New Horizons Breakthrough Prize."},{"start_ms":470000,"title":"The Framework of Physics","summary":"A discussion on the fundamental principles of the physical world and the triumphs of 20th-century physics."},{"start_ms":895000,"title":"Gluon Amplitudes and Quantum Probability","summary":"An exploration of the mathematical functions describing how gluons interact within the strong force."},{"start_ms":1295000,"title":"Identifying Loopholes in Particle Alignment","summary":"Examining the specific regime where particle alignment allows for non-zero amplitudes, challenging previous assumptions."},{"start_ms":1710000,"title":"The Complexity of Feynman Diagrams","summary":"Discussing the extreme computational difficulty of expanding diagrams when particles are aligned."},{"start_ms":2125000,"title":"AI as a Research Partner","summary":"Alex recounts how OpenAI's research into stronger physics capabilities enabled models to derive complex proofs."},{"start_ms":2530000,"title":"The Acceleration of Scientific Publication","summary":"How the rapid release of new findings is being enabled by the integration of AI into the research lifecycle."},{"start_ms":3350000,"title":"The Growing Gap in Research","summary":"The widening distance between established knowledge and the frontier of new discovery, and how AI bridges it."}],"topics":["Theoretical Physics","Artificial Intelligence","Quantum Field Theory","Large Language Models","Scientific Discovery","OpenAI","Mathematical Reasoning","Breakthrough Prize"],"duration_seconds":5511,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/latent-space-ai-engineer/episodes/doing-vibe-physics-alex-lupsasca-openai/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/latent-space-ai-engineer/doing-vibe-physics-alex-lupsasca-openai.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}