The podcast by and for AI Engineers! In 2025, over 10 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 Sponsorship and business inquiries: [email protected] www.latent.space
In this episode of the Latent Space podcast, Alessio and Swyx are joined by Will Brown from Prime Intellect to discuss the newly released Claude 4. The conversation covers Claude 4's emphasis on coding and agentic capabilities, downplaying reasoning aspects compared to previous versions. They speculate on the differenc...
This episode explores OpenAI's newly released ChatGPT Codex and its implications for software development, focusing on its capabilities as an independent software engineering agent. The discussion begins with Alexander Embiricos and Josh Ma from OpenAI detailing their involvement in the Codex project, from its origins ...
This episode explores Claude Code, Anthropic's CLI-based coding agent, detailing its origins as an internal research tool and its evolution into a publicly available product. Boris Cherny, one of the creators, explains that Claude Code provides terminal access to Claude, enabling it to execute bash commands and access ...
This episode explores the evolution and future of vector databases in the context of Retrieval Augmented Generation (RAG) applications. Against the backdrop of the rapid rise and subsequent perceived decline of dedicated vector database companies like Pinecone, the discussion analyzes the integration of vector search ...
This episode explores the evolution and current state of E2B, a cloud computing platform designed for AI agents. Against the backdrop of the initial development of DevBook, an interactive documentation tool, the conversation details the pivot to E2B, driven by the emergence of GPT 3.5 and the need for scalable sandbox...
This episode explores the release of GPT 4.1, GPT 4.1 Mini, and GPT 4.1 Nano, focusing on improvements designed to enhance developer experience. Against the backdrop of previous model releases (like GPT 4.0 and GPT 4.5), the hosts and guests discuss the rationale behind the version numbering and the models' architectu...
The podcast explores the GPU cloud market, particularly analyzing CoreWeave's success and SF Compute's unique approach. Evan Conrad from SF Compute explains CoreWeave's focus on long-term contracts with low-risk clients as key to securing favorable financing. He contrasts this with the challenges faced by CPU cloud pro...
This episode explores the complexities of the GPU cloud market, focusing on CoreWeave's successful IPO and the broader implications for industry players. Against the backdrop of CoreWeave's strategy of securing long-term contracts with low-risk clients, the discussion analyzes why this model deviates from traditional ...
This episode explores the Model Context Protocol (MCP), a new standard designed to enhance the functionality of AI applications by enabling seamless integration with external plugins. Against the backdrop of the 2023-2025 "agent open standard wars," MCP emerged as a leading contender, attracting significant attention ...
The Model Context Protocol (MCP) is explored as a means for AI applications to extend functionality through a client-server plugin system, likened to a USB-C port for AI. Justin Spahr-Summers and David Soria-Para from Anthropic, the co-creators of MCP, detail its origin as an internal developer tool to integrate Anthro...
The podcast explores recent surprises and future trends in AI, particularly focusing on open source models and AI engineering. The speakers were surprised by the speed at which open source models, especially DeepSeek, caught up to closed source models, though they debate whether this is sustainable. They also discuss t...
The podcast explores recent surprises, overhyped trends, and future opportunities within the AI landscape. Reasoning models and the pace of open-source model development are highlighted as positive surprises, while AI agent frameworks are considered potentially overhyped. The discussion questions whether new companies ...
This episode explores the evolving landscape of AI agents, focusing on their definition, capabilities, and future implications. Against the backdrop of the recent AI Engineer Conference, the discussion centers on Dharmesh Shah's pragmatic definition of an AI agent as "AI-powered software that accomplishes a goal," spa...
This podcast interviews Kevin Ben-Smith, co-founder of Snipd, an AI-powered podcast app. The conversation begins with a discussion of the AI Engineer Summit, then delves into Snipd's features, including AI-driven transcription, summarization, chapterization, and a unique "snipping" function for saving key insights. B...
This podcast episode announces OpenAI's new API updates, focusing on the Responses API, which unifies and supersedes the existing chat completions and Assistants APIs. The discussion covers new built-in tools like web search (offering significantly improved accuracy over GPT 4.0), improved file search with metadata fi...
This podcast interviews David Hershey from Anthropic about Claude Plays Pokémon, a project where Anthropic's Claude language model plays Pokémon Red. The interview covers the project's origins, technical implementation (including tools like a Navigator to address Claude's vision limitations), and the challenges of usi...
This podcast interviews Paul Klein, CEO of Browserbase, a headless browser infrastructure company. The conversation covers Browserbase's technology, focusing on the challenges of running browsers at scale in the cloud and the company's unique approach using Kubernetes and Firecracker. Klein discusses the company's fr...
This Latent Space podcast episode interviews Aarush Selvan and Mukund Sridhar, the product and tech leads for Google's Gemini Deep Research. The discussion centers on Deep Research's functionality as a research assistant, its iterative research planning process (allowing user edits), and the technical challenges of bu...
Follow this podcast in Podwise
Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.
