#builtinai — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #builtinai, aggregated by home.social.
-
I stumbled across Arcrawls (https://arcrawls.com/), a cute browser pet that reacts to the content in your tabs and gains XP as you surf. It also has AI smarts, because obviously it does ✨🚀 :)
By using local Distilbert (via ONNX WASM) and the Prompt API, it side-steps 3 massive hurdles:
1. No cloud API bills to pay.
2. 100% privacy (no data leaves your machine).
3. No friction (users don't have to paste an API key).Check out the code: https://github.com/fujiDevv/context-aware-browser-pet
-
I stumbled across Arcrawls (https://arcrawls.com/), a cute browser pet that reacts to the content in your tabs and gains XP as you surf. It also has AI smarts, because obviously it does ✨🚀 :)
By using local Distilbert (via ONNX WASM) and the Prompt API, it side-steps 3 massive hurdles:
1. No cloud API bills to pay.
2. 100% privacy (no data leaves your machine).
3. No friction (users don't have to paste an API key).Check out the code: https://github.com/fujiDevv/context-aware-browser-pet
-
I stumbled across Arcrawls (https://arcrawls.com/), a cute browser pet that reacts to the content in your tabs and gains XP as you surf. It also has AI smarts, because obviously it does ✨🚀 :)
By using local Distilbert (via ONNX WASM) and the Prompt API, it side-steps 3 massive hurdles:
1. No cloud API bills to pay.
2. 100% privacy (no data leaves your machine).
3. No friction (users don't have to paste an API key).Check out the code: https://github.com/fujiDevv/context-aware-browser-pet
-
I stumbled across Arcrawls (https://arcrawls.com/), a cute browser pet that reacts to the content in your tabs and gains XP as you surf. It also has AI smarts, because obviously it does ✨🚀 :)
By using local Distilbert (via ONNX WASM) and the Prompt API, it side-steps 3 massive hurdles:
1. No cloud API bills to pay.
2. 100% privacy (no data leaves your machine).
3. No friction (users don't have to paste an API key).Check out the code: https://github.com/fujiDevv/context-aware-browser-pet
-
I stumbled across Arcrawls (https://arcrawls.com/), a cute browser pet that reacts to the content in your tabs and gains XP as you surf. It also has AI smarts, because obviously it does ✨🚀 :)
By using local Distilbert (via ONNX WASM) and the Prompt API, it side-steps 3 massive hurdles:
1. No cloud API bills to pay.
2. 100% privacy (no data leaves your machine).
3. No friction (users don't have to paste an API key).Check out the code: https://github.com/fujiDevv/context-aware-browser-pet
-
Per popular request, the LanguageDetector API will soon gain the ability to dissociate Simplified Chinese and Traditional Chinese.
https://groups.google.com/a/chromium.org/g/blink-dev/c/jzHYvmyjTYMDocumentation: https://developer.chrome.com/docs/ai/language-detection
-
Per popular request, the LanguageDetector API will soon gain the ability to dissociate Simplified Chinese and Traditional Chinese.
https://groups.google.com/a/chromium.org/g/blink-dev/c/jzHYvmyjTYMDocumentation: https://developer.chrome.com/docs/ai/language-detection
-
Per popular request, the LanguageDetector API will soon gain the ability to dissociate Simplified Chinese and Traditional Chinese.
https://groups.google.com/a/chromium.org/g/blink-dev/c/jzHYvmyjTYMDocumentation: https://developer.chrome.com/docs/ai/language-detection
-
Per popular request, the LanguageDetector API will soon gain the ability to dissociate Simplified Chinese and Traditional Chinese.
https://groups.google.com/a/chromium.org/g/blink-dev/c/jzHYvmyjTYMDocumentation: https://developer.chrome.com/docs/ai/language-detection
-
Per popular request, the LanguageDetector API will soon gain the ability to dissociate Simplified Chinese and Traditional Chinese.
https://groups.google.com/a/chromium.org/g/blink-dev/c/jzHYvmyjTYMDocumentation: https://developer.chrome.com/docs/ai/language-detection
-
That's a wrap on the International JavaScript Conference in San Diego! 🌴
A huge thank you to everyone who joined my sessions:
🤖 A full-day hands-on workshop on making #Angular apps smarter with Generative AI.
