NotebookLM en 2026, lo que realmente merece la pena
This video explores NotebookLM 2.0's powerful features for 2026, demonstrating how to use curated sources to generate reports, presentations, Excel files, and vertical videos. The tool works best as a structured context-based system rather than a general chatbot, transforming sources into actionable insights and multiple formats while requiring critical review of outputs.
Summary
The transcript provides a comprehensive guide to NotebookLM's architecture and capabilities. The tool is structured in three parts: sources on the left (PDFs, videos, documents, links), a chat interface in the center that references specific source fragments through citations, and a studio on the right that converts information into reports, presentations, mind maps, infographics, videos, and new vertical shorts. The speaker emphasizes that NotebookLM differs fundamentally from general chatbots because it grounds responses in provided sources with specific citations. Featured notebooks from publishers and researchers offer pre-curated sources on trending topics, allowing users to ask practical questions grounded in real data rather than generic AI responses. Key practical applications include generating downloadable PDFs and PowerPoint presentations from sources, creating Excel files with editable financial models (demonstrated through a car purchase comparison), and producing visual charts from analysis. The speaker introduces three critical validation questions users should ask before trusting a notebook: detecting contradictions between sources, identifying gaps in coverage, and finding missing perspectives or alternative viewpoints. A powerful use case involves combining Gemini and NotebookLM to turn a creator's content into a private mentor—gathering recent videos from a channel, analyzing patterns in the creator's thinking, transforming those patterns into actionable principles, and converting the knowledge into various formats like infographics and presentations. The video also discusses Google's announced short video summary feature, converting complex sources into 60-second vertical videos for mobile learning. The speaker cautions that NotebookLM should not be used as a general chatbot but rather as a tool for working within closed contexts and specific sources. Importantly, outputs require verification—calculations, health claims, financial decisions, and client work must have all data, sources, and conclusions reviewed. The correct approach is using NotebookLM to eliminate slow initial work, organize information, detect patterns, and produce polished first versions rather than expecting final, perfect outputs.
Key Insights
- NotebookLM's value proposition differs fundamentally from general chatbots because it grounds all responses in specific source citations—users can click citation numbers to jump to exact fragments where information originated
- The speaker identifies three critical validation questions to assess source quality before trusting a notebook: detecting contradictions between sources, identifying coverage gaps, and finding missing perspectives or alternative viewpoints
- Excel file generation can create editable financial models with changeable variables—when users modify inputs like annual kilometers, the spreadsheet automatically recalculates comparisons, transforming static analyses into personalized decision tools
- A notebook can be built by combining Gemini's synthesis of creator philosophy with actual source material from recent YouTube videos, enabling pattern detection across a creator's content to extract repeatable principles
- The speaker argues NotebookLM should not function as a general chatbot but specifically as a context-bounded tool that eliminates slow initial work and produces polished first versions requiring verification, particularly for calculations, health claims, and financial decisions
Topics
Transcript
[0:00] Notebook LM has long been one of Google's most useful tools, but in recent weeks it has received several features that significantly change how it is used. We're no longer just talking about uploading a PDF, asking questions, and requesting a summary. We already knew that. Now we're talking about taking your sources, your videos, your documents, your data, or even a person's channel and starting to build much more interesting things. For example, you can generate vertical videos from your own sources. You can request files directly from the chat, you can [0:31] use it to analyze real data, and you can turn the content of a creator, a company, or an expert into a kind of private…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Migue Baena IA
🚨 6 skills de Claude que necesitas probar
The speaker identifies six essential Claude skills developed after testing over 100 options, focusing on workflow automation, planning, task management, code review, context preservation, and cross-session memory. These skills significantly improve project development speed, reduce errors, and eliminate repetitive work.
Aprende el 99% de Claude Code en menos de 25 minutos
This video tutorial explains how to use Claude Code, an AI agent that works within project folders to create, test, and iterate on projects directly from your computer. It covers the complete workflow from initial setup through publishing projects online, including how to use connectors, skills, GitHub, and Vercel.
El método MIT para aprender cualquier tema en 90 minutos con NotebookLM
An MIT student developed a method called "context accumulation" to learn complex topics in 90 minutes using NotebookLM by uploading multiple sources, asking strategic questions to identify core concepts, and generating difficult questions to test deep understanding rather than surface-level memorization.
¿Una app completa sin saber programar? Mira esto 👀
Repll agent is an AI tool that enables non-programmers to create complete applications by describing their ideas in natural language. Unlike single-assistant AI tools, it uses multiple AI agents working in parallel—one coding, one testing, one designing, and one handling deployment—to transform concepts into functional products faster.
Estás usando Claude Code mal: así lo usan los ingenieros de Anthropic
This video explains how Anthropic's own engineers use Claude Code through a skills-based system rather than isolated prompts. The core idea is to build reusable, modular skill folders that package instructions, examples, and scripts for repeated tasks. Four principles guide this approach: create skills for repeated tasks, save complete processes not just instructions, keep skills small and specific, and continuously improve skills based on corrections.