Hi Alex! Yes, here is some positive quantitative feedback <https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-02-26-cg-minutes.md#:~:text=Kenji:%20I%20can,what%20we%20can>we've gathered via surveys as of February 2025 (similar to Translator API). We've also publicly shared a more recent snapshot of feedback at BlinkOn: bit.ly/blinkon-2025-builtin-ai (slide 34). Origin Trial signups have been 5x higher than what we see from typical Origin Trials which suggest a lot of interest. We also have third-party partners excited to launch with this API.
Best, Ayu On Wednesday, April 16, 2025 at 8:08:03 AM UTC-7 Alex Russell wrote: > hey Ayu, > > Thanks for including the changes since the original intent. Great to see > things evolve while in OT. > > Has there been feedback on this so far? Anything y'all can share? > > Best, > > Alex > > On Tuesday, April 15, 2025 at 10:31:03 AM UTC-7 Ayu Ishii wrote: > >> Contact emails >> >> dome...@chromium.org, fer...@chromium.org, kenjibah...@chromium.org, >> m...@chromium.org, btri...@chromium.org, ds...@chromium.org, >> a...@chromium.org >> >> Explainer >> >> >> https://github.com/explainers-by-googlers/writing-assistance-apis/blob/main/README.md >> >> Specification >> >> >> https://webmachinelearning.github.io/writing-assistance-apis/#summarizer-api >> >> >> Summary >> >> A JavaScript API for producing summaries of input text, backed by an AI >> language model. >> >> >> Blink component >> >> Blink>AI>Summarization >> <https://issues.chromium.org/issues?q=customfield1222907:%22Blink%3EAI%3ESummarization%22> >> >> TAG review >> >> https://github.com/w3ctag/design-reviews/issues/991 >> >> TAG review status >> >> Pending >> >> Origin Trial Name >> >> Summarization API >> >> Chromium Trial Name >> >> AISummarizationAPI >> >> Origin Trial documentation link >> >> https://developer.chrome.com/docs/ai/summarizer-api >> >> WebFeature UseCounter name >> >> kSummarizer_Summarize >> >> Risks >> >> Interoperability and Compatibility >> >> This feature has definite interoperability and compatibility risks, due >> to the likelihood that different implementations will use different >> language models, prompts, and fine-tunings, and even within a single >> implementation such as Chrome, these pieces will likely change over time. >> Additionally, not all browsers and operating systems will have a built-in >> language model to expose, and not all devices will be powerful enough to >> run one effectively. >> >> We are taking a variety of steps to attempt to mitigate these risks. For >> example, the specification is designed to allow the API to be backed by a >> cloud-based language model. This approach could extend the functionality to >> a wider range of devices and users. The API is designed to abstract away >> the specifics of the underlying language model, including prompts and >> fine-tuning. This prevents developers from relying on specific outputs, >> ensuring they receive a generalized summary rather than structured data >> that might vary across implementations. Finally, the API surface is >> designed with many clear points of failure, that encourage the developer to >> probe for capabilities ahead of time and fall back to other techniques if a >> capability is not available. >> >> Nevertheless, interoperability and compatibility risk remains high for >> these sorts of APIs, and we'll be closely monitoring it during the >> experimentation period. >> >> >> Gecko: Defer (https://github.com/mozilla/standards-positions/issues/1067) >> >> WebKit: No signal ( >> https://github.com/WebKit/standards-positions/issues/393) >> >> Web developers: Mixed signals ( >> https://github.com/WICG/proposals/issues/163) Prototyping with partners >> behind a flag revealed enthusiasm and many prototypes built, from which we >> drew the discussion of potential use cases [1]. Feedback on the WICG thread >> was more mixed. Some themes we saw include: asking for more capabilities >> (e.g. full prompting of a language model instead of higher-level APIs (our >> response at [2]); multi-modal support); desire to make sure the API >> actually works robustly in many real-world use cases; removal of any >> safety/ethical safeguards; and confusion about client-side vs. cloud APIs. >> [1]: >> https://github.com/WICG/writing-assistance-apis/blob/main/README.md#summarizer-api >> >> [2]: >> https://github.com/WICG/writing-assistance-apis/blob/main/README.md#directly-exposing-a-prompt-api >> >> Other signals: >> >> Activation >> >> This feature would definitely benefit from having polyfills, backed by >> any of: cloud services, lazily-loaded client-side models using WebGPU, or >> the web developer's own server. We anticipate seeing an ecosystem of such >> polyfills grow as more developers experiment with this API. >> >> >> WebView application risks >> >> Does this intent deprecate or change behavior of existing APIs, such that >> it has potentially high risk for Android