🤖 Two talks on the Prompt API & #WebNN for in-browser inference, and #BuiltInAI & #WebMCP for bringing agentic capabilities right into the browser.Thanks for the questions, the hallway chats, and the new connections. Until next time! 👋
🔗 https://www.thinktecture.com/conferences/international-javascript-conference-san-diego-2026/
-
That's a wrap on the International JavaScript Conference in San Diego! 🌴
A huge thank you to everyone who joined my sessions:
🤖 A full-day hands-on workshop on making #Angular apps smarter with Generative AI.
🤖 Two talks on the Prompt API & #WebNN for in-browser inference, and #BuiltInAI & #WebMCP for bringing agentic capabilities right into the browser.Thanks for the questions, the hallway chats, and the new connections. Until next time! 👋
🔗 https://www.thinktecture.com/conferences/international-javascript-conference-san-diego-2026/
-
That's a wrap on the International JavaScript Conference in San Diego! 🌴
A huge thank you to everyone who joined my sessions:
🤖 A full-day hands-on workshop on making #Angular apps smarter with Generative AI.
🤖 Two talks on the Prompt API & #WebNN for in-browser inference, and #BuiltInAI & #WebMCP for bringing agentic capabilities right into the browser.Thanks for the questions, the hallway chats, and the new connections. Until next time! 👋
🔗 https://www.thinktecture.com/conferences/international-javascript-conference-san-diego-2026/
-
Is your AI feature a "Main Quest" helper or a high-friction detour?
Most AI feels like a "Pull" handle on a door that should have a Push-bar. I deconstructed an AI Alt-Text demo using the built-in AI APIs to meet users where they already go.
✅ Follow The Momentum: Why Push-bars beat Pull handles.
✅ The Latency Tax: Hide the seams or quality won't matter.
✅ Temporal Illusions: Why "instant" AI can decrease trust.📖 https://exploractical.com/blog/2026/alt-text/
🧪 https://exploractical.com/demos/alt-text/ -
Is your AI feature a "Main Quest" helper or a high-friction detour?
Most AI feels like a "Pull" handle on a door that should have a Push-bar. I deconstructed an AI Alt-Text demo using the built-in AI APIs to meet users where they already go.
✅ Follow The Momentum: Why Push-bars beat Pull handles.
✅ The Latency Tax: Hide the seams or quality won't matter.
✅ Temporal Illusions: Why "instant" AI can decrease trust.📖 https://exploractical.com/blog/2026/alt-text/
🧪 https://exploractical.com/demos/alt-text/ -
Is your AI feature a "Main Quest" helper or a high-friction detour?
Most AI feels like a "Pull" handle on a door that should have a Push-bar. I deconstructed an AI Alt-Text demo using the built-in AI APIs to meet users where they already go.
✅ Follow The Momentum: Why Push-bars beat Pull handles.
✅ The Latency Tax: Hide the seams or quality won't matter.
✅ Temporal Illusions: Why "instant" AI can decrease trust.📖 https://exploractical.com/blog/2026/alt-text/
🧪 https://exploractical.com/demos/alt-text/ -
Is your AI feature a "Main Quest" helper or a high-friction detour?
Most AI feels like a "Pull" handle on a door that should have a Push-bar. I deconstructed an AI Alt-Text demo using the built-in AI APIs to meet users where they already go.
✅ Follow The Momentum: Why Push-bars beat Pull handles.
✅ The Latency Tax: Hide the seams or quality won't matter.
✅ Temporal Illusions: Why "instant" AI can decrease trust.📖 https://exploractical.com/blog/2026/alt-text/
🧪 https://exploractical.com/demos/alt-text/ -
Is your AI feature a "Main Quest" helper or a high-friction detour?
Most AI feels like a "Pull" handle on a door that should have a Push-bar. I deconstructed an AI Alt-Text demo using the built-in AI APIs to meet users where they already go.
✅ Follow The Momentum: Why Push-bars beat Pull handles.
✅ The Latency Tax: Hide the seams or quality won't matter.
