- Google upgraded NotebookLM to a one-million-token context window, allowing AI to analyze entire books or massive project archives in a single chat
- The update also quadruples NotebookLM’s memory storage and lays the groundwork for new memory features like a saved conversation history
- The improved NotebookLM’s flexibility means it can take on all kinds of personas and uses the new ‘Goals’ system, which lets users define the AI’s role
NotebookLM is no longer just for footnotes. Google’s ambitious research assistant has just reached beyond its academic roots and into more extensive conversational collaboration.
Google has announced a comprehensive set of upgrades designed to improve NotebookLM’s ability to mimic human understanding of circumstances and appropriate interactions.
The upgrades are made possible by a massive expansion of NotebookLM’s context window, essentially its short-term memory. NotebookLM now supports Gemini’s full context window of one million tokens across all plans.
Eight times what was previously available, it means AI can now hold entire books, long meeting transcripts and sprawling project files in its virtual mind for instant recall and analysis at once. It’s a big leap for users juggling large document collections who want more than surface-level answers.
You’re no longer stuck copying and pasting fragments of a PDF into a chat box. You can upload it all, along with any supporting documents, emails or notes you’d like to add, and NotebookLM will not only read it all, but refer to it across long, continuous conversations. It’s the difference between talking to a helpful stranger and working with someone who’s been in the project trenches with you since day one.
Improved responses
And the payoff is very real, according to Google. The company claims internal tests show a 50% improvement in user satisfaction for longer responses from multiple sources, thanks to this boost in attention span.
The memory improvement also applies to conversations with users. Where you might have noticed that NotebookLM lost its train of thought after you’ve sent just a few messages, it can now track context six times further into a dialog.
Your chat history will also be kept on top of, for lack of a better term, NotebookLM. This means you can start a session on Tuesday, close your laptop and pick up the same train of thought on Friday afternoon without going back. That memory also remains private. Shared notebooks don’t share chats unless you want them to.
Google goals
What ties all these upgrades together is the addition of ‘Targets’, essentially a way to set how the AI assistant approaches and interacts with you. You can request a virtual PhD thesis advisor to poke holes in your logic, or a sounding board for a new manuscript that answers each question with another question to encourage thinking. You can even ask it to take on a guiding role through fiction, act as game master for tabletop role-playing games, and ‘improvise’ a complex narrative.
NotebookLM is based on using AI not to search all the time, but to provide insight into the research you’ve already done. The platform does exactly that, which is useful as AI tools become more ubiquitous in the workplace (open or otherwise).
The flexibility of NotebookLM’s target and personality setting makes this even more obvious. You no longer adjust the tone on the fly. You set parameters for how this assistant should think. These changes push NotebookLM towards platforms like Notion AI. You could also see Google going for a personal agent that ChatGPT’s memory enables, or Perplexity’s multimodal capabilities that can absorb multiple documents at once. But NotebookLM stands out for how closely it melds these features into a single interface, something Google is often successful at doing.
There is also a distinctly Google-flavored logic at work. The integrations now span over a million apps and websites. The chat interface coordinates things across these apps. So while NotebookLM can’t quite emulate the semi-autonomous digital agents emerging from AI providers, the groundwork is being laid.
The new version of NotebookLM may be the kind of tool to attract those currently wary of AI but fearful of document analysis. Arguably, what most people want from AI is a tool whose function is shown through its form, not a black box you can’t understand. NotebookLM could fill that niche.
The upgrades make it easy for NotebookLM to serve more people. It can offer better study guides for students, better citation management and improved cross-referencing. NotebookLM learns how you work, remembers what you’re doing, and meets you halfway. And that’s a claim that’s much easier to believe than those about “transforming the way you work.”
Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews and opinions in your feeds. Be sure to click the Follow button!
And of course you can too follow TechRadar on TikTok for news, reviews, video unboxings, and get regular updates from us on WhatsApp also.
The best business laptops for all budgets
