Introduction to WebAI
Browser maker Opera has introduced a new web standard that lets users run AI models directly in its browser, without relying on the cloud.
The new standard, WebAI, is designed to work with a variety of AI models. Opera highlights Google’s Gemma as one example, while noting that WebAI also supports Apple’s on-device foundation model on Macs.
Opera states that WebAI is not tied to any specific model and is built to support a wide range of open-weight artificial intelligence systems, growing out of previous efforts to bring locally run models into its browsers.
Availability in Browsers
The company is making the new features available as an early preview in its flagship Opera One browser, with plans to bring the capability to Opera GX and Opera Neon. Users must explicitly choose to opt into the feature.
Open-weight models provide several benefits, including free availability and public model weights that allow developers greater customization freedom, though they still carry certain usage restrictions compared to fully open source software.
Privacy and Local Processing
Local execution offers privacy advantages by eliminating the need to transmit personal data to external corporate servers or pay for cloud-based subscriptions.
According to the company, developers can integrate artificial intelligence features without maintaining infrastructure or paying per request, keeping user information and control on the local device.
The standard enables tasks such as text generation, content classification, and relational information understanding to be performed directly within the browser.
Trade-offs and Hardware Demands
As artificial intelligence assistants gain access to sensitive personal information, privacy concerns have escalated regarding how data is stored and utilized by cloud services.
Processing data locally on the user's device provides an alternative that increases user control, aligning with Opera's longstanding focus on digital privacy.
However, running models locally introduces performance trade-offs by increasing demands on computer hardware, meaning performance will depend heavily on the user's specific device capabilities.
