Resumen del episodio
How can AI models learn from private data without compromising privacy? Chris is joined by Lorenzo Sani, Research Scientist at Flower Labs and PhD researcher at Cambridge, to explore federated learning and privacy-preserving AI. They discuss how collaborative learning can expand access to private data for LLM training, how model trajectories can help improve agentic AI systems, and the benefits of open-weight models. The conversation also explores real-world applications of locally hosted AI agents, from healthcare and robotics to everyday automation (for a Halloween party). Featuring: Lorenzo Sani – LinkedIn Chris Benson – Website, LinkedIn, Bluesky, GitHub, X Links: Endeavor model page Introducing Endeavor 1.1 Sponsors: Hostinger: Create your website today. Go to hostinger.com/practical and use practical for 10 percent off now. Perplexity AI: "Start your free trial of Perplexity Computer today at pplx.ai/practical and experience the next phase of AI. Resources and Events: Register for upcoming webinars…
How can AI models learn from private data without compromising privacy? Chris is joined by Lorenzo Sani, Research Scientist at Flower Labs and PhD researcher at Cambridge, to explore federated learning and privacy-preserving AI. They discuss how collaborative learning can expand access to private data for LLM training, how model trajectories can help improve agentic AI systems, and the benefits of open-weight models. The conversation also explores real-world applications of locally hosted AI agents, from healthcare and robotics to everyday automation (for a Halloween party). Featuring: Lorenzo Sani – LinkedIn Chris Benson – Website, LinkedIn, Bluesky, GitHub, X Links: Endeavor model page Introducing Endeavor 1.1 Sponsors: Hostinger: Create your website today. Go to hostinger.com/practical and use practical for 10 percent off now. Perplexity AI: "Start your free trial of Perplexity Computer today at pplx.ai/practical and experience the next phase of AI. Resources and Events: Register for upcoming webinars…
Episodios
Implementing Federated Learning to enhance Agentic AI
EscuchadoHow can AI models learn from private data without compromising privacy? Chris is joined by Lorenzo Sani, Research Scientist at Flower Labs and PhD researcher at Cambridge, to explore federated learning and privacy-preserving AI. They discuss how collaborative learning can expand access to private data for LLM training, how model trajectories can help improve agentic AI systems, and the benefits of open-weight models. The conversation also explores real-world applications of locally hosted AI agents, from healthcare and robotics to everyday automation (for a Halloween party). Featuring: Lorenzo Sani – LinkedIn Chris Benson – Website, LinkedIn, Bluesky, GitHub, X Links: Endeavor model page Introducing Endeavor 1.1 Sponsors: Hostinger: Create your website today. Go to hostinger.com/practical and use practical for 10 percent off now. Perplexity AI: "Start your free trial of Perplexity Computer today at pplx.ai/practical and experience the next phase of AI. Resources and Events: Register for upcoming webinars…
Abundant Intelligence at the Midwest AI Summit Part 2
EscuchadoHow do organizations decide what AI should do, where to set boundaries, and when to keep humans in control? In this special episode, we bring you three more talks from the Midwest AI Summit, exploring how organizations are putting AI into practice. Don Barger of the International Mission Board shares how establishing an AI charter helped define what the organization would and wouldn't use AI for. Mark Lay of Noblis explores four key decisions for managing AI across an organization, from delegation and accountability to technical debt. And Darren Taillie of Aerocore Technologies walks through how his team uses AI agents, text-to-SQL, and vision models to improve data access and automate work order verification. Featuring: Don Barger – LinkedIn Mark Lay – LinkedIn Darren Taillie – LinkedIn Daniel Whitenack – Website, GitHub, X Links: Noblis International Mission Board AeroCore Technologies Sponsors: SerpAPI: A Web Search API that gives developers real-time, structured access to search engine results. Visit…
Abundant Intelligence at the Midwest AI Summit
EscuchadoIn this special episode, we bring you highlights from three talks at the Midwest AI Summit. Heidi Porter explores how to build reliable AI-augmented workflows using the right tools, evaluations, and guardrails. Kevin Solorio shares why building AI with frontline workers, not just for them, is key to earning trust and driving adoption, emphasizing collaboration and continuous feedback. And Chris Shinkle and Andrew Dunlap of SEP discuss how software teams can find the right level of AI autonomy based on their goals, constraints, and verification needs, sharing lessons from teams using AI to build software more effectively. Featuring: Heidi Porter – LinkedIn Kevin Solorio – LinkedIn Chris Shinkle – LinkedIn Andrew Dunlap – LinkedIn Daniel Whitenack – Website, GitHub, X Links: Moyer Group AI SEP Focused Sponsors: Hostinger: Create your website today. Go to hostinger.com/practical and use practical for 10 percent off now. Resources and Events: Register for upcoming webinars here! Prior Webinars from our partner…
Exploit Development, Agentic Vulnerability Discovery, and Fake PoCs
EscuchadoAI is changing cybersecurity, accelerating vulnerability research and exploit development while raising new questions about reliability, risk, and guardrails. Daniel and Chris talk with Spencer McIntyre, Director of Exploit Development at VulnCheck, about how agents are being used to discover vulnerabilities, why many proof-of-concept exploits (POCs) fail to deliver, and how initial access intelligence helps security teams prioritize real threats. They also explore the limitations of AI-assisted exploitation, the challenges of AI guardrails for security researchers, and what these developments mean for the future of threat intelligence. Featuring: Spencer McIntyre – LinkedIn Daniel Whitenack – Website, GitHub, X Chris Benson – Website, LinkedIn, Bluesky, GitHub, X Links: VulnCheck Go Exploit framework Initial Access Intelligence Sponsors: Hostinger: Create your website today. Go to hostinger.com/practical and use practical for 10 percent off now. Resources and Events: Register for upcoming webinars here!…
Is Education Failing our Students in this AI-Driven World?
EscuchadoSchools and universities are failing to adapt to our modern world, in which AI is becoming increasingly pervasive in all aspects of life and work. In fact, AI may be changing what should be considered foundational knowledge that all students must learn. In this Fully Connected episode, Daniel and Chris explore the role of AI in education and the future of learning. They note the bureaucratic inhibitors to educational reform, and the fact that classroom teachers don’t have the authority to innovate and personalize the learning process for their students, and discuss how AI tools can support personalized learning while preserving critical thinking, creativity, and problem-solving skills. Featuring: Daniel Whitenack – Website, GitHub, X Chris Benson – Website, LinkedIn, Bluesky, GitHub, X Sponsors: SerpAPI: A Web Search API that gives developers real-time, structured access to search engine results. Visit serpapi.com/practicalai to get started for free and get 250 searches every month. Resources and Events:…