Best Bridges And Bytes Podcasts (2025)

1
Multimodal AI Models on Apple Silicon with MLX with Prince Canuma - #744 1:10:20

Play Pause

6d ago1:10:20

1:10:20

Today, we're joined by Prince Canuma, an ML engineer and open-source developer focused on optimizing AI inference on Apple Silicon devices. Prince shares his journey to becoming one of the most prolific contributors to Apple’s MLX ecosystem, having published over 1,000 models and libraries that make open, multimodal AI accessible and performant on …

1
The Innovation of Cumulative Cultures and Developer Problem-Solving 1:29:53

10d ago1:29:53

1:29:53

Did you know that crows are better than toddlers at generating novel solutions? It's true! In the earliest days of childhood, around the globe scientists have documented that human cognition struggles to generate novel solutions. But we are adept at imitation, transmitting and teaching the solutions that we see others put into practice. What does t…

1
Brandon Powers on dance, technology, immersive experiences, reframing the role of the audience, working with engineers, and the importance of translation 45:00

11d ago45:00

45:00

A chat with New York-based creative director and choreographer, Brandon Powers. Brandon works with technology to create experiences across physical and virtual spaces. We talked about his early experiences with technology, inter-disciplinary teams, the various ways that technology and virtual spaces can enhance and extend experiences for both artis…

1
The TCO Survival Guide 20:30

12d ago20:30

20:30

In this episode of Power Bytes, we explore why understanding the Total Cost of Ownership (TCO) is critical for businesses relying on generator sets for prime power. From fuel efficiency and maintenance strategies to predictive technologies and regulatory compliance, we break down hidden costs that impact long-term performance and profitability. Lea…

1
Genie 3: A New Frontier for World Models with Jack Parker-Holder and Shlomi Fruchter - #743 1:01:01

13d ago1:01:01

1:01:01

Today, we're joined by Jack Parker-Holder and Shlomi Fruchter, researchers at Google DeepMind, to discuss the recent release of Genie 3, a model capable of generating “playable” virtual worlds. We dig into the evolution of the Genie project and review the current model’s scaled-up capabilities, including creating real-time, interactive, and high-re…

1
Closing the Loop Between AI Training and Inference with Lin Qiao - #742 1:01:11

20d ago1:01:11

1:01:11

In this episode, we're joined by Lin Qiao, CEO and co-founder of Fireworks AI. Drawing on key lessons from her time building PyTorch, Lin shares her perspective on the modern generative AI development lifecycle. She explains why aligning training and inference systems is essential for creating a seamless, fast-moving production pipeline, preventing…

1
Hazel Weakly - Abstractions as Bridges 1:34:31

22d ago1:34:31

1:34:31

Have you ever wondered about what makes a good abstraction vs a bad one? Do you want to examine potential reasons why efforts to develop abstractions at a company or in a project take hold, and some don't? Or what it takes to develop an abstraction that reaches beyond the technical corner of your company or project and becomes something that helps …

1
Turning Up the Heat: Microgrids & Chilies 18:43

1M ago18:43

18:43

In this episode of the Power Bytes podcast, Neil Smith discusses the significant demand for microgrid solutions, especially for rural electrification, and highlights how these projects can drastically improve quality of life in communities. He also shares insights on the Nagaland project, which aims to help bring sustainable energy to remote areas,…

1
Context Engineering for Productive AI Agents with Filip Kozera - #741 46:01

1M ago46:01

46:01

In this episode, Filip Kozera, founder and CEO of Wordware, explains his approach to building agentic workflows where natural language serves as the new programming interface. Filip breaks down the architecture of these "background agents," explaining how they use a reflection loop and tool-calling to execute complex tasks. He discusses the current…

1
Infrastructure Scaling and Compound AI Systems with Jared Quincy Davis - #740 1:13:02

1M ago1:13:02

1:13:02

In this episode, Jared Quincy Davis, founder and CEO at Foundry, introduces the concept of "compound AI systems," which allows users to create powerful, efficient applications by composing multiple, often diverse, AI models and services. We discuss how these "networks of networks" can push the Pareto frontier, delivering results that are simultaneo…

