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
131 snips
Jun 20, 2023 • 1h 13min
Commoditizing the Petaflop — with George Hotz of the tiny corp
In this conversation, George Hotz, known for his groundbreaking work in unlocking the iPhone and founding Comma.ai, delves into the innovations at tiny corp. He discusses the groundbreaking tinybox, a luxury AI computer poised to revolutionize personal computing, boasting impressive specs for local AI processing. George also tackles the commoditization of petaflop computing and the intricacies of multi-GPU design. Additionally, he explores the benefits of on-device AI training versus cloud solutions, emphasizing privacy and security in the evolving landscape of technology.
68 snips
Jun 14, 2023 • 1h 28min
Emergency Pod: OpenAI's new Functions API, 75% Price Drop, 4x Context Length (w/ Alex Volkov, Simon Willison, Riley Goodside, Joshua Lochner, Stefania Druga, Eric Elliott, Mayo Oshin et al)
In this engaging discussion, AI expert Alex Volkov, prompt injection specialist Simon Willison, and software engineer Riley Goodside dissect OpenAI's transformative Functions API. They dive into the significant 75% price drop and the increase in context length, exploring the implications for developers. Eric Elliott shares prompting techniques to enhance accuracy, while the panel addresses security concerns related to prompt injection. The conversation is rich with insights on coding efficiency, the future of AI tools, and the evolution of user interactions with these technologies.
47 snips
Jun 8, 2023 • 49min
From RLHF to RLHB: The Case for Learning from Human Behavior - with Jeffrey Wang and Joe Reeve of Amplitude
Join Jeffrey Wang, co-founder of Amplitude with over a decade in product analytics, and Joe Reeve, head of AI R&D, as they dive into the intricacies of AI and product development. They discuss the transition from RLHF to RLHB in learning from human behavior and the messiness of gathering quality feedback. The conversation highlights how AI is evolving in product analytics, the ethical considerations of data usage, and the balance between leveraging AI insights while prioritizing user privacy. Prepare for a thought-provoking exploration of AI's potential!
177 snips
Jun 1, 2023 • 1h 10min
Building the AI × UX Scenius — with Linus Lee of Notion AI
Linus Lee, a product engineer at Notion and an AI UX specialist, shares his insights on designing intuitive AI interfaces. He emphasizes the importance of setting constraints and building community around AI technologies. Linus discusses the unique features of Notion AI, from project scoping to innovative writing tools, while addressing the challenges of prompt engineering. He also explores the balance between nostalgia and functionality in design, spotlighting how user feedback shapes the evolution of AI-driven interfaces.
21 snips
May 25, 2023 • 1h 3min
Debugging the Internet with AI agents – with Itamar Friedman of Codium AI and AutoGPT
Itamar Friedman, CEO of CodiumAI and former founder of Visualead, dives into the transformative world of AI in software development. He discusses the impressive capabilities of Codium's AI coding assistant, aimed at drastically reducing bugs in code. Their innovative tool integrates seamlessly with traditional coding methods for real-time analysis and debugging. Itamar also shares insights into the dynamic startup culture in Tel Aviv and the future of AI in coding practices, highlighting the importance of user feedback and flexibility in evolving software development.
59 snips
May 20, 2023 • 1h 7min
MPT-7B and The Beginning of Context=Infinity — with Jonathan Frankle and Abhinav Venigalla of MosaicML
Jonathan Frankle, Chief Scientist at MosaicML, and Abhinav Venigalla, Research Scientist at MosaicML, dive into the groundbreaking MPT-7B model. They discuss its unprecedented 84,000-token context length and how it was trained on 1 trillion tokens, achieving industry-leading performance for a fraction of the cost. The duo also navigates the complexities of AI model training, ethical considerations in creative generation, and the balance between open research and business interests, providing fascinating insights into the future of AI technologies.
33 snips
May 16, 2023 • 1h 2min
Guaranteed quality and structure in LLM outputs - with Shreya Rajpal of Guardrails AI
Shreya Rajpal, the creator of Guardrails AI, dives deep into improving the reliability of large language models (LLMs). She discusses her journey and the need for structured outputs in AI, unveiling the innovative RAIL system that ensures quality and validation. The conversation highlights the challenges of keeping AI outputs predictable, especially in complex tasks like SQL execution. Shreya emphasizes community engagement for iterative development and explores creative ways to enhance user interaction with AI technologies.
34 snips
May 8, 2023 • 51min
The AI Founder Gene: Being Early, Building Fast, and Believing in Greatness — with Sharif Shameem of Lexica
Sharif Shameem, founder of Lexica and previously a pioneer in AI startups like VectorDash and Debuild, shares his thrilling journey in the fast-paced world of AI. He discusses launching Lexica just after Stable Diffusion's release, achieving rapid product-market fit with 5 billion image searches daily. Sharif delves into being 'chronically early' in tech, the impact of GPT-3 on AI projects, and the vital role of quality data in training models. His insights on innovation and user-focused design are both enlightening and inspiring for aspiring founders.
16 snips
May 5, 2023 • 44min
No Moat: Closed AI gets its Open Source wakeup call — ft. Simon Willison
Simon Willison, an exceptional communicator and writer, delves into the implications of the 'No Moat' memo regarding the competition between Google and OpenAI. He discusses the staggering advances in open-source AI, particularly Facebook’s Llama, and how it challenges traditional models. The podcast highlights Google's internal struggles with AI monetization and concerns about chatbots disrupting revenue streams. Willison also shares insights on the rise of Mojo, a programming language designed to supercharge Python, and its potential to revolutionize coding efficiency.
5 snips
May 3, 2023 • 1h 10min
Training a SOTA Code LLM in 1 week and Quantifying the Vibes — with Reza Shabani of Replit
Reza Shabani, Head of AI at Replit with a PhD in economics, shares insights from his transition from finance to AI. He delves into the creation of Ghostwriter, a code completion tool, and the innovative 'Amjad eval' method for improving code assessment. Reza discusses Replit’s new coding model, Replicode V1 3B, which boasts 2.7 billion parameters and outperforms competitors. He also explores the societal impact of AI recruitment and highlights the crucial balance between AI integration and human work.
