Xavier Mitjana

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 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.

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.

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.

Google's new Gemini 2.5 Flash TTS model offers advanced voice generation with detailed emotional direction, surpassing tools like ElevenLabs — and it's free. The presenter demonstrates how to use it via Google AI Studio and even build a custom voice app on top of it. He closes with a broader warning about AI models absorbing specialized software markets and concentrating power in a few large companies.

Google's new Gemini 3.1 Flash Live model introduces real-time multimodal AI that can see your screen and provide voice guidance, potentially replacing YouTube tutorials. The presenter demonstrates using it as a personal tutor for software like Premiere Pro and as a voice assistant for websites.

The speaker demonstrates how connecting NotebookLM with Gemini through GEMs creates a powerful workflow for document generation, allowing users to transform research into editable documents. This method combines NotebookLM's contextual understanding with Gemini's Canvas editing capabilities.

Minimax engineers developed M2.7, an AI model that can self-improve by analyzing its own code, tests, and performance metrics. The model autonomously improved its performance by 30% over 100 iterations and won 9 gold medals in machine learning competitions while costing 20 times less than competitors like Claude Opus.

The video analyzes how artificial intelligence has exposed fundamental flaws in the education system, contrasting two students - one celebrated for using ChatGPT throughout university and another expelled for similar behavior. The speaker argues AI hasn't broken education but rather accelerated the collapse of an already obsolete 300-year-old industrial model.

A video explains how an MIT student mastered coursework in 48 hours versus classmates' 5 months using three strategic questions with NotebookLM, an AI tool that analyzes multiple sources simultaneously. The presenter demonstrates this method using personal finance as an example, uploading 47 sources and applying the student's technique.