Practical AI 4a3nz

In this first of a two part series of episodes on federated learning, we dive into the evolving world of federated learning and distributed AI frameworks with Patrick Foley from Intel. We explore how frameworks like OpenFL and Flower are enabling secure, collaborative model training across silos, especially in sensitive fields like healthcare. The conversation touches on real-world use cases, the challenges of distributed ML/AI experiments, and why privacy-preserving techniques may become essential for deploying AI to production. Featuring: Patrick Foley – LinkedIn Chris Benson – Website, GitHub, LinkedIn, X Daniel Whitenack – Website, GitHub, X Links: Intel OpenFL Sponsors: NordLayer is a toggle-ready network security platform built for modern businesses. It combines VPN, access control, and threat protection in one easy-to-use platform. No hardware. No complex setup. Just secure connection and full control—in less than 10 minutes. Up to 22% off NordLayer yearly plans plus 10% on top with the coupon code practically-10.

Loïc Houssier, Head of Engineering at Superhuman, s us to discuss how AI and LLMs are reshaping the email experience. They discuss challenges like prompt and infrastructure optimization. Loïc also shares how a deep focus on experience and real human workflows is key to building AI tools people actually love to use.  Featuring: Loïc Houssier – LinkedIn Chris Benson – Website, GitHub, LinkedIn, X Daniel Whitenack – Website, GitHub, X Links: Superhuman Referral Code for a Free month Sponsors: Outshift by Cisco - AGNTCY is an open source collective building the Internet of Agents. It's a collaboration layer where AI agents can communicate, discover each other, and work across frameworks. For developers, this means standardized agent discovery tools, seamless protocols for inter-agent communication, and modular components to compose and scale multi-agent workflows.

In this episode, Daniel and Chris unpack the Model Context Protocol (M), a rising standard for enabling agentic AI interactions with external systems, APIs, and data sources. They explore how M s interoperability, community contributions, and a rapidly developing ecosystem of AI integrations. The conversation also highlights some real-world tooling such as FastAPI-M. Featuring: Chris Benson – Website, GitHub, LinkedIn, X Daniel Whitenack – Website, GitHub, X Links: Protocol website Anthropic blog post Blog post - Model Context Protocol (M) an overview FastAPI-M How to Use FastAPI M Server: A Complete Guide  Candle (Rust framework)

In this episode, we explore the intersection of AI, machine learning, and healthcare through the lens of neuroimaging and epilepsy diagnosis. Dr. Gavin Winston shares insights from his work using MRI data and machine learning to uncover subtle abnormalities in brain function. We discuss the cultural and ethical barriers to AI adoption in medicine, how predictive data analysis could transform the diagnostic workflow, and what the future holds for medical imaging in a world increasingly shaped by intelligent systems. Featuring: Gavin Winston – LinkedIn, Website Chris Benson – Website, GitHub, LinkedIn, X Daniel Whitenack – Website, GitHub, X Links: Detection of Epileptogenic Focal Cortical Dysplasia Using Graph Neural Networks: A MELD Study Machine Learning in Neuroimaging across Disciplines Automated and Interpretable Detection of Hippocampal Sclerosis in Temporal Lobe Epilepsy: AID-HS Literature review and protocol for a prospective multicentre cohort study on multimodal prediction of seizure recurrence after unprovoked first seizure Deep learning in neuroimaging of epilepsy Non-parametric combination of multimodal MRI for lesion detection in focal epilepsy Detection of covert lesions in focal epilepsy using computational analysis of multimodal magnetic resonance imaging data

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, tooling, collaboration, and what it means to build software in the era of AI agents. Whether you're coding from your laptop or your phone on a morning walk, the future is hands-free (and All Hands). Featuring: Robert Brennan – LinkedIn, X Graham Neubig – LinkedIn, X Chris Benson – Website, GitHub, LinkedIn, X Daniel Whitenack – Website, GitHub, X Links: All Hands All Hands on GitHub All Hands on Hugging Face  

