What Is Jev? Fast discriminative models vs. LLMs
📖 Codelab next: Getting started with Discriminative (Jev/DiffusionGemma) models https://g.dev/ai/discriminative-models.
High-signal audio and video shows covering AI engineering, MLOps, modern data platforms, analytics, and technical leadership. Each episode is processed through our pipeline and summarized with Google Gemini.
31
12 Spotify • 19 YouTube
566
Technical Depth
2 Platforms
Audio RSS + Video
Gemini 2.0
Executive Summaries
Hand-picked technical podcasts and YouTube engineering channels tracked by our pipeline.
Cutting through AI bullsh*t.Come join the discussion on Discord! https://discord.gg/4UNKGf3
Conversations that explore technology, history, philosophy, physics, mathematics, biology, chemistry, engineering, AI, robotics, programming, music, film, art, sports, psychology, neuroscience, geopolitics, business, economics, religion, astronomy, and the human condition with people from all walks of life.
Demystifying AI for the intelligently curious
@SoftwareDaily
YouTube Channel Software Engineering Daily
@AIJasonZ
YouTube Channel AI Jason
@AndrejKarpathy
YouTube Channel Andrej Karpathy
This show goes behind the scenes for the tools, techniques, and difficulties associated with the discipline of data engineering. Databases, workflows, automation, and data manipulation are just some of the topics that you will find here.
@duckdb
YouTube Channel DuckDB
Continuously updated feed with executive AI summaries and extracted topics.
📖 Codelab next: Getting started with Discriminative (Jev/DiffusionGemma) models https://g.dev/ai/discriminative-models.
Choosing the right integration path for your Looker AI agents can be tricky. In this video, we break down the key differences between the native Looker-Managed MCP Server and the open-source MCP Toolbox for databases to help you pick the best approach for your workload. Resources: * Use the Looker Managed MCP Server → https://g.dev/cloud/looker-managed-mcp * Get Started with MCP toolbox for databases → https://g.dev/cloud/mcp-toolbox-for-databases-looker Speaker: Chrissie Goodrich Products Mentioned: Looker
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 – LinkedInChris Benson – Website, LinkedIn, Bluesky, GitHub, XLinks:Endeavor model pageIntroducing Endeavor 1.1Sponsors: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 here!Prior Webinars from our partner Prediction GuardMidwest AI Summit 2026Chris’s new book The Art of Swarming will be published soon, written to be the seminal foundational book for the fledgling swarming industry, defining the principles and architecture that enable autonomous agentic UxS swarms with emergent distributed embodied intelligence. You can find out more at his website: https://chrisbenson.com
In this month's episode of ICYMI, Jon Krohn moves from the fears that surround AI to the work it makes possible when we use it well. Hear from Richard Socher, Carly Taylor, Jeff Hancock, Kate Niederhoffer and John Renne, discussing why the founder of a company built to create recursively self-improving superintelligence is not afraid of the idea, how inviting your fears to tea helps you keep growing, why AI-generated “workslop” that is harmless fun on social media becomes infuriating at work and how two hours of AI-assisted research can now do the work of a half-million-dollar grant. Additional materials: www.superdatascience.com/1044 Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information. In this episode you will learn: (00:20) Recursive Self-Improvement: The Eureka Machine (08:21) Workslop, Glass Cliffs and Inviting Your Fears to Tea (14:49) Workslop: The Hidden Cost of AI-Generated Work (21:58) AI for Real Estate, Walkable Cities and Climate Action
