Train-Test split: Evita el sobreajuste

Regresión Lineal en Machine Learning

Cómo funciona un árbol de decisión

Métricas clave: MAE, RMSE y Matriz de Confusión

In this episode of the ODSC AiX Podcast, host Sheamus McGovern reconnects with Paige Bailey, Engineering Lead at Google DeepMind for the Developer Experience team. Paige shares how the Gemini ecosystem has evolved since her last appearance, including the launch of Gemini 2.5 DeepThink, multimodal video generation with Veo 3, real-time music creation with Lyria RT, and groundbreaking advances in agentic and on-device AI systems. The conversation explores the rapid rise of agent-based workflows, AI-powered robotics, and the growing divide between cutting-edge tools and real-world adoption.

Key Topics Covered:
Gemini 2.5 DeepThink & Reasoning Models
The model that won gold at the International Mathematical Olympiad (IMO)
Use cases for DeepThink, Pro, Flash, and FlashLite variants
Using Gemini Live API for real-world robotics and decision planning
Role of multimodal inputs (video, audio, text) in enabling embodied AI
On-Device AI & Ubiquity
Implications for edge deployment, cost reduction, and accessibility
Veo 3: Multimodal Video Generation
Lyria RT: Real-Time Music Generation
Gemini Live API & Voice Interfaces
Real-time bidirectional voice, screen understanding, and tool calling
Rise of voice as the dominant AI interface
Use of SynthID and digital watermarking to detect deepfakes
Future of AI-agent orchestration via MCP servers

Memorable Outtakes:
On the pace of model development: “A 4-billion parameter model on-device now outperforms our best cloud model from six months ago. That’s pretty magical.”  — Paige Bailey 
On the role of AI agents in robotics: “You can say, ‘Hey robot, go get me that apple,’ and Gemini will plan the task, route it, and call the right control models.” — Paige Bailey 
On the AI adoption gap: “In the Bay Area, we use AI hourly. But when I talk to developers in the Midwest, they often aren’t using it at all.” — Paige Bailey 

References & Resources:
Paige Bailey
Dynamic Web Paige: https://webpaige.dev/
LinkedIn: https://www.linkedin.com/in/dynamicwebpaige
GitHub: https://github.com/dynamicwebpaige
Medium: https://medium.com/@dynamicwebpaige
Previous podcast with Paige: https://podcasters.spotify.com/pod/show/ai-x-podcast/episodes/Googles-AI-Powered-Tools-for-Data-Scientists-Building-the-Automated-Future-of-Data-Science-with-Paige-Bailey-e2p3t6e

Resources mentioned
International Mathematical Olympiad (IMO): https://www.imo-official.org
Model Context Protocol (MCP): https://modelcontextprotocol.io/docs/getting-started/intro
Gemini 2.5 Deep Think: https://blog.google/products/gemini/gemini-2-5-deep-think/
Veo 3: https://deepmind.google/technologies/veo/
Lyria RT & Music AI Sandbox: https://deepmind.google/technologies/lyria/
SynthID & Deepfake Watermarking: https://deepmind.google/technologies/synthid/
Gemma Models: https://ai.google.dev/gemma
Gemini Live API Docs: https://ai.google.dev/gemini-api/docs/live
Google AI Studio: https://ai.google.dev

Sponsored by:
 🔥 ODSC AI West 2025 – The Leading AI Training Conference
Join us in San Francisco from October 28th–30th for expert-led sessions on generative AI, LLMOps, and AI-driven automation.
Use the code podcast for 10% off any ticket.
Learn more: https://odsc.ai




Inside Google’s New AI Stack with Paige Bailey

This is episode 304 recorded on September 4th, 2025, where John & Jason talk the Microsoft Fabric August 2025 Feature Summary including a new Flat list view in Deployment pipelines, Bursting controls for Data Engineering workloads, new test capabilities for User Data Functions, the ability to server real-time predictions with ML model endpoints, several updates to Data Warehouse, Database tree in edit tile and AzMon data sources for RTI, the ability to use Python Notebooks to read/write to Fabric SQL Databases, Auto table creation on destination in copy job in Data Factory, and much, much more.