1
Neil Williams (BFI) on transforming organisations through digital, comparisons between the civil service and the cultural sector, working in the open, and intentionally not empire-building 57:19

2M ago57:19

57:19

A conversation recorded in-person (hurray!) with the BFI's Exec Director of Technology and Digital Transformation, Neil Williams. Neil writes a regular 'fortnight notes' post on his blog, which you can find here neilojwilliams.netBy Digital Works

1
Building Voice AI Agents That Don’t Suck with Kwindla Kramer - #739 1:13:02

2M ago1:13:02

1:13:02

In this episode, Kwindla Kramer, co-founder and CEO of Daily and creator of the open source Pipecat framework, joins us to discuss the architecture and challenges of building real-time, production-ready conversational voice AI. Kwin breaks down the full stack for voice agents—from the models and APIs to the critical orchestration layer that manages…

1
Distilling Transformers and Diffusion Models for Robust Edge Use Cases with Fatih Porikli - #738 1:00:29

2M ago1:00:29

1:00:29

Today, we're joined by Fatih Porikli, senior director of technology at Qualcomm AI Research for an in-depth look at several of Qualcomm's accepted papers and demos featured at this year’s CVPR conference. We start with “DiMA: Distilling Multi-modal Large Language Models for Autonomous Driving,” an end-to-end autonomous driving system that incorpora…

1
The Power Struggle: Disruptors, Developers, and the Future of Power 19:30

2M ago19:30

19:30

In this episode of the Power Bytes Podcast, host Ryan Karlin sits down with Brandon Lynn, Caterpillar Electric Power’s Global Director of Business Development, to discuss the growing role of distributed generation and how industries are adapting to enhance operational efficiencies and achieve their goals. Email us: [email protected] LinkedIn: http…

1
Building the Internet of Agents with Vijoy Pandey - #737 56:13

2M ago56:13

56:13

Today, we're joined by Vijoy Pandey, SVP and general manager at Outshift by Cisco to discuss a foundational challenge for the enterprise: how do we make specialized agents from different vendors collaborate effectively? As companies like Salesforce, Workday, and Microsoft all develop their own agentic systems, integrating them creates a complex, pr…

1
LLMs for Equities Feature Forecasting at Two Sigma with Ben Wellington - #736 59:31

3M ago59:31

59:31

Today, we're joined by Ben Wellington, deputy head of feature forecasting at Two Sigma. We dig into the team’s end-to-end approach to leveraging AI in equities feature forecasting, covering how they identify and create features, collect and quantify historical data, and build predictive models to forecast market behavior and asset prices for tradin…

1
Zero-Shot Auto-Labeling: The End of Annotation for Computer Vision with Jason Corso - #735 56:45

3M ago56:45

56:45

Today, we're joined by Jason Corso, co-founder of Voxel51 and professor at the University of Michigan, to explore automated labeling in computer vision. Jason introduces FiftyOne, an open-source platform for visualizing datasets, analyzing models, and improving data quality. We focus on Voxel51’s recent research report, “Zero-shot auto-labeling riv…

1
Tash Willcocks (TPX Impact) on navigating uncertainty, intellectual humility, leadership in turbulent times, why zebras don't get ulcers, the importance of structure in enabling agility, how to actually ... 56:03

3M ago56:03

56:03

A wide-ranging chat with Tash Willcocks (Head of Learning Design at TPX Impact) on organisational culture, leadership, and how to deal with change and uncertainty. Tash mentioned a whole load of ideas, articles, books, and thinkers - a few of which I've linked to below: Tash's Medium lives here: https://medium.com/@tash-willcocks This is the first …

1
Grokking, Generalization Collapse, and the Dynamics of Training Deep Neural Networks with Charles Martin - #734 1:25:21