🔗 Document understanding → https://g.dev/cloud/document-understanding 🔗 Gemini models → https://g.dev/cloud/gemini-models ⚡ How to compare documents 🍿 Just a moment #02 Have you ever had to compare two versions of a complex document? What if one is a digital PDF and the other is a scan, spanning hundreds of pages, with different layouts and pagination? In this episode, see how Gemini's native multimodality spots subtle differences, from tiny typos to $100M contract updates, in a single prompt. 🍵 Grab your tea, coffee, or matcha… It only takes a moment! Prompt template used in the video example: [DOCUMENT_A] … [/DOCUMENT_A] [DOCUMENT_B] … [/DOCUMENT_B] TASK: Perform an exhaustive, character-by-character textual comparison between DOCUMENT_A and DOCUMENT_B. CRITICAL REQUIREMENTS: 1. You must systematically verify every numbered paragraph sequentially from start to finish. 2. You must catch every single difference, including single-character changes, minor typos, spelling corrections (e.g., missing letters in common words), and punctuation changes, in addition to substantive changes (numbers, dates, names). OUTPUT FORMAT: ### Difference #[1, 2, 3…] - Location: [location] - Evidence A: "[short quote from Document A]" with difference in **bold** - Evidence B: "[short quote from Document B]" with difference in **bold** - Explanation: [brief description] 📌 Follow Laurent online: 🔗 LinkedIn → https://goo.gle/laurent-picard-linkedin 🔗 X → https://goo.gle/laurent-picard-x 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #GoogleGemini #GenerativeAI #GoogleCloud #DocumentUnderstanding #NativeMultimodality #JustAMoment #TechIn2Minutes Speaker: Laurent Picard Products mentioned: Gemini
🎙️ Episode 110 · November 2026Start Small, Then Scale: Huntington Bank's Data Governance Success StoryNot sure where to start with master data or governance? One bank started with the low-stakes data first and built from there.📌 In this episode:- Why Huntington started with reference data: lists of values, not customer records- Moving on to householding, including trusts and wealth relationships, refreshed every 15 minutes instead of overnight- Cutting duplicate customer records from 15–18% to 3%, against an industry benchmark of around 10%- The dotted-line governance model that got traction after centralized and decentralized attempts stalled💬 The takeaway: "To be results oriented is then to take action and give momentum to what the actual data quality … measures are telling you." — Shaun RankinAbout the host + guestMalcolm Hawker is a former Gartner analyst, Chief Data Officer at Profisee, Editor-in-Chief of CDO Matters on Substack, and host of the CDO Matters Podcast.Guest: Shaun Rankin is SVP of Information Governance at Huntington Bank. He leads the bank's customer master, reference data and commercial party relationship data.🔗 Watch + full transcript: https://profisee.com/podcast/start-small-then-scale-a-banks-data-governance-success-story/Subscribe to CDO Matters Monthly → https://profisee.com/cdo-matters-community/#join-communityFollow Malcolm on LinkedIn → https://www.linkedin.com/in/malhawker/Guest → https://www.linkedin.com/in/shaunrankin
Everyone's quoting Karpathy's "vibe coding" post. Almost no one quotes the part where he says it's for throwaway weekend projects, not production. Struggling with AI and Software? Here is my new book available for purchase on https://mythicaltokenmonth.com/ Come have a chat on our Discord Channel: https://discord.gg/4UNKGf3 Buy me a coffee https://ko-fi.com/datascience Check my company Amethix Technologies https://amethix.com References https://mythicaltokenmonth.com/ ✨ Connect with us! Personal newsletter: https://defragzone.substack.com 📩 Newsletter: https://datascienceathome.substack.com 🎙 Podcast: Available on Spotify, Apple Podcasts, and more. 🐦 Twitter: @DataScienceAtHome 📘 LinkedIn: https://www.linkedin.com/in/fragadaleta/ Instagram: https://www.instagram.com/datascienceathome/ Facebook: https://www.facebook.com/datascienceAH LinkedIn: https://www.linkedin.com/company/data-science-at-home-podcast NEW TO DATA SCIENCE AT HOME? Welcome! Data Science at Home explores the latest in AI, data science, and machine learning. Whether you’re a data professional, tech enthusiast, or just curious about the field, our podcast delivers insights, interviews, and discussions. Learn more at https://datascienceathome.com SEND US MAIL! We love hearing from you! Send us mail at: hello@datascienceathome.com Don’t forget to like, subscribe, and hit the 🔔 for updates on the latest in AI and data science! We are excited to be featured in list of the top machine learning and data science podcasts in the world! https://www.millionpodcasts.com/machine-learning-podcasts/ https://www.millionpodcasts.com/data-science-podcasts/ https://www.millionpodcasts.com/big-data-podcasts/
▶ Watch next: Make your website agent ready with WebMCP https://www.youtube.com/watch?v=FARxSG_EY98
