I gave a Gemma 4 AI agent a sandbox and it taught itself physics | The Agent Factory Podcast

Google Cloud Tech · Beginner ·🧠 Large Language Models ·3w ago
Gemma 4 → https://goo.gle/4tFKxGE Gemma 4 in Google Cloud → https://goo.gle/4mpWI8f Deploy Gemma 4 in Cloud Run → https://goo.gle/48mIizK Can an open source model running entirely offline on a smartphone outperform the cloud based APIs of last year? In this episode of The Agent Factory, we dive deep into the release of Gemma 4, the latest family of open models from Google DeepMind. We answer the critical question for developers: how do you balance high intelligence with low hardware overhead and data sovereignty? You’ll see Omar Sanseviero from Google DeepMind explain the architectural breakthroughs that allow Gemma 4 to deliver massive "intelligence per parameter." We don’t just talk about the specs; we show them in action. You’ll watch a food tour agent navigate Seattle via an MCP server, and witness a stunning demo where Gemma 4 reasons through laws of physics to code a bouncing ball animation from scratch in a Python sandbox. We also break down Gemma 4 adopting the Apache 2.0 license and what that opens up for you. Whether you are a cloud architect or an independent developer, you will walk away with a clear roadmap for self hosting these models. You'll learn how to leverage new features like native function calling, structured JSON output, and multimodal understanding to build agents that are faster, cheaper, and more private than ever before. Chapters: 0:00 - Introduction 0:50 - Meet Omar Sanseviero from Google DeepMind 1:40 - What makes Gemma 4 a "major milestone" for agents? 1:53 - Demo: Running Gemma 4 on an Android phone 2:45 - Agent skills running on a phone! Function calling, structured output, thinking, and multi-modal understanding. 4:05 - The move to Apache 2.0: Why the license change matters 5:29 - ADK demo: Building a Food Tour agent with Google Maps 8:03 - Demo: How Gemma 4 uses physics and gravity to create animations using Python code 12:05 - Why 256k context on a local device is a game changer 12:34 - The explosion of code execution a
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

⚡
The Wall Every AI Has Been Hitting And the Startup That Claims to Have Broken Through
Startup SubQ claims to have broken through the context length constraint in AI, solving a decade-long limitation
Medium · LLM
 ⚡
Unsolved AI Mystery Is Solved Along With Lessons Learned On Why ChatGPT Became Oddly Obsessed With Gremlins And Goblins
Discover why ChatGPT became obsessed with gremlins and goblins, and learn vital lessons from this AI mystery
Forbes Innovation
 ⚡
The Human Element in AI-Based Emotion Recognition: When Machines Start to Read Our Faces
Learn how AI-based emotion recognition systems use facial analysis to understand human emotions and the importance of the human element in these systems
Medium · Deep Learning
 ⚡
ChatGPT vs Claude AI: Which AI Tool is Best for Your Business? — Complete Guide by Amigoways
Learn how to choose between ChatGPT and Claude AI for your business needs and understand their differences
Medium · ChatGPT

Chapters (10)

Introduction
0:50 Meet Omar Sanseviero from Google DeepMind
1:40 What makes Gemma 4 a "major milestone" for agents?
1:53 Demo: Running Gemma 4 on an Android phone
2:45 Agent skills running on a phone! Function calling, structured output, thinking
4:05 The move to Apache 2.0: Why the license change matters
5:29 ADK demo: Building a Food Tour agent with Google Maps
8:03 Demo: How Gemma 4 uses physics and gravity to create animations using Python c
12:05 Why 256k context on a local device is a game changer
12:34 The explosion of code execution a
Up next
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Watch →