Gemini 3.5 and Antigravity come to Google NotebookLM
Gemini 3.5 and Antigravity come to Google NotebookLM
Gemini 3.5 与 Antigravity 登陆 Google NotebookLM
Google’s NotebookLM was one of the company’s first forays into generative AI technology, and in un-Googley fashion, it hasn’t been shut down yet. In fact, NotebookLM is getting one of its biggest updates, ever, today, moving to the latest Gemini 3.5 model, support for more file types, and streamlined web source integration. Google also says NotebookLM will be able to do more with all those queries thanks to embedded support for Antigravity.
Google 的 NotebookLM 是该公司在生成式 AI 技术领域的首次尝试之一，而且不同于 Google 一贯的作风，它至今尚未被砍掉。事实上，NotebookLM 今天迎来了史上最大规模的更新之一：升级至最新的 Gemini 3.5 模型，支持更多文件类型，并简化了网页来源的整合。Google 还表示，得益于对 Antigravity 的内置支持，NotebookLM 将能够处理更多复杂的查询任务。
Gemini 3.5 Flash debuted at Google I/O this year, promising much faster and more efficient processing. Google has claimed that companies worried about token costs can save big by moving their projects to the new Flash model while also getting outputs that are of similar or better quality. Those improvements are now filtering down to other Google products.
Gemini 3.5 Flash 在今年的 Google I/O 大会上首次亮相，承诺提供更快、更高效的处理能力。Google 声称，担心 Token 成本的企业可以通过将项目迁移到新的 Flash 模型来节省大量开支，同时获得质量相当甚至更好的输出结果。这些改进目前正逐步下放到 Google 的其他产品中。
NotebookLM, which launched in 2023 at the very beginning of the AI boom, lets you analyze specific sources like documents and webpages with Google’s latest AI models. The upgraded NotebookLM beats the old version in all of Google’s “core evaluation dimensions.”
NotebookLM 于 2023 年 AI 热潮初期推出，允许用户利用 Google 最新的 AI 模型分析文档和网页等特定来源。升级后的 NotebookLM 在 Google 的所有“核心评估维度”上均超越了旧版本。
Google conducted side-by-side evaluations of NotebookLM on the old Gemini 3.1 branch and with the updated 3.5. The company is being somewhat vague about the nature of the tests, breaking things up into “top five core evaluation dimensions,” which are Accuracy and Quality, Multilingual Support, Large Document Analysis, Document Creation, and Advanced Research. In these tests, Google says NotebookLM averaged a 65 percent win rate versus the older model.
Google 对运行在旧版 Gemini 3.1 分支和更新版 3.5 上的 NotebookLM 进行了对比评估。该公司对测试的具体性质表述较为模糊，将其划分为“五大核心评估维度”，即准确性与质量、多语言支持、大型文档分析、文档创建以及高级研究。在这些测试中，Google 表示 NotebookLM 相比旧模型平均胜出率为 65%。
NotebookLM also now has its own “cloud computer,” which allows NotebookLM to use Antigravity to write and run code in service of your research goals. Google says NotebookLM will come with a set of more than 100 software skills that can help you build workflows with your notebooks that previously would have required you to jump between apps.
NotebookLM 现在还拥有了自己的“云端计算机”，允许它利用 Antigravity 编写并运行代码，以服务于你的研究目标。Google 表示，NotebookLM 将配备 100 多种软件技能，帮助你在笔记本中构建工作流，而这些工作流以往需要你在多个应用程序之间来回切换才能完成。
This update will also expand NotebookLM beyond text outputs. The research bot will now be able to generate documents for you across a variety of formats. Documents are added to the Studio Panel, where infographics, quizzes, audio overviews, and other specialized outputs go. You can even prompt NotebookLM to make edits to these files after they’ve been created.
此次更新还将使 NotebookLM 的输出不再局限于文本。该研究机器人现在能够为你生成多种格式的文档。文档会被添加到 Studio 面板中，信息图表、测验、音频概览以及其他专业输出内容也会存放在这里。你甚至可以在文件创建后，通过提示词要求 NotebookLM 对其进行编辑。
Google plans to add more file types over time, but it’s starting with the following: Data visualizations and charts (png, svg), Documents (PDFs, docx, markdown, text files), Images with Nano Banana (png, jpg, gif), Structured data (csv, json), Microsoft Excel (xlsx), Microsoft PowerPoint (pptx).
Google 计划在未来增加更多文件类型，目前首批支持的格式包括：数据可视化与图表（png, svg）、文档（PDF, docx, markdown, 文本文件）、基于 Nano Banana 的图像（png, jpg, gif）、结构化数据（csv, json）、Microsoft Excel (xlsx) 以及 Microsoft PowerPoint (pptx)。
NotebookLM’s reliance on your sources is what has made it distinct from other implementations of Google’s AI tools, but this update can find some of those sources for you. If you need more context in a notebook, Google has expanded the app’s ability to import webpages. Right from the chat interface, you can ask Gemini to find sources fitting your needs, and it presents a “research report” with the option to import all or some of those as sources. All future interactions with the Notebook will use those sources in addition to the ones you’ve provided manually.
NotebookLM 对用户提供来源的依赖性使其区别于 Google 其他 AI 工具，但此次更新能够为你主动寻找部分来源。如果你在笔记本中需要更多背景信息，Google 扩展了该应用导入网页的能力。你可以直接在聊天界面要求 Gemini 寻找符合你需求的来源，它会呈现一份“研究报告”，并提供将全部或部分内容导入为来源的选项。未来与该笔记本的所有交互，都将在你手动提供的来源基础上，使用这些新导入的来源。
These features are starting to roll out today, but most NotebookLM users won’t see any changes just yet. Gemini 3.5 and the other improvements are coming first to AI Ultra subscribers, as well as Workspace business customers with AI Ultra Access and AI Expanded Access. Other Google accounts will see the updates in the near future.
这些功能从今天开始逐步推出，但大多数 NotebookLM 用户暂时还不会看到变化。Gemini 3.5 及其他改进将首先提供给 AI Ultra 订阅用户，以及拥有 AI Ultra Access 和 AI Expanded Access 权限的 Workspace 企业客户。其他 Google 账户将在不久的将来获得这些更新。