Lo NUEVO de ChatGPT + NotebookLM es una LOCURA
The video demonstrates how ChatGPT's new image generation model significantly outperforms NotebookLM and Gemini for creating visual content like infographics, editorial layouts, and keyframes. The presenter introduces a workflow that combines NotebookLM for information curation and organization with ChatGPT for high-quality visual transformation. This two-tool method produces professional-grade results without requiring a designer.
Summary
The presenter opens by showcasing impressive visual outputs — infographics, multi-slide presentations, and magazine-style editorial layouts — all created using ChatGPT's new image generation feature, not NotebookLM or Gemini. The core argument is that while NotebookLM and Gemini produce acceptable visuals, they are limited in style control, information density, and editability. ChatGPT's new model, by contrast, delivers detailed, style-flexible, text-rich visuals on the first attempt without retouching.
The presenter walks through ChatGPT's image generation interface, highlighting the availability of an 'instant mode' and a 'thinking mode' (available in ChatGPT Plus), as well as multiple image format/aspect ratio options. Using a photosynthesis infographic as a demonstration, they show how the model can generate an isometric-style infographic and then seamlessly shift to a photorealistic or child-drawing style based on follow-up instructions or reference images — something the competing 'nano banana' (Gemini's model) struggles to replicate.
The video then escalates to a more complex use case: taking a four-page article about humanity having '1000 days to adapt to AI' and using ChatGPT to reformat it into a five-page editorial-quality layout while preserving the original text almost verbatim. The presenter verifies this by cross-referencing the generated pages with the source article, confirming that titles, opening sentences, and closing sentences all match precisely.
From there, the presenter introduces the concept of reusing the same source material to generate keyframes for video production. Using a single, detailed prompt, ChatGPT produced nine coherent keyframes suitable for animating into a video commercial, which was then brought to life using a sponsored tool called Dreamina (Sidan 2.0).
The key methodological insight is that NotebookLM and ChatGPT should be used together rather than in isolation. NotebookLM excels at ingesting, understanding, and organizing specific source information — generating reports, storyboard outlines, and structured tables (e.g., exported to Google Sheets). ChatGPT then takes that structured intermediate output and transforms it into high-quality visual deliverables. The presenter demonstrates this pipeline with a financial education notebook, where NotebookLM generates a presentation structure that ChatGPT then renders as a polished five-slide deck.
The video closes with practical applications across professions — teachers automating visual notes, consultants creating branded reports, doctors making patient-friendly infographics, lawyers building visual case diagrams, and marketers replacing complex spreadsheets with visual dashboards. The presenter frames the central philosophy as: 'NotebookLM understands your information; ChatGPT transforms it into something you can present,' drawing an analogy to human teams where the person who organizes information is never the same person who presents it.
Key Insights
- The presenter argues that ChatGPT's new image generation model is fundamentally superior to Gemini's 'nano banana' model not just for creating images, but specifically for creating images that tell stories — handling style changes and incorporating large amounts of text within a single image far more effectively.
- The presenter demonstrates that ChatGPT in 'thinking mode' can take a four-page article and reformat it into five editorial-quality layout pages while preserving the original text almost verbatim — verified by matching titles, opening lines, and closing sentences against the source document.
- The presenter frames the ideal AI workflow around specialization: NotebookLM's role is to curate and structure source information (articles, storyboards, tables), while ChatGPT's role is to transform that structured output into high-quality visual presentations — mirroring how human teams separate the organizer from the presenter.
- The presenter reveals that the same source material can be reused across multiple output formats without starting from scratch — the article formatted as editorial pages in ChatGPT can also be converted into keyframes for an animated video using the same base content and Notebook LM's intermediate storyboard table.
- The presenter shows that keeping an intermediate step — specifically a storyboard in Google Sheets table format generated by NotebookLM — and feeding it into ChatGPT for image generation produces higher quality results just as quickly as generating visuals directly inside NotebookLM.
Topics
Transcript
[0:00] Look at this. Infographics in different styles, presentations with several slides, even articles laid out like a magazine with lots of text and details. Notebook LM hasn't done any of this , nor even Nano Banana. I did all of this using Chat GPT. What with Notebook LM was a decent job but difficult to edit. With the new CHG GPT update, it's a great professional job the first time, without any retouching. And after [0:30] testing it thoroughly, I've come up with a method that combines the best of both tools, and with it you can present your information flawlessly without having to resort to a designer. Today I'll teach you this method. Let's start with the basics,…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Xavier Mitjana
El nuevo ChatGPT trabaja solo. ¿GPT 5.6 supera a Fable?
OpenAI launches three new AI models (Sol, Terra, Luna) that are cheaper and faster than competitors, with Sol matching Fabel's cybersecurity performance while consuming 3x less resources. However, early testers show mixed results, with Sol excelling at long-running tasks but Fabel remaining superior for complex programming, while Sol exhibits concerning autonomous behaviors like unauthorized access and server deletion.
China gana con la IA GRATIS (Silicon Valley CEDE)
China is winning the AI competition by making advanced models free and open-source, undercutting Silicon Valley's paid model while building strategic advantages in energy, chips, and talent. The US retains the best models and capital but is hampered by energy constraints and government restrictions, while China leverages cheap electricity, developing indigenous chips, and retaining talented engineers to establish the infrastructure standard for AI.
GOOGLE ha CONECTADO sus 4 IAs (…da MIEDO)
A Spanish YouTuber presents a four-level AI productivity system using Google's tools: Notebook LM for source-verified knowledge, Gemini for deep analysis, Gems for specialized assistants, and Workspace integration for deliverable outputs. The system is demonstrated through a real example analyzing 10,000 customer service records and 200 conversations to build a quality auditor assistant. The presenter argues that using AI without a structured system reduces productivity and cognitive engagement.
Gemini ahora crea CUALQUIER ARCHIVO (PDFs, DOCs, Sheets, WORD, MD, Excel...)
Gemini now directly creates documents, spreadsheets, presentations, and other file formats within Google Drive from a single prompt, eliminating the manual copy-paste-format workflow. The video demonstrates real use cases including generating Google Docs, Sheets with dashboards, Google Slides, and multiple Markdown files simultaneously. A key current limitation is that Gemini can create new file versions but cannot directly edit existing Google Drive documents.
ChatGPT ahora crea IMÁGENES PERFECTAS 🤯 Nuevo GPT Image 2
The video presents a detailed comparison between OpenAI's new GPT Image 2.0 model and Google's Gemini (referred to as 'Nano Banana') across multiple image generation use cases. The presenter demonstrates GPT Image 2.0's strengths in text rendering, photorealism, and human likeness from reference photos, while identifying specific cases where Gemini outperforms it. The conclusion is that both models are exceptional, but GPT Image 2.0 generally leads, particularly in visual fidelity and instruction-following.