✅ Temporal Illusions: Why "instant" AI can decrease trust.📖 https://exploractical.com/blog/2026/alt-text/
🧪 https://exploractical.com/demos/alt-text/ -
In most enterprise environments, third party cloud-based STT is a non-starter. That usually leaves us with mediocre OS defaults.
My colleague @paul 's "Utter" Chrome extension fixes this by keeping the intelligence loop local. It uses the WebSpeech and Prompt APIs to transcribe and polish your "train of thought" entirely on-device. 🛡️✨
A productivity unlock for AI agent workflows without the data leakage.
Give it a spin: https://chromewebstore.google.com/detail/utter/eejdhhjghkhkfejhbceeknhebhegijee
-
In most enterprise environments, third party cloud-based STT is a non-starter. That usually leaves us with mediocre OS defaults.
My colleague @paul 's "Utter" Chrome extension fixes this by keeping the intelligence loop local. It uses the WebSpeech and Prompt APIs to transcribe and polish your "train of thought" entirely on-device. 🛡️✨
A productivity unlock for AI agent workflows without the data leakage.
Give it a spin: https://chromewebstore.google.com/detail/utter/eejdhhjghkhkfejhbceeknhebhegijee
-
In most enterprise environments, third party cloud-based STT is a non-starter. That usually leaves us with mediocre OS defaults.
My colleague @paul 's "Utter" Chrome extension fixes this by keeping the intelligence loop local. It uses the WebSpeech and Prompt APIs to transcribe and polish your "train of thought" entirely on-device. 🛡️✨
A productivity unlock for AI agent workflows without the data leakage.
Give it a spin: https://chromewebstore.google.com/detail/utter/eejdhhjghkhkfejhbceeknhebhegijee
-
In most enterprise environments, third party cloud-based STT is a non-starter. That usually leaves us with mediocre OS defaults.
My colleague @paul 's "Utter" Chrome extension fixes this by keeping the intelligence loop local. It uses the WebSpeech and Prompt APIs to transcribe and polish your "train of thought" entirely on-device. 🛡️✨
A productivity unlock for AI agent workflows without the data leakage.
Give it a spin: https://chromewebstore.google.com/detail/utter/eejdhhjghkhkfejhbceeknhebhegijee
-
In most enterprise environments, third party cloud-based STT is a non-starter. That usually leaves us with mediocre OS defaults.
My colleague @paul 's "Utter" Chrome extension fixes this by keeping the intelligence loop local. It uses the WebSpeech and Prompt APIs to transcribe and polish your "train of thought" entirely on-device. 🛡️✨
A productivity unlock for AI agent workflows without the data leakage.
Give it a spin: https://chromewebstore.google.com/detail/utter/eejdhhjghkhkfejhbceeknhebhegijee
-
Videos from the Web AI Summit coming soon!
In the meantime, here's the deck for "Beyond the demo: building the WebAI playbook." Let's validate ideas & UX patterns, fill tooling gaps, and write this playbook together.
-
Videos from the Web AI Summit coming soon!
In the meantime, here's the deck for "Beyond the demo: building the WebAI playbook." Let's validate ideas & UX patterns, fill tooling gaps, and write this playbook together.
-
Videos from the Web AI Summit coming soon!
In the meantime, here's the deck for "Beyond the demo: building the WebAI playbook." Let's validate ideas & UX patterns, fill tooling gaps, and write this playbook together.
-
Videos from the Web AI Summit coming soon!
In the meantime, here's the deck for "Beyond the demo: building the WebAI playbook." Let's validate ideas & UX patterns, fill tooling gaps, and write this playbook together.
-
Videos from the Web AI Summit coming soon!
In the meantime, here's the deck for "Beyond the demo: building the WebAI playbook." Let's validate ideas & UX patterns, fill tooling gaps, and write this playbook together.
