

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

472 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.

911 snips
Jul 23, 2025 • 56min
AI is Eating Search
Robert McCloy, co-founder of Scrunch AI and former CTO of Hearsay, discusses the dramatic shift in search dynamics driven by AI technologies like ChatGPT. He reveals that AI is set to rival traditional search engines by 2026, prompting businesses to rethink SEO strategies. Conversion rates from AI-driven traffic are outperforming conventional methods. McCloy emphasizes the importance of user intent and structured content while navigating this new landscape, exploring how AI tools are reshaping consumer interactions and optimizing content on-the-fly.

1,338 snips
Jul 16, 2025 • 1h 16min
Cline: the open source coding agent that doesn't cut costs
Saoud Rizwan, a key contributor at Cline, chats about developing innovative coding agents and enhancing VS Code through their open-source extension. He discusses the plan + act paradigm, which revolutionizes coding interactions. The conversation also dives into the surprising use of IDEs by non-tech users for marketing tasks. Challenges in monetizing the Model Code Plugin ecosystem and the evolving complexity of programming tasks are also highlighted, providing intriguing insights into the future of coding and automation.

1,178 snips
Jul 11, 2025 • 1h 4min
Personalized AI Language Education — with Andrew Hsu, Speak
In this engaging discussion, Andrew Hsu, CTO of Speak and a former Teal Fellow, dives into the innovative world of AI-driven language education. He shares how Speak has transformed language learning, particularly in South Korea, by creating personalized AI tutors that rival human instruction. The conversation highlights the app's evolution, its unique teaching methods, and the challenges of adapting to diverse cultural contexts. Hsu also emphasizes the importance of real-world language applications and the future of immersive, technology-enhanced learning.

919 snips
Jul 9, 2025 • 49min
AI Video Is Eating The World — Olivia and Justine Moore, a16z
Justine and Olivia Moore, partners at a16z, share their insights on the explosive growth of AI-generated video content. They discuss how platforms like TikTok are evolving to feature collaborative characters, enhancing emotional connections with audiences. The Moores explore the democratization of creativity through AI, highlighting the shift from niche trends to mainstream engagement. They also touch on tools like Comfy UI that simplify video workflows, making viral content creation accessible for everyone. Tune in for their strategies on crafting compelling and relatable media!

704 snips
Jul 2, 2025 • 1h 18min
Information Theory for Language Models: Jack Morris
In this engaging discussion, Jack Morris, a PhD grad student at Cornell Tech, unpacks the intricate relationship between information theory and large language models. He shares fascinating insights about the efficiency of data representation in AI, particularly in models like GPT-3. The conversation dives into the revolutionary concepts of embedding inversion and the implications for model alignment and security. Jack also explores the potential of emerging programming languages like Mojo, merging performance with innovation in AI research.

1,233 snips
Jun 19, 2025 • 0sec
Scaling Test Time Compute to Multi-Agent Civilizations — Noam Brown, OpenAI
Noam Brown, who leads the multi-agent team at OpenAI, shares insights from his groundbreaking work in AI, especially in competitive strategy games like poker and Diplomacy. He discusses the fascinating impact of AI on human gameplay and critiques the constraints of the System 1/2 thinking model in AI reasoning. The conversation also touches on the challenges of test-time compute limitations, multi-agent intelligence, and innovative applications of AI tools like Codex and Windsurf, while pondering the future of AI civilizations.

1,087 snips
Jun 13, 2025 • 0sec
The Shape of Compute (Chris Lattner of Modular)
Chris Lattner, the visionary behind LLVM and Swift, now leads Modular, pushing the boundaries of GPU programming with Mojo. He discusses breaking NVIDIA's hold on the market and achieving AMD performance levels. The conversation delves into Mojo's design, merging simplicity with advanced capabilities for AI applications. Lattner also shares insights on community engagement, the importance of open-source contributions, and his reflections on leadership, emphasizing the blend of technical innovation and personal balance in a startup environment.

934 snips
Jun 6, 2025 • 0sec
The Utility of Interpretability — Emmanuel Amiesen
Emmanuel Amiesen, lead author at Anthropic focusing on AI model interpretability, joins guest host Vibhu Sapra, an AI enthusiast with a rich background in economics and data science. They dive into groundbreaking tools for analyzing language model behaviors, revealing how circuit tracing enhances interpretability. The duo explores model complexities, the significance of feature interpretation, and the challenges of biases in AI systems. They also discuss the interplay between research and engineering roles, emphasizing the importance of transparency and safety in AI development.

705 snips
Jun 3, 2025 • 0sec
[AIEWF Preview] Containing Agent Chaos — Solomon Hykes
In this discussion, Solomon Hykes, the creator of Docker and founder of Dagger, dives into the evolution of developer workflows powered by container technology. He highlights Dagger's role in automating software delivery and the importance of creating intuitive experiences for coding agents. Solomon emphasizes the need for standardization in agent environments and explores the balance between simplicity and modularity, using a Lego analogy. He also examines the challenges of ephemeral applications and the future landscape of AI-driven development.