Google's Chrome for Developers has demonstrated how the multimodal input capability of the browser's built-in on-device AI, the Prompt API, can analyze images locally to produce structured JSON containing alt text and captions. Because the processing runs entirely on the device with no server round-trip, developers can obtain the metadata needed for Markdown and <figure> tags with low latency while keeping data private.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.