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 helps us understand things like M servers and why connecting assistants via APIs is easy—but making them useful is hard.  Featuring: Pavel Veller – LinkedIn, X Daniel Whitenack – Website, GitHub, X Links: EPAM DIAL SWE-bench results ★ this 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 s emerging model architectures.  Featuring: Dhananjay Singh – LinkedIn Chris Benson – Website, GitHub, LinkedIn, X Daniel Whitenack – Website, GitHub, X Links: Groq Sponsors: Augment Code - Developer AI that uses deep understanding of your large codebase and how you build software to deliver personalized code suggestions and insights. Augment provides relevant, contextualized code right in your IDE or Slack. It transforms scattered knowledge into code or answers, eliminating time spent searching docs or interrupting teammates. ★ this podcast ★

Kyle Daigle, COO of GitHub, s 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 for ambient AI, which seamlessly integrates into workflows to enhance productivity and innovation, shaping the future of developer tools.  Featuring: Kyle Daigle – LinkedIn Chris Benson – Website, GitHub, LinkedIn, X Daniel Whitenack – Website, GitHub, X Sponsors: Domo – The AI and data products platform. Strengthen your entire data journey with Domo’s AI and data products. ★ this podcast ★

We often judge AI models by leaderboard scores, but what if efficiency matters more? Kate Soule from IBM s us to discuss how Granite AI is rethinking AI at the edge—breaking tasks into smaller, efficient components and co-deg models with hardware. She also shares why AI should prioritize efficiency frontiers over incremental benchmark gains and how seamless model routing can optimize performance.  Featuring: Kate Soule – LinkedIn Chris Benson – Website, GitHub, LinkedIn, X Daniel Whitenack – Website, GitHub, X Links: IBM Granite IBM Granite on Hugging Face IBM Expands Granite Model Family with New Multi-Modal and Reasoning AI Built for the Enterprise  ★ this podcast ★

How can every single person build a personal AI protégé and then accumulate (and share) a host of other assistants? In this episode, we dive into the world of no-code AI with Scott Meyer from Chipp.ai. We discuss AI tooling for people that can't code, the cultural shift that needs to happen for widespread AI adoption in businesses, and the predicted growth trajectory of AI assistant that you can own. Featuring: Chris Benson – Website, GitHub, LinkedIn, X Daniel Whitenack – Website, GitHub, X Scott Meyer - LinkedIn, X Sponsors: Domo – The AI and data products platform. Strengthen your entire data journey with Domo’s AI and data products. Show Notes: Chipp.ai Chipp.ai's Discord ★ this podcast ★

It seems like all we hear about are the great use cases for GenAI, but where should you NOT be using the technology? On this episode Chris and Daniel share their hot takes and bad use cases. Some may surprise you! the discussion Changelog++ save 3 minutes on this episode because they made the ads disappear. today! Sponsors: Domo – The AI and data products platform. Strengthen your entire data journey with Domo’s AI and data products. Fly.io – The home of Changelog.com — Deploy your apps close to your s — global Anycast load-balancing, zero-configuration private networking, hardware isolation, and instant WireGuard VPN connections. Push-button deployments that scale to thousands of instances. Check out the speedrun to get started in minutes. Featuring: Chris Benson – Website, GitHub, LinkedIn, X Daniel Whitenack – Website, GitHub, X Show Notes: Something missing or broken? PRs welcome!

It seems like everyone is uses the term “agent” differently these days. In this episode, Chris and Daniel dig into the details of tool calling and its connection to agents. They help clarify how LLMs can “talk to” and “interact with” other systems like databases, APIs, web apps, etc. Along the way they share related learning resources. the discussion Changelog++ save 4 minutes on this episode because they made the ads disappear. today! Sponsors: Notion – Notion is a place where any team can write, plan, organize, and rediscover the joy of play. It’s a workspace designed not just for making progress, but getting inspired. Notion is for everyone — whether you’re a Fortune 500 company or freelance designer, starting a new startup or a student juggling classes and clubs. Featuring: Chris Benson – Website, GitHub, LinkedIn, X Daniel Whitenack – Website, GitHub, X Show Notes: smolagents Hugging Face agents course Something missing or broken? PRs welcome!

