Thanks Jeffrey! That makes sense. I have opened a focused TAG review for the samplingMode design here and updated ChromeStatus accordingly: https://github.com/w3ctag/design-reviews/issues/1308
Best, Isaac On Mon, Nov 9, 2026 at 10:42 AM Jeffrey Yasskin <[email protected]> wrote: > On Mon, Nov 9, 2026 at 10:24 AM Chromestatus < > [email protected]> wrote: > >> *TAG review* >> https://github.com/w3ctag/design-reviews/issues/1093 This update >> directly addresses the TAG’s Prompt API early design review feedback on >> “Interoperable model parameters”. We adopted TAG guidance by replacing raw >> hyperparameters with samplingMode presets, which enable user agents to map >> semantic developer intent to model-specific sampling configurations. >> Because this incremental refinement directly fulfills prior TAG advice >> rather than a new architectural surface, a separate review is not merited. >> > > Even though you're implementing a goal the TAG expressed, the TAG may > still have feedback on _how_ you're implementing it. I can't promise that > we'll give timely feedback, but I think it's still worth sending a review > for this. > > Thanks, > Jeffrey > -- You received this message because you are subscribed to the Google Groups "blink-dev" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion visit https://groups.google.com/a/chromium.org/d/msgid/blink-dev/CAFk4SLaZq%3DBQo-Ggx8YLu6VE7f6WPe_Fx6tB2xootsVDHjeV1A%40mail.gmail.com.
