swyx

Swyx, organizer of the AI Engineer Summit and host of Latent Space, shares insights on the evolving landscape of AI engineering. He discusses the innovative Model Context Protocol (MCP) and the rising influence of AI agents in businesses. Listeners will find engaging ideas about transforming AI conferences into hands-on experiences and the creative concept of 'vibe coding' in development. Swyx also emphasizes the importance of trust and community engagement in navigating the challenges of AI adoption and integration.

Swyx, AI writer and commentator, and Sebastian Raschka, ML professor specializing in interpretability, join to dissect distillation, benchmarks, and model memorization. They debate detection limits for API-based distillation, teacher-student dynamics, and logits vs open-weight approaches. Sweebench and its vulnerabilities to leakage and curation issues are also explored.

VB (OpenAI developer experience lead) and Vincent Koh (OpenClaw maintainer) join Peter Gostev (Arena contributor) and swyx (AI Engineer founder). They discuss Anthropic’s Mythos preview and its security implications. Meta’s Muse Spark and new infra get attention. Z.AI’s GLM 5.1, video model advances, agentic memory tools, and evaluation tooling rounds out the conversation.

Jessica Gallegos of Google DeepMind breaks down the transformative features of VEO 3.1, highlighting its new creative controls for video generation. Kyle Corbett from OpenPipe shares insights on reinforcement learning's resurgence and the benefits of serverless RL infrastructure. Lastly, swyx introduces SweetGrep, a powerful new tool for fast code search, emphasizing its design for efficiency in agentic tasks. The conversation touches on innovative discoveries in cancer biology that open new avenues for AI in science.

Swyx and Alessio, co-hosts of the Latent Space podcast, delve into the dynamism of AI development. They discuss the imminent release of GPT-5 and emerging competitors like Anthropic. The conversation reveals insights on alternative AI architectures and the rise of wearable technology in the market. They also explore the introduction of innovative devices such as the Open Interpreter and the significance of smaller AI chip companies challenging industry giants like NVIDIA. Their perspectives offer a fascinating glimpse into the future of AI.