There is crazy hype and a lot of confusion related to DeepSeek’s latest model DeepSeek R1. The products provided by DeepSeek (their version of a ChatGPT-like app) has exploded in popularity. However, ties to China have raised privacy and geopolitical concerns. In this episode, Chris and Daniel cut through the hype to talk about the model, privacy implications, running DeepSeek models securely, and what this signals for open models in 2025. the discussion Changelog++ save 5 minutes on this episode because they made the ads disappear. today! Sponsors: Notion – Notion is a place where any team can write, plan, organize, and rediscover the joy of play. It’s a workspace designed not just for making progress, but getting inspired. Notion is for everyone — whether you’re a Fortune 500 company or freelance designer, starting a new startup or a student juggling classes and clubs. Domo – The AI and data products platform. Strengthen your entire data journey with Domo’s AI and data products. Featuring: Chris Benson – Website, GitHub, LinkedIn, X Daniel Whitenack – Website, GitHub, X Show Notes: Daniel’s blog post on DeepSeek DeepSeek R1 on Hugging Face DeepSeek Something missing or broken? PRs welcome!

We seem to be experiencing a surge of video generation tools, models, and applications. However, video generation models generally struggle with some basic physics, like realistic walking motion. This leaves some generated videos lacking true motion with disappointing, simplistic panning camera views. Genmo is focused on the motion side of video generation and has released some of the best open models. Paras s us to discuss video generation and their journey at Genmo. the discussion Changelog++ save 2 minutes on this episode because they made the ads disappear. today! Sponsors: Domo – The AI and data products platform. Strengthen your entire data journey with Domo’s AI and data products. Featuring: Paras Jain – LinkedIn, X Chris Benson – Website, GitHub, LinkedIn, X Daniel Whitenack – Website, GitHub, X Show Notes: Genmo Something missing or broken? PRs welcome!

Daniel and Chris groove with Jeff Smith, Founder and CEO at CHRP.ai. Jeff describes how CHRP anonymously analyzes emotional wellness data, derived from employees’ music preferences, giving HR leaders actionable insights to improve productivity, retention, and overall morale. By monitoring key trends and identifying shifts in emotional health across teams, CHRP.ai enables proactive decisions to ensure employees feel ed and engaged. the discussion Changelog++ save 9 minutes on this episode because they made the ads disappear. today! Sponsors: Shopify – Sign up for a $1/month trial period at shopify.com/practicalai Eight Sleep – Up to $600 off Pod 4 Ultra — Go to eightsleep.com/changelog and use the code CHANGELOG. You can try it for free for 30 days - but we’re confident you will not want to return it (we love ours). Once you experience AI-optimized sleep, you’ll wonder how you ever slept without it. Currently shipping to: United States, Canada, United Kingdom, Europe, and Australia. DeleteMe – DeleteMe makes it quick, easy and safe to remove your personal data online. Featuring: Jeff Smith – Twitter, LinkedIn Chris Benson – Twitter, GitHub, LinkedIn, Website Daniel Whitenack – Twitter, GitHub, Website Show Notes: CHRP | Website MyCHRP CHRP | Instagram CHRP | LinkedIn Something missing or broken? PRs welcome!

