Conversations with the people building AI
In this episode, Kelly Hong, a researcher at Chroma, joins us to discuss "Generative Benchmarking," a novel approach to evaluating retrieval systems, like RAG applications, using synthetic data. Kelly explains how traditional benchmarks like MTEB fail to represent real-world query patterns and how embedding models…
54 MinutesThe TWIML AI Podcast
Vibe coding, agentic workflows, and AI-assisted pull requests? In this episode, Daniel and Chris chat with Robert Brennan and Graham Neubig of All Hands AI about how AI is transforming software development—from senior engineer productivity to open source agents that address GitHub issues. They dive into trust…
42 MinutesPractical AI
In this episode, Emmanuel Ameisen, a research engineer at Anthropic, returns to discuss two recent papers: "Circuit Tracing: Revealing Language Model Computational Graphs" and "On the Biology of a Large Language Model." Emmanuel explains how his team developed mechanistic interpretability methods to understand the…
1h 34mThe TWIML AI Podcast
In this episode, Daniel sits down with Pavel Veller, EPAM’s Chief Technologist, to explore the practical challenges of orchestrating many AI agents and managing connections to disparate systems/tools. Pavel shares insights from his hands-on work with agentic architectures and internal tools like "DIAL". Pavel also…
43 MinutesPractical AI
Today, we're joined by Maohao Shen, PhD student at MIT to discuss his paper, “Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search.” We dig into how Satori leverages reinforcement learning to improve language model reasoning—enabling model self-reflection…
52 MinutesThe TWIML AI Podcast
How do you enable AI acceleration (at both the hardware and software layers) that stays ahead of rapid industry shifts? In this episode, Dhananjay Singh from Groq dives into the evolving landscape of AI inference and acceleration. We explore how Groq optimizes the serving layer, adapts to industry shifts, and supports…
43 MinutesPractical AI
Today, we're joined by Drago Anguelov, head of AI foundations at Waymo, for a deep dive into the role of foundation models in autonomous driving. Drago shares how Waymo is leveraging large-scale machine learning, including vision-language models and generative AI techniques to improve perception, planning, and…
1h 09mThe TWIML AI Podcast
Today, we're joined by Julie Kallini, PhD student at Stanford University to discuss her recent papers, “MrT5: Dynamic Token Merging for Efficient Byte-level Language Models” and “Mission: Impossible Language Models.” For the MrT5 paper, we explore the importance and failings of tokenization in large language…
51 MinutesThe TWIML AI Podcast
Kyle Daigle, COO of GitHub, joins the hosts to discuss the evolving role of AI in software development, GitHub Copilot’s impact, and the challenges of AI-assisted coding. The conversation covers licensing concerns, ethical considerations, and how developers can navigate these complexities. Kyle also shares his vision…
50 MinutesPractical AI
Today, we're joined by Jonas Geiping, research group leader at Ellis Institute and the Max Planck Institute for Intelligent Systems to discuss his recent paper, “Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach.” This paper proposes a novel language model architecture which uses recurrent…
59 MinutesThe TWIML AI Podcast
We often judge AI models by leaderboard scores, but what if efficiency matters more? Kate Soule from IBM joins us to discuss how Granite AI is rethinking AI at the edge—breaking tasks into smaller, efficient components and co-designing models with hardware. She also shares why AI should prioritize efficiency frontiers…
44 MinutesPractical AI
Today, we're joined by Chengzu Li, PhD student at the University of Cambridge to discuss his recent paper, “Imagine while Reasoning in Space: Multimodal Visualization-of-Thought.” We explore the motivations behind MVoT, its connection to prior work like TopViewRS, and its relation to cognitive science principles such…
42 MinutesThe TWIML AI Podcast