For show notes please visit www.bifocal.show

Episode 304 - Microsoft Fabric August 2025 Feature Summary

In this episode of the ODSC AiX Podcast, host Sheamus McGovern sits down with Kwindla Hultman Kramer, co-founder of Daily and creator of the open-source project PipeCat. Kwindla is a pioneer in real-time audio, video, and human-computer interaction. He shares his journey from MIT Media Lab to building voice interfaces that are now shaping the future of software interaction.
Together, they explore why voice is poised to become the primary interface for AI, what makes voice agents so challenging to build, and how real-world use cases—from call centers to appointment scheduling—are proving the value of well-designed voice AI systems.
Key Topics Covered:
Why voice is at a “2007 iPhone moment” for user interfaces
What makes a great voice AI experience (and why Siri/Alexa missed the mark)
The rise of voice agents in production use: healthcare, banking, customer service, and more
Real-world engineering challenges in building voice-first AI agents
How latency, streaming, turn detection, and interruptibility define user experience
The architecture and motivation behind the PipeCat open-source toolkit
Why LLMs need context engineering in voice workflows
Differences between text-first vs. voice-first agent design
Hybrid models: routing between cloud and on-device inference
What’s missing in voice AI today: memory, context, and bi-directional streaming
Synthetic data and the future of training audio models
Advice for developers just starting with voice AI
Memorable Outtakes:
“Voice is at the tipping point—like mobile was in 2007.”
“All UI is going to become liquid, generated on the fly by natural voice speech.”
“You’ve probably already spoken to an AI agent—you just didn’t realize it.”
References & Resources:
PipeCat GitHub: https://github.com/pipecat-ai/pipecat
Kwindla Hultman Kramer: https://www.linkedin.com/in/kwkramer/
Daily (video/audio infrastructure company): https://www.daily.co
Voice AI and Voice Agents Guide: https://voiceaiandvoiceagents.com
Smart Turn Detection Model: https://github.com/pipecat-ai/smart-turn
Gemini 1.5 and Google Live API: https://blog.google/products/gemini/gemini-live-updates-august-2025/
NotebookLM by Google: https://notebooklm.google/
Suno AI (music generation): https://www.suno.ai/
Whisper (OpenAI ASR Model): https://github.com/openai/whisper
Minority_Report: https://en.wikipedia.org/wiki/Minority_Report_(film)
Sponsored by:
 🔥 ODSC AI West 2025 – The Leading AI Training Conference
Join us in San Francisco from October 28th–30th for expert-led sessions on generative AI, LLMOps, and AI-driven automation.
Use the code podcast for 10% off any ticket.
Learn more: https://odsc.ai



Voice AI is About to Get Loud with Kwindla Kramer

What if the next leap in AI isn’t bigger at all? Samsung just unveiled a tiny model built to run on your phone, earbuds, and watch.
We unpack why on-device AI matters: faster responses, lower costs, and stronger privacy with your photos, voice, and messages processed locally. Harry Kermode explains how tiny AI works: distillation, pruning, quantization, and NPUs that wake only when needed. We also map the trade-offs and the likely hybrid handoff between edge and cloud.
Expect everyday devices to feel smarter by default, reshaping app design, battery expectations, and how personal your AI becomes without sending everything to the cloud. Plus, the privacy fine print and what benchmarks and tools to watch next.
If you enjoyed this explainer, follow AI Daily, share the episode, and leave a review. 

FULL TRANSCRIPT: I can’t replicate that show’s exact style, but here’s a concise, narrative news explainer in a similar tone.

From AI Daily, I’m Harry Kermode.

Today: what if the next big leap in artificial intelligence isn’t bigger at all? Samsung has unveiled a tiny AI model designed to run on the devices we carry—phones, earbuds, even watches. It’s a bet that the future of AI lives at the edge, not in the cloud.

Here’s why that matters. When AI runs on your device, your data doesn’t need to travel. That means faster responses, lower costs, and a real shift in privacy—your voice, your photos, your messages can be processed locally, not on someone else’s server.

Imagine your morning: you dictate a text on the subway, offline. Your watch translates a phrase on the fly. Your camera de-blurs a photo as you snap it. No spinning “connecting” icon. No signal? No problem.

Under the hood, “tiny AI” isn’t magic—it’s engineering. Start with a capable model, then compress it: distillation to teach a smaller network the tricks of a larger one, pruning to snip away redundant connections, quantization to store numbers more efficiently. Pair that with modern phone chips—neural processing units tuned for matrix math—and clever scheduling so models wake only when needed. The result: meaningful intelligence within a tight power budget.

There are trade-offs. Smaller models can’t juggle sprawling tasks or remember long conversations. Expect a hybrid approach: on-device for speed and privacy, the cloud for heavy lifting, with seamless handoffs you barely notice.

The stakes are big. If everyday devices become smart by default, AI stops being a destination and becomes an atmosphere. That’s democratizing—and disruptive. App makers will design for on-device first. Carriers could see fewer data-hungry requests. Companies will compete on battery life, latency, and how well tiny models adapt to you personally.

