- From: Reilly Grant <notifications@github.com>
- Date: Thu, 30 Oct 2025 15:56:38 -0700
- To: w3ctag/design-reviews <design-reviews@noreply.github.com>
- Cc: Subscribed <subscribed@noreply.github.com>
Received on Thursday, 30 October 2025 22:56:42 UTC
reillyeon left a comment (w3ctag/design-reviews#1093) From the [explainer](https://github.com/webmachinelearning/prompt-api/blob/main/README.md#goals): > We do not intend to force every browser to ship or expose a language model; in particular, not all devices will be capable of storing or running one. It would be conforming to implement this API by always signaling that no language model is available, or to implement this API entirely by using cloud services instead of on-device models. The implementations in Chrome and Edge today only use on-device models, but there's nothing in the API design that forces a compliant implementation to choose a particular approach. I'm interested in hearing the TAG's perspective on the trade-offs between always guaranteeing on-device execution and expanding reach to more devices by enabling a cloud-based solution. There's some discussion of this in https://github.com/webmachinelearning/writing-assistance-apis/issues/38. -- Reply to this email directly or view it on GitHub: https://github.com/w3ctag/design-reviews/issues/1093#issuecomment-3470598937 You are receiving this because you are subscribed to this thread. Message ID: <w3ctag/design-reviews/issues/1093/3470598937@github.com>
Received on Thursday, 30 October 2025 22:56:42 UTC