3M ago1:25:21

1:25:21

Today, we're joined by Charles Martin, founder of Calculation Consulting, to discuss Weight Watcher, an open-source tool for analyzing and improving Deep Neural Networks (DNNs) based on principles from theoretical physics. We explore the foundations of the Heavy-Tailed Self-Regularization (HTSR) theory that underpins it, which combines random matri…

1
Google I/O 2025 Special Edition - #733 26:21

3M ago26:21

26:21

Today, I’m excited to share a special crossover edition of the podcast recorded live from Google I/O 2025! In this episode, I join Shawn Wang aka Swyx from the Latent Space Podcast, to interview Logan Kilpatrick and Shrestha Basu Mallick, PMs at Google DeepMind working on AI Studio and the Gemini API, along with Kwindla Kramer, CEO of Daily and cre…

1
RAG Risks: Why Retrieval-Augmented LLMs are Not Safer with Sebastian Gehrmann - #732 57:09

3M ago57:09

57:09

Today, we're joined by Sebastian Gehrmann, head of responsible AI in the Office of the CTO at Bloomberg, to discuss AI safety in retrieval-augmented generation (RAG) systems and generative AI in high-stakes domains like financial services. We explore how RAG, contrary to some expectations, can inadvertently degrade model safety. We cover examples o…

1
From Prompts to Policies: How RL Builds Better AI Agents with Mahesh Sathiamoorthy - #731 1:01:25

4M ago1:01:25

1:01:25

Today, we're joined by Mahesh Sathiamoorthy, co-founder and CEO of Bespoke Labs, to discuss how reinforcement learning (RL) is reshaping the way we build custom agents on top of foundation models. Mahesh highlights the crucial role of data curation, evaluation, and error analysis in model performance, and explains why RL offers a more robust altern…

1
Beyond Backup: Financing the Future of Data Centers 22:03

4M ago22:03

22:03

In this episode, host Ryan Karlin engages in a compelling conversation with Adam Brown, Senior Manager of Sales at Caterpillar Financial. They delve into the financial intricacies of the data center industry, highlighting key challenges such as extended lead times for grid connectivity and significant capital investments. Email us: [email protected]…

1
How OpenAI Builds AI Agents That Think and Act with Josh Tobin - #730 1:07:27

4M ago1:07:27

1:07:27

Today, we're joined by Josh Tobin, member of technical staff at OpenAI, to discuss the company’s approach to building AI agents. We cover OpenAI's three agentic offerings—Deep Research for comprehensive web research, Operator for website navigation, and Codex CLI for local code execution. We explore OpenAI’s shift from simple LLM workflows to reaso…

1
CTIBench: Evaluating LLMs in Cyber Threat Intelligence with Nidhi Rastogi - #729 56:18

4M ago56:18

56:18

Today, we're joined by Nidhi Rastogi, assistant professor at Rochester Institute of Technology to discuss Cyber Threat Intelligence (CTI), focusing on her recent project CTIBench—a benchmark for evaluating LLMs on real-world CTI tasks. Nidhi explains the evolution of AI in cybersecurity, from rule-based systems to LLMs that accelerate analysis by p…

1
Generative Benchmarking with Kelly Hong - #728 54:17

4M ago54:17

54:17

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 that perform well on public benchm…

1
Exploring the Biology of LLMs with Circuit Tracing with Emmanuel Ameisen - #727 1:34:06

5M ago1:34:06

1:34:06

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 internal workings of Claude by rep…

1
Teaching LLMs to Self-Reflect with Reinforcement Learning with Maohao Shen - #726 51:45

5M ago51:45

51:45

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, self-correction, and exploration of a…

1
Emma Keith (National Theatre) on NT Live, remote audiences, experimentation, learning, thinking about value, leadership, and the importance of pilots 56:27

5M ago56:27

56:27

A great chat with the National Theatre's outgoing Managing Director - Digital, Emma Keith. We talked about how digital practice has developed at the NT and how that differs from other performing arts organisations. The history of the NT Live programme, and the importance of pilots and testing ideas. The hidden value of digital infrastructure, remot…