Today, Chris explores Shopify Magic and other AI offerings with Mike Tamir, Distinguished ML Engineer and Head of Machine Learning, and Matt Colyer, Director of Product Management for Sidekick. They talk about how Shopify uses generative AI and LLMs to enhance their products, and they take a deeper dive into Sidekick, a first-of-its-kind, AI-enabled commerce assistant that understands a merchant’s business (products, orders, customers) and has been trained to know all about Shopify. the discussion Changelog++ save 9 minutes on this episode because they made the ads disappear. today! Sponsors: Fly.io – The home of Changelog.com — Deploy your apps close to your s — global Anycast load-balancing, zero-configuration private networking, hardware isolation, and instant WireGuard VPN connections. Push-button deployments that scale to thousands of instances. Check out the speedrun to get started in minutes. Timescale – Purpose-built performance for AI Build RAG, search, and AI agents on the cloud and with PostgreSQL and purpose-built extensions for AI: pgvector, pgvectorscale, and pgai. Eight Sleep – Up to $600 off Pod 4 Ultra — Go to eightsleep.com/changelog and use the code CHANGELOG. You can try it for free for 30 days - but we’re confident you will not want to return it (we love ours). Once you experience AI-optimized sleep, you’ll wonder how you ever slept without it. Currently shipping to: United States, Canada, United Kingdom, Europe, and Australia. Featuring: Mike Tamir – LinkedIn Matt Colyer – Twitter, LinkedIn Chris Benson – Twitter, GitHub, LinkedIn, Website Show Notes: Shopify Shopify’s Winter Edition ’25 Something missing or broken? PRs welcome!

Kyutai, an open science research lab, made headlines over the summer when they released their real-time speech-to-speech AI assistant (beating OpenAI to market with their teased GPT-driven speech-to-speech functionality). Alex from Kyutai s us in this episode to discuss the research lab, their recent Moshi models, and what might be coming next from the lab. Along the way we discuss small models and the AI ecosystem in . the discussion Changelog++ save 10 minutes on this episode because they made the ads disappear. today! Sponsors: Fly.io – The home of Changelog.com — Deploy your apps close to your s — global Anycast load-balancing, zero-configuration private networking, hardware isolation, and instant WireGuard VPN connections. Push-button deployments that scale to thousands of instances. Check out the speedrun to get started in minutes. Timescale – Purpose-built performance for AI Build RAG, search, and AI agents on the cloud and with PostgreSQL and purpose-built extensions for AI: pgvector, pgvectorscale, and pgai. WorkOS – AuthKit offers 1,000,000 monthly active s (MAU) free — The world’s best box, powered by WorkOS + Radix. Learn more and get started at WorkOS.com and AuthKit.com Featuring: Alexandre Défossez – Twitter, GitHub, Website Chris Benson – Twitter, GitHub, LinkedIn, Website Daniel Whitenack – Twitter, GitHub, Website Show Notes: Kyutai Kyutai on GitHub Kyutai on Hugging Face Something missing or broken? PRs welcome!

Chris and Daniel dive into what Trump’s impending second term could mean for AI companies, model developers, and regulators, unpacking the potential shifts in policy and innovation. Next, they discuss the latest models, like Qwen, that blur the performance gap between open and closed systems. Finally, they explore new AI tools for meeting clones and AI-driven commerce, sparking a conversation about the balance between digital convenience and fostering genuine human connections. the discussion Changelog++ save 8 minutes on this episode because they made the ads disappear. today! Sponsors: WorkOS – AuthKit offers 1,000,000 monthly active s (MAU) free — The world’s best box, powered by WorkOS + Radix. Learn more and get started at WorkOS.com and AuthKit.com Notion – Notion is a place where any team can write, plan, organize, and rediscover the joy of play. It’s a workspace designed not just for making progress, but getting inspired. Notion is for everyone — whether you’re a Fortune 500 company or freelance designer, starting a new startup or a student juggling classes and clubs. Retool – The low-code platform for developers to build internal tools — Some of the best teams out there trust Retool…Brex, Coinbase, Plaid, Doordash, LegalGenius, Amazon, Allbirds, Peloton, and so many more – the developers at these teams trust Retool as the platform to build their internal tools. Try it free at retool.com/changelog Featuring: Chris Benson – Twitter, GitHub, LinkedIn, Website Daniel Whitenack – Twitter, GitHub, Website Show Notes: New Models Qwen2.5 Alibaba’s Qwen AI Model Qwen2.5 Turbo Reads Ten Novels in One Minute DeepSeek DeepSeek API Docs Update FLUX Black Forest Labs’ FLUX.1-dev on Hugging Face OuteTTS OuteTTS 0.1 - 350M Blog OuteTTS 0.2 - 500M Blog Smol TTS Update on LinkedIn SmolLVM SmolLVM Updates on LinkedIn What Donald Trump’s Win Means for AI Practical AI Podcast: Episode 244 GetPickle.ai Docling Docling Paper on arXiv Docling GitHub Repository Red Hat Blog on Docling LinkedIn Post on PDF Table Extraction Hugging Face Blog on Observers SDK AI and Commerce Stripe Blog: Adding Payments to Agentic Workflows LinkedIn Announcement: Payments Integration SDK Something missing or broken? PRs welcome!

