Previewed at I/O 2023 in May, Google today is rolling out its “AI-first notebook” with a new name: NotebookLM. It was previously called “Project Tailwind,” though the old icon remains in use.
LM is for “language model,” with the new name meant to emphasize how it’s “grounded in your own documents.” At the start, this applies to Google Docs, with additional formats coming soon.
You select/upload your cloud documents and can have NotebookLM do three things. The first capability automatically summarizes your notes and sources. You can then ask questions like:
- A medical student could upload a scientific article about neuroscience and tell NotebookLM to “create a glossary of key terms related to dopamine.”
- An author working on a biography could upload research notes and ask questions like: “Summarize all the times Houdini and Conan Doyle interacted.”
NotebookLM can also generate “creative new ideas”:
- A content creator could upload their ideas for new videos and ask: “Generate a script for a short video on this topic.”
- Or an entrepreneur raising money could upload their pitch and ask: “What questions would potential investors ask?”
NotebookLM is an “experimental product,” and Google says the “source-grounding” approach “does seem to reduce the risk of model “hallucinations.” However, it says you should still “fact-check the AI’s responses against your original source material.”
Build a product with our users: We’ll be talking to people and communities often to learn about what’s working well and where the gaps are, with the intent of making NotebookLM a truly useful product.
On the privacy front, “your files and dialogue with the AI are not visible to other users,” and Google says it is not using any collected data to train new AI models.
Starting today, Notebook LM will be available to a small group of US users. You can sign-up for the waitlist here.
FTC: We use income earning auto affiliate links. More.
Comments