🔗 Gemini models → https://g.dev/cloud/gemini-models ⚡ What is native multimodality? 🍿 Just a moment #01 Did you know there are three tokenizers involved when Gemini processes multimodal inputs? In this episode, we peek under the hood to see how text, vision, and audio tokenizers work together. 🍵 Grab your tea, coffee, or matcha… It only takes a moment! 📌 Follow Laurent online: 🔗 LinkedIn → https://goo.gle/laurent-picard-linkedin 🔗 X → https://goo.gle/laurent-picard-x 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #GoogleGemini #GenerativeAI #GoogleCloud #NativeMultimodality #JustAMoment #TechIn2Minutes Speaker: Laurent Picard Products mentioned: Gemini
What happens when the people who understand your customers can build the software to help them? At Holiday Extras, Codex is helping turn that ambition into reality—from rebuilding its main app in two weeks to responding faster to customer feedback. Hear how CEO Matthew Pack, David Lee and Liam Thompson are giving colleagues the confidence to build, improving the travel experience and rethinking what the business can achieve with OpenAI. Read the full story: https://openai.com/business/customer-stories/holidays-extras-codex/
A live keynote featuring OpenAI's latest cyber announcements.
Erik Bernhardsson, CEO and Co-Founder of Modal, explains what drove demand for Modal's sandboxes (vibe coding apps, background agents, and reinforcement learning rollouts) and why he thinks agent harnesses should run outside the sandbox, with sandboxes that are short-lived, maybe one per tool call. He also covers how Modal, which builds AI infrastructure for inference, training, and sandboxes, moved up the stack with auto and shared endpoints for open source models, when he thinks RL is worth its cost over supervised fine-tuning, and the multi-node training and discounted batch products Modal is building. The conversation closes on how Modal's engineers use coding agents and why Erik is watching voice to voice models. This session was captured at Interrupt New York City, the agent conference by LangChain. Chapters: 0:00 What Modal builds for inference, training, and sandboxes 0:57 Was Modal built for AI workloads before ChatGPT? 2:47 What made Modal's sandboxes finally take off? 5:35 Why Modal is moving sandboxes from gVisor to VMs 7:11 Should the agent harness run inside the sandbox? 10:09 Do agents need a full VM or a lightweight sandbox? 12:27 Are open source models close enough to swap in? 15:49 When is RL worth it over supervised fine-tuning? 17:08 Why Modal built auto and shared inference endpoints 18:43 Can reinforcement learning be packaged as a product? 19:44 What Modal is building next for training and batch jobs 21:09 Why Modal built a team of forward deployed engineers 23:25 How Modal uses coding agents and MCP servers internally 26:41 Why Erik is bullish on voice to voice models Resources: → Modal: https://modal.com → Modal Sandboxes: https://modal.com/products/sandboxes → Deep Agents with Modal sandboxes: https://docs.langchain.com/oss/python/integrations/sandboxes/modal → Interrupt, the agent conference by LangChain: https://interrupt.langchain.com
Getting an agent working on your laptop takes hours, but putting it in front of real users can take weeks of infrastructure work around the agent itself. This new LangChain Academy course shows you how to close that gap with LangSmith Managed Agents, where you define the agent and the context it needs and deploy it with one command. You'll start with how an agent is put together, then run it on the managed platform with its own sandbox and user credentials. From there you'll add authentication and connect the agent to Slack so people can use it where they already work. The course ends with evaluation, so you catch problems before your users do. Chapters: 0:00 Why agents stall between prototype and production 0:33 What LangSmith Managed Agents handles for you 0:46 What you'll learn in the course Resources: → LangChain Academy: https://academy.langchain.com/courses/managed-agents → LangSmith Managed Agents docs: https://docs.langchain.com/langsmith/python/managed-deep-agents-overview → LangSmith Managed Agents quickstart: https://docs.langchain.com/langsmith/python/managed-deep-agents-quickstart