1
Waymo's Foundation Model for Autonomous Driving with Drago Anguelov - #725 1:09:07

5M ago1:09:07

1:09:07

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 simulation for its self-driving vehicl…

1
Dynamic Token Merging for Efficient Byte-level Language Models with Julie Kallini - #724 50:32

5M ago50:32

50:32

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 models—including inefficient compression…

1
Scaling Up Test-Time Compute with Latent Reasoning with Jonas Geiping - #723 58:38

6M ago58:38

58:38

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 depth to enable “thinking in l…

1
Beks Leary (National Gallery) on the challenges & opportunities of working in larger vs smaller teams, different ways of thinking about audiences, and the value of building meaningful relationships with ... 31:35

6M ago31:35

31:35

A chat with Beks Leary, Senior Social Media and Content Lead at the National Gallery in London. We talked about Beks's career, which has encompassed working at a diverse range of organisations including the Bush Theatre, BBC, and National Theatre before Beks's current role at the National Gallery. Beks explained the opportunities and challenges tha…

1
Imagine while Reasoning in Space: Multimodal Visualization-of-Thought with Chengzu Li - #722 42:11

6M ago42:11

42:11

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 as dual coding theory. We dig i…

1
Inside s1: An o1-Style Reasoning Model That Cost Under $50 to Train with Niklas Muennighoff - #721 49:29

6M ago49:29

49:29

Today, we're joined by Niklas Muennighoff, a PhD student at Stanford University, to discuss his paper, “S1: Simple Test-Time Scaling.” We explore the motivations behind S1, as well as how it compares to OpenAI's O1 and DeepSeek's R1 models. We dig into the different approaches to test-time scaling, including parallel and sequential scaling, as well…

1
Accelerating AI Training and Inference with AWS Trainium2 with Ron Diamant - #720 1:07:05

6M ago1:07:05

1:07:05

Today, we're joined by Ron Diamant, chief architect for Trainium at Amazon Web Services, to discuss hardware acceleration for generative AI and the design and role of the recently released Trainium2 chip. We explore the architectural differences between Trainium and GPUs, highlighting its systolic array-based compute design, and how it balances per…

1
π0: A Foundation Model for Robotics with Sergey Levine - #719 52:30

7M ago52:30

52:30

Today, we're joined by Sergey Levine, associate professor at UC Berkeley and co-founder of Physical Intelligence, to discuss π0 (pi-zero), a general-purpose robotic foundation model. We dig into the model architecture, which pairs a vision language model (VLM) with a diffusion-based action expert, and the model training "recipe," emphasizing the ro…

1
Mike Keating (Art Fund) on the collaborative development of AI policy, balancing the priorities of being both a membership and sector support organisation, and the impact of COVID on Art Fund's digital ... 35:44

7M ago35:44

35:44

A conversation with Art Fund's Associate Director of Digital Experience, Mike Keating. Most of our chat focused on Mike's relatively recent work in developing Art Fund's first AI policy. The collaborative, open, and pragmatic approach that Mike and colleagues took to this work feels like a useful model that other cultural organisations could borrow…

1
AI Trends 2025: AI Agents and Multi-Agent Systems with Victor Dibia - #718 1:44:59

7M ago1:44:59

1:44:59

Today we’re joined by Victor Dibia, principal research software engineer at Microsoft Research, to explore the key trends and advancements in AI agents and multi-agent systems shaping 2025 and beyond. In this episode, we discuss the unique abilities that set AI agents apart from traditional software systems–reasoning, acting, communicating, and ada…

1
Speculative Decoding and Efficient LLM Inference with Chris Lott - #717 1:16:30

7M ago1:16:30

1:16:30

Today, we're joined by Chris Lott, senior director of engineering at Qualcomm AI Research to discuss accelerating large language model inference. We explore the challenges presented by the LLM encoding and decoding (aka generation) and how these interact with various hardware constraints such as FLOPS, memory footprint and memory bandwidth to limit…

