NEW NotebookLM Updates are INSANE!
Google has released a major update to NotebookLM, transforming it from a basic AI research tool into a full interactive learning system. Key new features include enhanced flashcards with progress tracking, shuffle, retry weak areas, and bulk email sharing for notebooks. The presenter argues this represents a fundamental shift in how people can learn from their own documents.
Summary
The video covers a significant update to Google's NotebookLM, which the presenter frames as transforming the tool from a simple AI document assistant into a comprehensive AI-powered learning platform. The host begins by highlighting that the update has gone largely unnoticed despite its significance.
The centerpiece of the update is an overhauled flashcard and quiz system. Previously, the flashcard feature was described as basic and passive — users could create cards but had no way to track progress or focus on weak areas. The new system introduces persistent progress saving, so users can resume study sessions exactly where they left off. Cards can be marked as 'got it' or 'missed it,' allowing the AI to build a picture of what the user knows and doesn't know. Additional features include deck shuffling (to prevent order-based memorization), the ability to delete irrelevant cards, and a 'retry weak areas' mode that isolates only the questions a user got wrong for repeated practice. The presenter compares this system to Duolingo but applied to a user's own uploaded documents.
The second major update covered is bulk sharing, which allows users to paste an entire list of email addresses at once to share a notebook, replacing the previous one-by-one email entry process. The presenter emphasizes that this is particularly impactful for teachers, team leads, and creators managing large groups.
The host then walks through a practical five-step workflow: upload a document, generate flashcards automatically, go through the deck marking responses, review weak spots on a personalized knowledge map, and share the notebook with a group via bulk email.
The presenter positions NotebookLM's evolution as a broader signal about the future of AI-assisted education, predicting that within five years, personalized AI tutoring from your own content will replace traditional passive learning methods like rereading textbooks. The video concludes with usage tips — including always using shuffle, prioritizing the retry weak areas feature, studying in groups, and avoiding uploading too many documents at once — before promoting the presenter's paid AI community and a free AI Success Lab.
Key Insights
- The presenter argues that the new 'retry weak areas' feature is the most important addition because it isolates only missed questions for repeated practice — mimicking how memory actually consolidates — rather than forcing users to redo entire decks.
- The presenter claims NotebookLM has fundamentally changed in category, describing it as no longer an AI research helper but a full learning system — comparing it to a combination of ChatGPT, Notion, Quizlet, and a podcast app.
- The presenter states that the shuffle feature, while appearing minor, is critical because without it users memorize the order of cards rather than the actual content, undermining genuine learning.
- The presenter warns against uploading too many documents at once, claiming the AI gets confused with 50 documents and recommending users start with one or two sources to maintain quality output.
- The presenter predicts that within five years, AI-adaptive learning from personal content will replace traditional education methods like sitting through lectures or rereading pages, and says NotebookLM is one of the first tools executing this vision effectively.
Topics
Transcript
[0:00] New Notebook LM updates are insane. Google just turned Notebook LM into a full-on AI learning machine, and almost no one is talking about it. This thing can now read your notes, quiz you, track what you get wrong, and teach you like a real tutor. It's wild. It's brand new, and it's going to change how you study, work, and learn forever. Let me show you. Okay, so here's the deal. Notebook LM just got a massive update. And when I say massive, I mean this is the kind of update that makes you stop what you're doing and pay attention, because Google quietly dropped some new features that turned Notebook LM from a cool AI tool into…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Julian Goldie SEO
NEW Nvidia Autonomous AI is WILD!! 🤯
Nvidia announced Nemo Clo, a new autonomous AI agent system that operates independently without continuous prompting. Powered by Nemotron 3 Ultra (a 550 billion parameter model), the system is five times faster and cheaper than previous versions, with OpenShell providing secure sandboxed execution.
Laguna XS 2.1: New FREE + Opensource Local AI!
Julian reviews Laguna XS 2.1, a new free open-source local AI coding model from Poolside that performs comparably to Qwen 3.6 and outperforms Claude Haiku on benchmarks. He demonstrates its practical capabilities by building landing pages and functional apps, highlighting its speed, offline functionality, and multiple deployment options through local setup, Claude Code, or OpenRouter's free API.
How to Run Hermes FREE Forever!
The video demonstrates how to run the Hermes AI agent for free using Gemma 4, a local open-source model from Google, with significant speed improvements through MLX optimization. The setup works on Apple Silicon Macs or via free APIs on Open Router, enabling autonomous agents to work offline and privately without subscription costs.
This NEW Chinese AI is INSANE! (FREE + Open Source!)
Long Cap 2.0 is a new open-source Chinese AI model from a food delivery app company that offers 1 million tokens of free context memory, beats GPT-4.5 on SWE bench pro benchmarks, and uses efficient parameter activation to reduce computational overhead while maintaining high performance.
Claude Code is now FREE: Here’s how…
Google's new Gemma 4 model running on Ollama is 90% faster on Apple Silicon, enabling free Claude Code usage locally without token costs. The setup requires three simple steps: downloading Ollama, Gemma 4, and installing into Claude Code, with alternatives available via OpenRouter API for non-Mac users.