Opera One 在 Mac 上支持直接调用 Apple 端侧基础模型
Opera One now lets Mac users run Apple’s foundation model directly in the browser
Opera One 浏览器推出预览功能，通过 WebAI 这一拟议网页标准让网站和扩展调用本地运行的 AI 模型，Mac 用户可直接使用 Apple 的端侧基础模型，也可选用 Google 的 Gemma。该功能为可选开启、无需订阅，用户可控制哪些网站能访问本地模型；Opera 同时发布了一批示例扩展，Opera GX 和 Opera Neon 后续跟进。Opera 还上线 HTML-in-Canvas，允许开发者把可交互网页嵌入 2D 和 3D 场景。
正文
Starting today, Opera One users can access a preview feature that lets them tap into local AI models through WebAI, a proposed web standard. Here are the details.
WebAI
Opera announced today that its Opera One browser is the first of its browsers to offer built-in access to local AI models, with Opera GX and Opera Neon to follow.
The feature relies on the WebAI proposed web standard, which allows websites and browser extensions to access AI models running locally on the user’s device.
Here’s Opera:
WebAI is a proposed web standard, backed by companies such as Google and Microsoft, that lets websites and browser extensions use AI hosted through the browser. Opera’s implementation is model-agnostic and built around open models, offering users choice among AI providers. At launch, users can already tap into models from Google and Apple, including Google’s Gemma and, on Macs, Apple’s on-device foundation model, directly in Opera.
The company notes that WebAI can be used to generate text, classify content, and identify relationships between pieces of information, and adds that the feature is opt-in, with no subscription needed, and with users able to control which websites can access local AI models.
Here’s Opera again on some of the potential uses for local AI in the browser:
With local AI built into the browser, both users and developers can benefit from new capabilities. Local AI lets anyone build on top of free, open-weight AI models. Developers can add AI features without running AI infrastructure or paying for every request. 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. For example, an extension could sort your tabs, flag clickbait or spot relevant job posts using a model on your laptop, with no account, no fee and no data sent to an AI service.
To help developers (and users) explore what’s possible with WebAI, Opera has released a collection of example extensions that you can find here.
HTML-in-Canvas
Additionally, Opera is launching HTML-in-Canvas today, which, as the company explains, “lets developers put real, interactive web pages inside 2D and 3D scenes.”
The feature allows developers to embed fully functional web pages into 2D and 3D environments, with interactive elements such as menus, buttons, and forms remaining usable even as they move around within a scene. Developers can build these experiences using familiar HTML and CSS.
“Honestly, this is a fun one […]. You can take a real web page and throw it into a 3D world, and everything still works: buttons, text, menus, all of it. We wanted users to get their hands on it early and see what they come up with.”
To demonstrate the possibilities, Opera has created two examples: Webpage Bulldozer, which turns elements of a web page into physical objects, and Gamer Room, a virtual 3D room featuring screens that display live web pages. Both demos work in Opera browsers without any additional setup, and you can check them out here.
Apple Watch Series 12 | Ultra 4
AirPods Pro 3 | AirPods 5
AirTag (2nd Generation) – 4 Pack
MacBook Neo
Logitech MX Master 4