浏览器制造商 Opera 推出了一项新的网络标准，让用户能够直接在其浏览器中运行 AI 模型，而无需依赖云端。
Browser maker Opera has introduced a new web standard that lets users to run AI models directly in its browser, without relying on the cloud.
这项名为 WebAI 的新标准旨在与多种 AI 模型配合使用。Opera 以 Google 的 Gemma 为例 —— 这是 Google 两年前首次推出的一种开放权重模型。Opera 表示，在 Mac 电脑上，WebAI 还支持 Apple 的设备端基础模型。
The new standard, WebAI, is designed to work with a variety of AI models. Opera name drops Google’s Gemma — an open-weight model that Google first introduced two years ago — as one example. On Macs, WebAI also supports Apple’s on-device foundation model, the company says.
但 Opera 称，WebAI 不绑定任何特定模型，而是构建为支持广泛的开放权重 AI 系统。WebAI 源于 Opera 此前将本地运行模型引入其浏览器的工作。
But Opera says WebAI isn’t tied to any particular model and is built to support a wide range of open-weight AI systems. WebAI grew out of previous work by Opera to bring locally run models into its browsers.
Opera 正在其旗舰浏览器 Opera One 中以早期预览形式提供这些新 AI 功能。公司表示，其面向游戏玩家和主播的浏览器 Opera GX，以及使用 AI 代理执行任务的浏览器 Opera Neon，很快也将获得同样的功能。据公司称，用户必须主动选择加入该功能。
Opera is making the new AI features available as an early preview in its flagship Opera One browser. The company says Opera GX, its browser built for gamers and streamers, and Opera Neon, its browser that uses AI agents to perform tasks, will soon get the same treatment. Users have to choose to opt into the feature, according to the company.
开放权重模型为用户提供了多项优势。首先，它们通常可以免费下载和使用。其底层模型权重也公开可用，这让开发者拥有更大的自由度来定制其工作方式。尽管与完全开源软件不同，开放权重模型仍附带一些限制。
Open-weight models offer a number of benefits to users. For one, they are typically free to download and use. Their underlying model weights are also publicly available, which gives developers more freedom to customize how they work. Although unlike fully open-source software, open-weight models still come with some restrictions.
公司表示，还有隐私方面的额外优势。用户无需将个人信息发送到公司服务器，也无需为基于云端的 AI 订阅付费，即可使用 AI 功能。
There’s the additional advantage of privacy, the company said. Users can tap into AI features without having to send their personal information to a company’s servers or pay for a cloud-based AI subscription.
公司在其公告中表示：“开发者无需运行 AI 基础设施，也无需为每次请求付费即可添加 AI 功能。用户不需要 AI 订阅，本地 AI 处理的信息留在其自己的设备上，并且他们始终掌控着自己电脑上的 AI。” 公司称，WebAI 还允许任何人直接在浏览器中生成文本、对内容进行分类，以及理解信息片段之间的关联。
“Developers can add AI features without running AI infrastructure or paying for every request,” the company said in its announcement. “Users don’t need AI subscriptions, the information the local AI handles stays on their own device, and they stay in control of the AI on their computer.”The company said WebAI also allows anyone to generate text, classify content, and understand how pieces of information relate, all directly in the browser.
随着 AI 助手变得更强大并能获取个人信息，隐私已成为日益令人担忧的问题。用户往往向 AI 聊天机器人提供大量个人信息，有时并不清楚这些数据将如何存储或使用。
Privacy has become a growing concern as AI assistants become more powerful and gain access to personal information. Users often surrender vast amounts of personal information with AI chatbots, sometimes without a clear understanding of how that data is stored or used.
本地运行的模型提供了一种替代方案，因为处理过程发生在用户自己的设备上，而非公司的云端服务器。这并不能消除所有隐私风险，但确实让用户拥有更多控制权。因此，Opera 多年来将数字隐私作为其主要卖点之一，这合情合理。
Locally run models offer an alternative because the processing happens on the user’s own device — and not on a company’s cloud server. That doesn’t eliminate every privacy risk, but it does give users a bit more control. It makes sense then that Opera has made digital privacy one of its primary selling points over the years.
不过，也存在权衡。在本地运行 AI 模型会对用户的电脑提出更高要求，可能影响性能。Opera 指出，模型性能将取决于设备的硬件配置。
There are trade-offs, however. Running AI models locally puts more demand on a user’s computer, which can affect performance. Opera notes that model performance will depend on the device’s hardware.