-
#JSConfMX 🌵 talk done (in bad Spanish 🫣). Demonstrated how to add built-in AI (Summarizer, Translator, Prompt API with multimodal input) to a conference webpage like https://tomayac.github.io/throw-aways/jsconf-mexico-2025/ (a clone of the real deal https://jsconfmx.org/speaker/W3Eio). Then walked through the code based on a broken down, step-by-step reduced version (https://googlechrome.github.io/samples/built-in-ai-rocks/). Learn more at https://developer.chrome.com/docs/ai/built-in-apis?hl=en#api_status! 🧠 #BuiltInAI
-
#JSConfMX 🌵 talk done (in bad Spanish 🫣). Demonstrated how to add built-in AI (Summarizer, Translator, Prompt API with multimodal input) to a conference webpage like https://tomayac.github.io/throw-aways/jsconf-mexico-2025/ (a clone of the real deal https://jsconfmx.org/speaker/W3Eio). Then walked through the code based on a broken down, step-by-step reduced version (https://googlechrome.github.io/samples/built-in-ai-rocks/). Learn more at https://developer.chrome.com/docs/ai/built-in-apis?hl=en#api_status! 🧠 #BuiltInAI
-
#JSConfMX 🌵 talk done (in bad Spanish 🫣). Demonstrated how to add built-in AI (Summarizer, Translator, Prompt API with multimodal input) to a conference webpage like https://tomayac.github.io/throw-aways/jsconf-mexico-2025/ (a clone of the real deal https://jsconfmx.org/speaker/W3Eio). Then walked through the code based on a broken down, step-by-step reduced version (https://googlechrome.github.io/samples/built-in-ai-rocks/). Learn more at https://developer.chrome.com/docs/ai/built-in-apis?hl=en#api_status! 🧠 #BuiltInAI
-
#JSConfMX 🌵 talk done (in bad Spanish 🫣). Demonstrated how to add built-in AI (Summarizer, Translator, Prompt API with multimodal input) to a conference webpage like https://tomayac.github.io/throw-aways/jsconf-mexico-2025/ (a clone of the real deal https://jsconfmx.org/speaker/W3Eio). Then walked through the code based on a broken down, step-by-step reduced version (https://googlechrome.github.io/samples/built-in-ai-rocks/). Learn more at https://developer.chrome.com/docs/ai/built-in-apis?hl=en#api_status! 🧠 #BuiltInAI
-
#JSConfMX 🌵 talk done (in bad Spanish 🫣). Demonstrated how to add built-in AI (Summarizer, Translator, Prompt API with multimodal input) to a conference webpage like https://tomayac.github.io/throw-aways/jsconf-mexico-2025/ (a clone of the real deal https://jsconfmx.org/speaker/W3Eio). Then walked through the code based on a broken down, step-by-step reduced version (https://googlechrome.github.io/samples/built-in-ai-rocks/). Learn more at https://developer.chrome.com/docs/ai/built-in-apis?hl=en#api_status! 🧠 #BuiltInAI
-
Building the "Guess Who?" game with the Prompt API: https://developer.chrome.com/blog/ai-guessing-game. Cool new #BuiltInAI demo by @utilitybend.
😃🥹🤩❌🧐
Is your character holding back its tears?
Does your character wear a a monocle? -
Building the "Guess Who?" game with the Prompt API: https://developer.chrome.com/blog/ai-guessing-game. Cool new #BuiltInAI demo by @utilitybend.
😃🥹🤩❌🧐
Is your character holding back its tears?
Does your character wear a a monocle? -
Building the "Guess Who?" game with the Prompt API: https://developer.chrome.com/blog/ai-guessing-game. Cool new #BuiltInAI demo by @utilitybend.
😃🥹🤩❌🧐
Is your character holding back its tears?
Does your character wear a a monocle? -
Building the "Guess Who?" game with the Prompt API: https://developer.chrome.com/blog/ai-guessing-game. Cool new #BuiltInAI demo by @utilitybend.
😃🥹🤩❌🧐
Is your character holding back its tears?
Does your character wear a a monocle? -
Building the "Guess Who?" game with the Prompt API: https://developer.chrome.com/blog/ai-guessing-game. Cool new #BuiltInAI demo by @utilitybend.
😃🥹🤩❌🧐
Is your character holding back its tears?
Does your character wear a a monocle? -
Before any of the built-in AI APIs in Chrome can be used, the underlying AI model and any customizations (such as fine-tunings) must be downloaded from the network 🌐, the compressed data be extracted 🗜️, and finally be loaded into memory 🧠. My new guide documents some of the best practices for improving the user experience as they wait for this download: https://developer.chrome.com/docs/ai/inform-users-of-model-download.