See what you can build using our latest Gemini models in Google Antigravity. From in-browser animation and multimodal prototyping to autonomous codebase modernization, explore how you can ship complex architectures straight from a prompt. What are you building with Gemini in Google Antigravity? Share your projects in the comments! Try out Google Antigravity today → https://goo.gle/4zGqjzT Subscribe to Google for Developers → https://goo.gle/developers Speaker: Tiger Souvannakoumane Products Mentioned: Google Antigravity
Build your custom evaluation with ADK → https://g.dev/cloud/cpm-vid-adk Codelab → https://g.dev/ai/self-evolving Learn how to build, test, and automate custom evaluations for your AI agents using Google's Agent Development Kit (ADK). In this step-by-step tutorial, Annie Wang teaches how to define what "success" means for complex agents, compare using requirement-based checkers, and integrate agent tests directly into CI/CD deployment pipelines using pytest. Chapters: 00:00 - Intro & the 4 pillars of agent evaluation 00:28 - What counts as success? 01:56 - Evaluation approaches: Comparators 03:45 - How to check: Deterministic code vs. LLM as a judge 05:50 - Building a custom metric in Python 08:00 - Configuring ADK eval & validating the evaluator 11:00 - Automating agent testing in CI/CD with Pytest Speaker: Annie Wang Products Mentioned: Agent Development Kit
📖 Read next: Developer's Guide to Building ADK Agents with Skills (Google Developers Blog) https://developers.googleblog.com/developers-guide-to-building-adk-agents-with-skills/
Get started with Codex Security, from installing the plugin to running your first scan. Learn how to select a repository, add context, review findings, and generate a patch. Then follow the fix into GitHub and see how to use the CLI to bring security scans into your automation workflows.
Bring security reviews into your pull request workflow with Codex Security. Learn how to check your GitHub connection, request a review, work through a fix, and review the change again. Then configure automatic reviews for your repository, including triggers and severity thresholds.
Learn how to request access to Daybreak Blue and enable it for your workspace and API organization. This walkthrough covers business verification, workspace permissions, role-based access controls, and confirming access in Codex. You’ll also see how to set up a project and API key for automation.
Your AI agent has been editing your Power BI reports with its screen turned off. It changes the JSON, says "Done! Your report is pink!" – and it's still blue. The Power BI Desktop Bridge (preview) fixes that: the agent can now check the state of your report, take a screenshot to verify its own work, and reload Power BI Desktop – all in one go. In this video Marthe shows you how to enable and install the Power BI Desktop Bridge, what the manifest tells the agent it can (and can't) do, why "closing the feedback loop" is the whole point, and then we put it to the test with GitHub Copilot. Spoiler: it fails first. Then it fixes itself. And no – verification is not the same as quality. You still have a job. 😅 ⏱️ CHAPTERS 00:00 Why AI agents fly blind in Power BI 00:45 Enable the Desktop Bridge in Power BI Desktop 01:06 Install the Power BI Desktop Bridge CLI 01:47 Check the bridge status 02:19 The manifest: what the agent can actually do 03:20 Wait, what's a "feedback loop"? 04:48 What Power BI can learn from software developers 05:15 Verification ≠ quality 05:40 Demo: making the report pink with GitHub Copilot 06:52 It failed… then it verified and fixed itself 07:25 Put this in your agent spec 🔗 LINKS Power BI Desktop Bridge docs: https://learn.microsoft.com/power-bi/developer/agentic/power-bi-desktop-bridge-overview Power BI Desktop Bridge CLI https://www.npmjs.com/package/@microsoft/powerbi-desktop-bridge-cli?activeTab=readme 🎓 Go deeper in THE CUBE: https://guyinacube.com/memberships 💬 Already experimenting with agentic report development? Tell me in the comments – or come have a real conversation in THE CUBE. LET'S CONNECT! - Official website: https://guyinacube.com - LinkedIn: https://www.linkedin.com/company/guyinacube - X: http://twitter.com/guyinacube - Facebook: http://www.facebook.com/guyinacube - Bluesky: https://bsky.app/profile/guyinacube.bsky.social #GuyInACube #PowerBI #MicrosoftFabric
Epizoda poskytuje strategický přehled o vývoji ekosystému Snowflake a definuje klíčové dovednosti, které budou nezbytné pro datové inženýry v roce 2027. Zaměřuje se na moderní architekturu datových platforem a integraci pokročilých analytických nástrojů.
