Why Gemini 3 Will Change How You Build AI Agents with Ravin Kumar (Google DeepMind) скачать в хорошем качестве

Why Gemini 3 Will Change How You Build AI Agents with Ravin Kumar (Google DeepMind)

Join the final cohort of our Building AI Applications course in March, 2026 (25% off for viewers): https://maven.com/hugo-stefan/buildin... Gemini 3 is a few days old and the massive leap in performance and model reasoning has big implications for builders: as models begin to self-heal, builders are literally tearing out the functionality they built just months ago: ripping out the defensive coding and reshipping their agent harnesses entirely. Ravin Kumar (Google DeepMind) joins Hugo to breaks down exactly why the rapid evolution of models like Gemini 3 is changing how we build software. They detail the shift from simple tool calling to building reliable "Agent Harnesses", explore the architectural tradeoffs between deterministic workflows and high-agency systems, the nuance of preventing context rot in massive windows, and why proper evaluation infrastructure is the only way to manage the chaos of autonomous loops. They talk through: The implications of models that can "self-heal" and fix their own code The two cultures of agents: LLM workflows with a few tools versus when you should unleash high-agency, autonomous systems. Inside NotebookLM: moving from prototypes to viral production features like Audio Overviews Why Needle in a Haystack benchmarks often fail to predict real-world performance How to build agent harnesses that turn model capabilities into product velocity The shift from measuring latency to managing time-to-compute for reasoning tasks Show notes and links here: 00:00 Gemini 3.0: A Leap in Model Reasoning 00:43 Implications for Product Builders 01:06 Inside Google: Rewriting Agent Harnesses 01:52 The Evolution of AI Agents 05:14 Understanding Function Calling 07:38 Tool Calling and Complex Interactions 15:38 Building Effective AI Agents 23:04 Evaluation and User Feedback 27:22 Refining Your Product with User Feedback 29:37 Understanding Evaluation Harnesses 31:39 Creating Effective Evaluation Systems 36:05 Challenges in Evaluating Agentic Systems 44:07 The Role of Multimodal Inputs in Agentic Systems 51:54 Future of Agentic Systems and Evaluations 57:40 Exciting Developments in AI Models 59:41 Conclusion and Final Thoughts