There are two embedded demos that show:
- Client-side only
- Hybrid implementation -
Before any of the built-in AI APIs in Chrome can be used, the underlying AI model and any customizations (such as fine-tunings) must be downloaded from the network 🌐, the compressed data be extracted 🗜️, and finally be loaded into memory 🧠. My new guide documents some of the best practices for improving the user experience as they wait for this download: https://developer.chrome.com/docs/ai/inform-users-of-model-download.
There are two embedded demos that show:
- Client-side only
- Hybrid implementation -
Before any of the built-in AI APIs in Chrome can be used, the underlying AI model and any customizations (such as fine-tunings) must be downloaded from the network 🌐, the compressed data be extracted 🗜️, and finally be loaded into memory 🧠. My new guide documents some of the best practices for improving the user experience as they wait for this download: https://developer.chrome.com/docs/ai/inform-users-of-model-download.
There are two embedded demos that show:
- Client-side only
- Hybrid implementation -
Before any of the built-in AI APIs in Chrome can be used, the underlying AI model and any customizations (such as fine-tunings) must be downloaded from the network 🌐, the compressed data be extracted 🗜️, and finally be loaded into memory 🧠. My new guide documents some of the best practices for improving the user experience as they wait for this download: https://developer.chrome.com/docs/ai/inform-users-of-model-download.
There are two embedded demos that show:
- Client-side only
- Hybrid implementation -
Before any of the built-in AI APIs in Chrome can be used, the underlying AI model and any customizations (such as fine-tunings) must be downloaded from the network 🌐, the compressed data be extracted 🗜️, and finally be loaded into memory 🧠. My new guide documents some of the best practices for improving the user experience as they wait for this download: https://developer.chrome.com/docs/ai/inform-users-of-model-download.
There are two embedded demos that show:
- Client-side only
- Hybrid implementation -
We're excited to announce the release of version 0.0.10 of our TypeScript types for Built-in AI APIs, now featuring support for the brand-new Proofreader API! Check it out and upgrade today: https://www.npmjs.com/package/@types/dom-chromium-ai @tomayac #BuiltinAI #WebAI
-
We're excited to announce the release of version 0.0.10 of our TypeScript types for Built-in AI APIs, now featuring support for the brand-new Proofreader API! Check it out and upgrade today: https://www.npmjs.com/package/@types/dom-chromium-ai @tomayac #BuiltinAI #WebAI
-
We're excited to announce the release of version 0.0.10 of our TypeScript types for Built-in AI APIs, now featuring support for the brand-new Proofreader API! Check it out and upgrade today: https://www.npmjs.com/package/@types/dom-chromium-ai @tomayac #BuiltinAI #WebAI
-
I have attendee codes for the Web AI Summit in Sunnyvale on Oct 17. The Chrome Web AI team wants to meet you for the hallway track. Share your Web AI projects & pain points for a chance to get a code & help us with critical context engineering.
Agenda: https://rsvp.withgoogle.com/events/web-ai-summit-2025/sessions
Can't make it? No worries—the talks will be published a few weeks after the event.
-
I have attendee codes for the Web AI Summit in Sunnyvale on Oct 17. The Chrome Web AI team wants to meet you for the hallway track. Share your Web AI projects & pain points for a chance to get a code & help us with critical context engineering.
Agenda: https://rsvp.withgoogle.com/events/web-ai-summit-2025/sessions
Can't make it? No worries—the talks will be published a few weeks after the event.
-
I have attendee codes for the Web AI Summit in Sunnyvale on Oct 17. The Chrome Web AI team wants to meet you for the hallway track. Share your Web AI projects & pain points for a chance to get a code & help us with critical context engineering.
Agenda: https://rsvp.withgoogle.com/events/web-ai-summit-2025/sessions
Can't make it? No worries—the talks will be published a few weeks after the event.
-
I have attendee codes for the Web AI Summit in Sunnyvale on Oct 17. The Chrome Web AI team wants to meet you for the hallway track. Share your Web AI projects & pain points for a chance to get a code & help us with critical context engineering.
Agenda: https://rsvp.withgoogle.com/events/web-ai-summit-2025/sessions
Can't make it? No worries—the talks will be published a few weeks after the event.