WebView-based applications? >> >> None >> >> >> Goals for experimentation >> We're most interested in feedback on whether the summarization quality we >> can provide is useful to sites, and whether the options we've defined for >> controlling the summarization are useful. Additionally, we want to learn >> about the impact of the current API's limitations, e.g. maximum input >> length, to determine where we should spend our best effort lifting those >> limits. >> The origin trial will be limited to English-language input to start. We >> are hoping to add support for more languages over time. Learning how much >> of a limitation this is, and which languages ought to be prioritized, will >> also be helpful. >> Finally, we're also interested in feedback about the API shape and ease >> of use. >> >> Reason this experiment is being extended >> >> Since the start of Origin Trial we've incorporated developer feedback and >> have iterated on API shape, making several breaking changes. We would like >> to continue experimenting and collect feedback on the new shape before >> launch. >> >> Progress since the original intent includes: >> >> - >> >> Spec: Spec >> >> <https://webmachinelearning.github.io/writing-assistance-apis/#summarizer-api> >> >> is now complete >> - >> >> TAG review: Still pending >> <https://github.com/w3ctag/design-reviews/issues/991> >> - >> >> Signals requests: Firefox has updated to defer >> <https://github.com/mozilla/standards-positions/issues/1067> >> - >> >> Outreach for feedback from spec community: This API has been >> discussed at Web ML Community Group meetings. >> - >> >> WPT tests: We’ve added some basic WPT tests >> >> <https://source.chromium.org/chromium/chromium/src/+/main:third_party/blink/web_tests/external/wpt/ai/summarizer/> >> >> API interface updates made since original intent: >> >> - >> >> Removed the “ai” namespace >> <https://github.com/webmachinelearning/writing-assistance-apis/issues/9> >> - >> >> Updating model availability values >> <https://github.com/webmachinelearning/writing-assistance-apis/issues/29> >> - >> >> Updating interface for availability testing and expected language >> options >> <https://github.com/webmachinelearning/writing-assistance-apis/pull/22> >> - >> >> Adding permissions policies & removing worker support >> <https://github.com/webmachinelearning/writing-assistance-apis/pull/46> >> - >> >> Updating values for model download progress >> <https://github.com/webmachinelearning/writing-assistance-apis/pull/30> >> >> >> Ongoing technical constraints >> >> None. >> >> >> Debuggability >> >> It is possible that giving DevTools more insight into the >> nondeterministic states of the model, e.g. random seeds, could help with >> debugging. See related discussion at >> https://github.com/explainers-by-googlers/prompt-api/issues/9. >> >> >> Will this feature be supported on all six Blink platforms (Windows, Mac, >> Linux, ChromeOS, Android, and Android WebView)? >> >> No >> >> Not all platforms will come with a language model. In particular, in the >> initial stages we are focusing on Windows, Mac, and Linux. >> >> >> Is this feature fully tested by web-platform-tests >> <https://chromium.googlesource.com/chromium/src/+/main/docs/testing/web_platform_tests.md> >> ? >> >> No >> >> We have added some web platform test coverage for this feature ( >> https://wpt.fyi/results/ai/summarizer?label=experimental&label=master&aligned), >> >> and plan to expand coverage of the API surface over the course of the >> Origin Trial. How much we are able to test beyond the surface API is >> unclear, given the nondeterministic nature of the output. The explainer >> discusses this in >> https://github.com/WICG/writing-assistance-apis/blob/main/README.md#specifications-and-tests >> . >> >> >> Flag name on about://flags >> >> summarization-api-for-gemini-nano >> >> Finch feature name >> >> EnableAISummarizationAPI >> >> Requires code in //chrome? >> >> True >> >> Tracking bug >> >> https://issues.chromium.org/issues/351744634 >> >> Estimated milestones >> >> Origin trial desktop first >> >> 131 >> >> Origin trial desktop last >> >> 136 >> >> Origin trial extension 1 end milestone >> >> 139 >> >> DevTrial on desktop >> >> 129 >> >> >> Link to entry on the Chrome Platform Status >> >> https://chromestatus.com/feature/5193953788559360 >> >> Links to previous Intent discussions >> >> Intent to Prototype: >> https://groups.google.com/a/chromium.org/d/msgid/blink-dev/CAM0wra8iMt24s_jP9Ng9_RKU3cH4wFywAt00kitJCeMJ3CaUAw%40mail.gmail.com >> >> Intent to Experiment: >> https://groups.google.com/a/chromium.org/d/msgid/blink-dev/CAM0wra8d6bZo%2B9-8Rum0N%3D4oFpwVfquqAzRC7mu1GTyVeDWw5A%40mail.gmail.com >> >> -- 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 blink-dev+unsubscr...@chromium.org. To view this discussion visit https://groups.google.com/a/chromium.org/d/msgid/blink-dev/b88218e2-f260-4eaa-9bb2-c394dcf26f76n%40chromium.org.
