Latent Space: The AI Engineer Podcast
swyx + Alessio
The podcast by and for AI Engineers! In 2024, over 2 million readers and listeners came to Latent Space to hear about news, papers and interviews in Software 3.0.We cover Foundation Models changing every domain in Code Generation, Multimodality, AI Agents, GPU Infra and more, directly from the founders, builders, and thinkers involved in pushing the cutting edge. Striving to give you both the definitive take on the Current Thing down to the first introduction to the tech you'll be using in the next 3 months! We break news and exclusive interviews from OpenAI, Anthropic, Gemini, Meta (Soumith Chintala), Sierra (Bret Taylor), tiny (George Hotz), Databricks/MosaicML (Jon Frankle), Modular (Chris Lattner), Answer.ai (Jeremy Howard), et al.Full show notes always on https://latent.space
Episodes
Mentioned books
1,469 snips
Oct 16, 2025 • 0sec
Why RL Won — Kyle Corbitt, OpenPipe (acq. CoreWeave)
Kyle Corbitt, co-founder and CEO of OpenPipe, discusses the shift from fine-tuning to reinforcement learning in AI. He highlights that many AI projects fail not due to capability, but reliability issues that can be resolved through continuous learning. Kyle introduces RULER, a system that simplifies reward assignment using LLMs to judge agent behaviors. He also critiques the impracticalities of GRPO and emphasizes the importance of realistic training environments for AI agents. Finally, he shares insights on the future of continual learning and serverless RL.
1,572 snips
Oct 7, 2025 • 0sec
DevDay 2025: Apps SDK, Agent Kit, MCP, Codex and why Prompting is More Important than Ever
Sherwin Wu, Head of Engineering at OpenAI, and Christina Huang, a Platform Experience Engineer, dive into the exciting features of AgentKit and the Apps SDK. They reveal how Christina built a customer support agent in under 8 minutes! The duo discusses the innovative shift in embedding apps directly within ChatGPT, the challenges of prompt optimization, and the significance of a visual workflow for complex agent systems. They also emphasize the role of human-in-the-loop approvals and share insights on why mastering prompting is more crucial than ever.
1,095 snips
Oct 2, 2025 • 0sec
Taste is your Moat (Dylan Field of Figma)
Dylan Field, CEO and co-founder of Figma, shares insights on the evolving role of design in the digital age. He discusses Figma Make, a tool aimed at turning ideas into prototypes quickly. Dylan emphasizes the need for natural language interfaces to foster creativity, while also addressing the importance of design quality as code generation advances. Delving into the concept of Figma as an aesthetic context repository, he explores how AI can enhance design representation without replacing designers, ensuring that aesthetics remain varied and innovative.
1,389 snips
Sep 25, 2025 • 0sec
Amp: The Emperor Has No Clothes
Quinn Slack, CEO of Sourcegraph, and Thorsten Ball, the lead engineer behind AMP, dive into the world of coding agents. They reveal their groundbreaking approach of shipping 15 times a day without code reviews. The duo debates the effectiveness of subagents and explores how AMP is reshaping workflows and team structures in software development. They also discuss the evolution of AI tooling, empowering users to craft their own enterprise software, and the critical need for agent-friendly logging practices. A fun and insightful look into the future of coding!
2,344 snips
Sep 11, 2025 • 0sec
Context Engineering for Agents - Lance Martin, LangChain
Lance Martin, a key figure at Langchain specializing in context engineering, dives deep into effective tools for AI agents. He discusses the critical importance of context management during tool interactions and differentiates it from traditional prompt engineering. The conversation highlights innovative strategies to improve information flow, reduce context loss, and tackle challenges like context poisoning. Lance also sheds light on the evolution of context engineering, exploring how new buzzwords and practices shape the future of AI technology.
1,031 snips
Sep 5, 2025 • 0sec
A Technical History of Generative Media
Dive into the groundbreaking world of generative media with insights from Fal.ai's founders. Discover their impressive pivot to diffusion models and the models that reshaped image generation. Explore the challenges and triumphs of scaling serverless GPU technologies. Learn about the rise of generative video in advertising and its cost advantages over traditional methods. The conversation also touches on content moderation, open-source innovations, and strategic revenue generation in this rapidly evolving landscape.
1,867 snips
Aug 29, 2025 • 0sec
Better Data is All You Need — Ari Morcos, Datology
Ari Morcos, CEO of Datology and former research scientist at Google and Meta, discusses the vital but overlooked area of data curation in AI. He emphasizes that high-quality data is essential for developing efficient models, arguing that the focus should shift from scaling models to improving data quality. Morcos recounts his journey from neuroscience to understanding that as data scales, the importance of model architecture diminishes. He advocates for automating data curation to enable organizations to harness the full potential of AI effectively.
1,997 snips
Aug 19, 2025 • 0sec
Long Live Context Engineering - with Jeff Huber of Chroma
Jeff Huber, Founder and CEO of Chroma, shares insights on the future of vector databases and the unique aspects of modern AI search. He discusses the challenges of context rot and the importance of context quality in AI applications. The conversation dives into retrieval strategies, memory management, and the evolution of transformer architecture. Huber also reflects on his previous startup experiences and the intersection of personal values with company culture, emphasizing the need for a cohesive brand identity in tech.
2,629 snips
Aug 15, 2025 • 0sec
Greg Brockman on OpenAI's Road to AGI
Greg Brockman, co-founder and president of OpenAI, shares insights on GPT-5's capabilities and the open-source initiative GPT-OSS. He discusses the evolution of machine learning from offline to dynamic online systems and explores how reinforcement learning influences AI refinement. The conversation dives into AI's role in coding enhancement, addressing the rise of self-improving coding agents. Brockman also touches on the aggressive pricing of GPT-5 and its implications for accessibility, framing a future where AI continues to learn and innovate.
709 snips
Jul 31, 2025 • 0sec
The RLVR Revolution — with Nathan Lambert (AI2, Interconnects.ai)
Nathan Lambert, an AI researcher from AI2 and Interconnects.ai, returns to explore the evolution of Reinforcement Learning with Verified Rewards (RLVR). He discusses how RLVR shifts from subjective feedback to verifiable reward signals, enhancing scalability and reliability. Lambert highlights the challenges of tool use in RL frameworks and showcases the Tulu model series aimed at democratizing AI development. The conversation dives into the balance of fine-tuning, user data significance, and the implications for future AI performance and design.