1
Ensuring Privacy for Any LLM with Patricia Thaine - #716 51:33

7M ago51:33

51:33

Today, we're joined by Patricia Thaine, co-founder and CEO of Private AI to discuss techniques for ensuring privacy, data minimization, and compliance when using 3rd-party large language models (LLMs) and other AI services. We explore the risks of data leakage from LLMs and embeddings, the complexities of identifying and redacting personal informat…

1
AI Engineering Pitfalls with Chip Huyen - #715 57:37

7M ago57:37

57:37

Today, we're joined by Chip Huyen, independent researcher and writer to discuss her new book, “AI Engineering.” We dig into the definition of AI engineering, its key differences from traditional machine learning engineering, the common pitfalls encountered in engineering AI systems, and strategies to overcome them. We also explore how Chip defines …

1
Evolving MLOps Platforms for Generative AI and Agents with Abhijit Bose - #714 58:08

8M ago58:08

58:08

Today, we're joined by Abhijit Bose, head of enterprise AI and ML platforms at Capital One to discuss the evolution of the company’s approach and insights on Generative AI and platform best practices. In this episode, we dig into the company’s platform-centric approach to AI, and how they’ve been evolving their existing MLOps and data platforms to …

1
#12 Implementing AI Agents—From Vision to Execution 46:03

8M ago46:03

46:03

In this episode of 'AI Demystified for Executives,' host Andrew Psaltis provides a comprehensive guide on implementing AI agents within organizations. The discussion includes aligning AI strategies with business goals, scoping use cases, and identifying tasks suitable for automation. Practical advice is offered on the build versus buy dilemma, pilo…

1
#11 - Understanding AI Agents 39:50

8M ago39:50

39:50

This episode of 'AI Demystified for Executives' explores the concept of AI agents, highlighting their fundamental differences from traditional chatbots and automation tools. Host Andrew Saltz describes AI agents as autonomous, decision-making software entities that can sense and respond to their environment, operate independently, and improve with …

1
Why Agents Are Stupid & What We Can Do About It with Dan Jeffries - #713 1:08:49

9M ago1:08:49

1:08:49

Today, we're joined by Dan Jeffries, founder and CEO of Kentauros AI to discuss the challenges currently faced by those developing advanced AI agents. We dig into how Dan defines agents and distinguishes them from other similar uses of LLM, explore various use cases for them, and dig into ways to create smarter agentic systems. Dan shared his “big …

1
Automated Reasoning to Prevent LLM Hallucination with Byron Cook - #712 56:48

9M ago56:48

56:48

Today, we're joined by Byron Cook, VP and distinguished scientist in the Automated Reasoning Group at AWS to dig into the underlying technology behind the newly announced Automated Reasoning Checks feature of Amazon Bedrock Guardrails. Automated Reasoning Checks uses mathematical proofs to help LLM users safeguard against hallucinations. We explore…

1
AI at the Edge: Qualcomm AI Research at NeurIPS 2024 with Arash Behboodi - #711 54:47

9M ago54:47

54:47

Today, we're joined by Arash Behboodi, director of engineering at Qualcomm AI Research to discuss the papers and workshops Qualcomm will be presenting at this year’s NeurIPS conference. We dig into the challenges and opportunities presented by differentiable simulation in wireless systems, the sciences, and beyond. We also explore recent work that …

1
7. Season in Review 33:14

9M ago33:14

33:14

Welcome to the season-in-review episode. Thank you for coming along on this journey with us where UCD engineering students investigate AI use in university assessments. In this episode, Ashly Antony and Derin Gurman review the main highlights from each episode, as well as some tips and tricks for those of you who have been inspired to try to use AI…

1
#10 - Deep Dive - The AI Usage Gap: From Shadow Innovation to Strategic Advantage 31:26

9M ago31:26

31:26

This episode covers three key themes: the gap between individual AI use and organizational strategy, the hidden potential of 'shadow AI,' and transitioning from ad hoc to strategic AI usage. It highlights communication, trust, and implementation as critical gaps hindering AI adoption and provides actionable steps for building an AI-ready culture. T…