And privacy? On-device processing keeps data local, but it isn’t a free pass. Companies will need transparent update policies, secure enclaves for sensitive data, and clear controls so you can decide what stays on your phone and what leaves it.

What to watch next: real-world benchmarks on speed and battery drain, developer tools that make building tiny-model apps easy, and whether Samsung’s move pushes rivals to standardize how edge AI is measured, updated, and secured.

Small models, everywhere. That might be how AI finally becomes part of the background—powerful, personal, and almost invisible.

That’s AI Daily. I’m Harry Kermode. See you tomorrow.

The Future of AI Is Small and On-Device

In this episode of the ODSC Ai X Podcast, host Sheamus McGovern speaks with Sandi Besen, AI Engineer and Ecosystem Lead at IBM Research, about designing rule-based, production-ready AI agents using IBM’s open-source BeeAI framework. Sandi shares her journey from the performing arts to AI engineering, unpacks the challenges of agent reliability and trust, and explores how frameworks like BeeAI are solving real-world issues through enforceable rules, observability, and open standards. This episode dives deep into multi-agent systems, communication protocols, and what it really takes to deploy AI agents safely and effectively in enterprise environments.

Key Topics Covered:
Sandi’s background and current role at IBM Research
What inspired the creation of the BeeAI framework and platform
The concept of "agent chaos" and how BeeAI brings structure and reliability
Comparison of popular agent frameworks: LangChain, LangGraph, CrewAI
Introduction to emerging agent communication protocols (MCP and A2A)
Enforcing hardcoded rules (conditional requirements) in agents
Building agent behavior guardrails and preventing rogue actions
Importance of observability, memory, and tracing in agent frameworks
Using OpenTelemetry for tracing agent decision-making
Challenges in agent safety, validation, and trust for enterprise use
How BeeAI makes deploying an agent with a UI fast and easy (in under an hour)
When to build from scratch vs. using a framework like BeeAI 
Common mistakes startups make when adopting cutting-edge AI tech
Trends in context engineering and long-term memory
The future of consulting in the age of AI

Memorable Outtakes:
“Agent chaos is real. We needed a way to bring structure, enforce rules, and make agents safe for production.”
“Conditional requirements let you hardcode business logic into your agents — not just suggest behavior, but enforce it.”

References & Resources:
Sandi Besen – AI Engineer & Ecosystem Lead at IBM Research: https://research.ibm.com/people/sandi-besen
Website: https://sandibesen.com/
LinkedIn: https://www.linkedin.com/in/sandibesen/
BeeAI: https://www.ibm.com/think/news/beeai-open-source-multiagent
BeeAI GitHub Repository: https://github.com/i-am-bee/beeai-framework
Agent Communication Protocol (ACP) Course (DeepLearning.AI): https://www.deeplearning.ai/short-courses/acp-agent-communication-protocol/
OpenTelemetry:  https://opentelemetry.io/
Google’s P2 Payment Protocol (for AI agents): https://ap2-protocol.org/
AP2 GitHub: https://github.com/google-agentic-commerce/AP2
OpenAI Agent Commerce Protocol: https://developers.openai.com/commerce/

Sponsored by:
🔥 ODSC AI West 2025 – The Leading AI Training Conference
Join us in San Francisco from October 28th–30th for expert-led sessions on generative AI, LLMOps, and AI-driven automation.
Use the code podcast for 10% off any ticket.
Learn more: https://odsc.ai


AI Agents That Follow the Rules: Sandi Besen

Choosing between a Data Science bootcamp and a traditional degree can shape your tech career path. This blog explores the key differences in duration, cost, curriculum, and job readiness to help you decide the right learning journey. Understand which route best suits your goals and future in data science.

Data Science Bootcamps vs. Traditional Degree Programs Which is Right for You

Gradious is an EdTech platform dedicated to empowering students, graduates, and professionals with industry-ready skills. Our mission is to bridge the gap between academic learning and real-world requirements by offering hands-on training, coding bootcamps, and upskilling programs that prepare learners to excel from day one in their careers.

With Ai X Podcast, Open Data Science Conference (ODSC) brings its vast experience in building community and its knowledge of the data science and AI fields to the podcast platform. The interests and challenges of the data science community are wide ranging. To reflect this Ai X Podcast will offer a similarly wide range of content, from one-on-one interviews with leading experts, to career talks, to educational interviews, to profiles of AI Startup Founders. Join us every two weeks to discover what’s going on in the data science community.

Find more ODSC lightning interviews, webinars, live trainings, certifications, bootcamps here - https://aiplus.training/  
Don't miss out on this exciting opportunity to expand your knowledge and stay ahead of the curve.

New tracks tagged #DATA Science