▶ Watch next: Introduction to Agent2Agent (A2A) Protocol https://www.youtube.com/watch?v=Fbr_Solax1w
▶ Watch next: Gemini 4 Argon: 10 incredible AI demos https://www.youtube.com/watch?v=gRhM1h10T3U
Full Season 1 playlist → https://www.youtube.com/playlist?list=PLc2r9FdYHRlg What actually separates a real-time multimodal AI agent from a chatbot with voice and vision bolted on? In the Season 1 finale of The Omni App, we connect all six layers of a bidirectional live multimodal agent, voice, Google ADK, tool calling, browser control, hybrid memory, and real-time vision, and distill the entire architecture into two core design questions that keep an open live session feeling like one natural conversation. 📺 Watch all of season 1 here: * Trailer → https://youtu.be/YGgErBnx6po * Ep 1 · Voice → https://youtu.be/pFc-HcUgFgY * Ep 2 · ADK → https://youtu.be/yQEKMsCtsmE * Ep 3 · Tools → https://youtu.be/Sdrpso7IKtU * Ep 4 · Browser → https://youtu.be/xDL5DFMo1-Y * Ep 5 · Memory → https://youtu.be/8C4bh59FtsI * Ep 6 · Vision → https://youtu.be/dNGchf4InU0 🧠 Watch along and learn: * Omni App (Perceive → Reason → Express) vs. turn-based request-response chatbots * How all 6 layers work together in one open live loop * Question 1 (Input): Continuous streams (mic, live camera) vs. complete inputs (screenshots, photos, text) * Question 2 (Execution): Blocking vs. non-blocking work—acknowledging fast while moving slow work off the live hot path * Architecture boundaries: Live path vs. background, SQL facts vs. semantic vectors, snapshots vs. frame streams ⏱️ Chapters: 00:00 - Intro: What Is an Omni App & Bidirectional Live Loop? 00:55 - Chatbot vs. Omni App: Request-Response vs. Live Workflow 01:32 - Ep 1 Recap: Real-Time Bidirectional Voice & Barge-In 01:47 - Ep 2 Recap: Structuring the Live Loop with Google ADK 02:05 - Ep 3 Recap: Live Tool Calling Without Breaking the Flow 02:24 - Ep 4 Recap: Voice-Driven Browser Control via Screenshots 02:41 - Ep 5 Recap: Structured Facts vs. Semantic Vector Memory 03:04 - Ep 6 Recap: Real-Time Vision — Snapshots vs. Frame Streams 03:21 - Architecture Question 1: Continuous Stream vs. Complete Input 04:05 - Architecture Question 2: Blocking vs. Non-Blocking Work 04:42 - Core Takeaway: Designing Multimodal Agent Boundaries 05:05 - Season 2 Preview: Deeper Perception & Creative Expression 🔔 Subscribe and stay tuned for Season 2, where our agents go deeper on multimodal understanding and creative generation! More resources: Gemini Live API docs → https://g.dev/cloud/gemini-live Agent Development Kit (ADK) docs → https://g.dev/cloud/adk-docs Google Cloud SQL docs → https://g.dev/cloud/docs-sql AlloyDB docs → https://g.dev/cloud/docs-alloydb Vertex AI Agent Engine Memory Bank → https://g.dev/ai/memory-bank-overview Follow Annie online: LinkedIn → https://goo.gle/annie-linkedin X → https://goo.gle/annie-x Watch more The Omni App → https://g.dev/cloud/modern-ai-app 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #AIAgents #MultimodalAI #SoftwareArchitecture #GeminiLiveAPI #GoogleADK #VoiceAI #GoogleCloud #AgenticAI #LLM #VertexAI Speaker: Annie Wang Products Mentioned: Gemini Live API, Agent Development Kit, Google Gen AI SDK, Google Cloud SQL, AlloyDB, Vertex AI Agent Engine Memory Bank
Try clearing your search query or selecting a different category.
Compare the architectural patterns discussed in these shows with verified S&P 500 employer hiring intensity across our 12 Canonical Roles.