RAG Risks: Why Retrieval-Augmented LLMs are Not Safer with Sebastian Gehrmann - #732
Today, we're ed by Sebastian Gehrmann, head of responsible AI in the Office of the CTO at...
57:37
From Prompts to Policies: How RL Builds Better AI Agents with Mahesh Sathiamoorthy - #731
Today, we're ed by Mahesh Sathiamoorthy, co-founder and CEO of Bespoke Labs, to discuss how...
01:01:53
How OpenAI Builds AI Agents That Think and Act with Josh Tobin - #730
Today, we're ed by Josh Tobin, member of technical staff at OpenAI, to discuss the company’s...
01:07:42
CTIBench: Evaluating LLMs in Cyber Threat Intelligence with Nidhi Rastogi - #729
Today, we're ed by Nidhi Rastogi, assistant professor at Rochester Institute of Technology to...
55:48
Generative Benchmarking with Kelly Hong - #728
In this episode, Kelly Hong, a researcher at Chroma, s us to discuss "Generative...
53:47
Exploring the Biology of LLMs with Circuit Tracing with Emmanuel Ameisen - #727
In this episode, Emmanuel Ameisen, a research engineer at Anthropic, returns to discuss two...
01:33:36
Teaching LLMs to Self-Reflect with Reinforcement Learning with Maohao Shen - #726
Today, we're ed by Maohao Shen, PhD student at MIT to discuss his paper, “Satori:...
51:15
Waymo's Foundation Model for Autonomous Driving with Drago Anguelov - #725
Today, we're ed by Drago Anguelov, head of AI foundations at Waymo, for a deep dive into the...
01:08:37
Dynamic Token Merging for Efficient Byte-level Language Models with Julie Kallini - #724
Today, we're ed by Julie Kallini, PhD student at Stanford University to discuss her recent...
50:02
Scaling Up Test-Time Compute with Latent Reasoning with Jonas Geiping - #723
Today, we're ed by Jonas Geiping, research group leader at Ellis Institute and the Max Planck...
58:08
Imagine while Reasoning in Space: Multimodal Visualization-of-Thought with Chengzu Li - #722
Today, we're ed by Chengzu Li, PhD student at the University of Cambridge to discuss his...
41:41
Inside s1: An o1-Style Reasoning Model That Cost Under $50 to Train with Niklas Muennighoff - #721
Today, we're ed by Niklas Muennighoff, a PhD student at Stanford University, to discuss his...
48:59
Accelerating AI Training and Inference with AWS Trainium2 with Ron Diamant - #720
Today, we're ed by Ron Diamant, chief architect for Trainium at Amazon Web Services, to...
01:07:29
π0: A Foundation Model for Robotics with Sergey Levine - #719
Today, we're ed by Sergey Levine, associate professor at UC Berkeley and co-founder of...
52:00
AI Trends 2025: AI Agents and Multi-Agent Systems with Victor Dibia - #718
Today we’re ed by Victor Dibia, principal research software engineer at Microsoft Research,...
01:44:29
Speculative Decoding and Efficient LLM Inference with Chris Lott - #717
Today, we're ed by Chris Lott, senior director of engineering at Qualcomm AI Research to...
01:16:00
Ensuring Privacy for Any LLM with Patricia Thaine - #716
Today, we're ed by Patricia Thaine, co-founder and CEO of Private AI to discuss techniques...
51:03
AI Engineering Pitfalls with Chip Huyen - #715
Today, we're ed by Chip Huyen, independent researcher and writer to discuss her new book, “AI...
57:07
Evolving MLOps Platforms for Generative AI and Agents with Abhijit Bose - #714
Today, we're ed by Abhijit Bose, head of enterprise AI and ML platforms at Capital One to...
57:38
Why Agents Are Stupid & What We Can Do About It with Dan Jeffries - #713
Today, we're ed by Dan Jeffries, founder and CEO of Kentauros AI to discuss the challenges...
01:08:19
Plus