We are at GenAI saturation, so let’s talk about scikit-learn, a long time favorite for data scientists building classifiers, time series analyzers, dimensionality reducers, and more! Scikit-learn is deployed across industry and driving a significant portion of the “AI” that is actually in production. :probabl is a new kind of company that is stewarding this project along with a variety of other open source projects. Yann Lechelle and Guillaume Lemaitre share some of the vision behind the company and talk about the future of scikit-learn! the discussion Changelog++ save 9 minutes on this episode because they made the ads disappear. today! Sponsors: Timescale – Purpose-built performance for AI Build RAG, search, and AI agents on the cloud and with PostgreSQL and purpose-built extensions for AI: pgvector, pgvectorscale, and pgai. WorkOS – A platform that gives developers a set of building blocks for quickly adding enterprise-ready features to their application. Add Single Sign-On (Okta, Azure, Google, Microsoft OAuth), sync s from any SCIM directory, HRIS integration, audit trails (SIEM), free magic link . WorkOS is designed for developers and offers a single, elegant interface that abstracts dozens of enterprise integrations. Learn more and get started at WorkOS.com Shopify – Sign up for a $1/month trial period at shopify.com/practicalai Featuring: Yann Lechelle – LinkedIn Guillaume Lemaitre – Mastodon, Twitter, GitHub, LinkedIn Chris Benson – Twitter, GitHub, LinkedIn, Website Daniel Whitenack – Twitter, GitHub, Website Show Notes: :probabl. TechCrunch: Probabl is a new AI company built around popular library scikit-learn scikit-learn Something missing or broken? PRs welcome!

It can be frustrating to get an AI application working amazingly well 80% of the time and failing miserably the other 20%. How can you close the gap and create something that you rely on? Chris and Daniel talk through this process, behavior testing, and the flow from prototype to production in this episode. They also talk a bit about the apparent slow down in the release of frontier models. the discussion Changelog++ save 10 minutes on this episode because they made the ads disappear. today! Sponsors: Fly.io – The home of Changelog.com — Deploy your apps close to your s — global Anycast load-balancing, zero-configuration private networking, hardware isolation, and instant WireGuard VPN connections. Push-button deployments that scale to thousands of instances. Check out the speedrun to get started in minutes. Timescale – Purpose-built performance for AI Build RAG, search, and AI agents on the cloud and with PostgreSQL and purpose-built extensions for AI: pgvector, pgvectorscale, and pgai. Eight Sleep – Up to $600 off Pod 4 Ultra Go to eightsleep.com/changelog and use the code CHANGELOG. You can try it for free for 30 days - but we’re confident you will not want to return it (we love ours). Once you experience AI-optimized sleep, you’ll wonder how you ever slept without it. Currently shipping to: United States, Canada, United Kingdom, Europe, and Australia. Featuring: Chris Benson – Twitter, GitHub, LinkedIn, Website Daniel Whitenack – Twitter, GitHub, Website Show Notes: MLOps Community “Agents in Production” event Something missing or broken? PRs welcome!