Загрузка видео...

Не удалось загрузить видео

На главную

Open-source Flutter + Google AI Dart SDK project alert 🚨 To try out the new Google AI package announced last week, I built a fun AI photo scavenger hunt application over the weekend! The game is simple: - Choose your hunting location - Gemini generates 5 items that you...

18,212 просмотров • 2 лет назад •via X (Twitter)

Комментарии: 10

Фото профиля Mangirdas Kazlauskas 💙
Mangirdas Kazlauskas 💙2 лет назад

Last week @FlutterDev team announced the Google AI Dart SDK - a package that simplifies the access to Gemini models for your Flutter apps and Dart applications. The package is published on and already gained some traction:

Фото профиля Mangirdas Kazlauskas 💙
Mangirdas Kazlauskas 💙2 лет назад

I have never used AI in my Flutter apps before (directly, not via some kind of back-end API), so it was a great chance to try out the waters. As a result, a new fun game was born and the code is available here:

Фото профиля Mangirdas Kazlauskas 💙
Mangirdas Kazlauskas 💙2 лет назад

Launch the project, play with prompts and other app settings, and create pull requests for new features. We still do not have that many learning resources for the new Dart AI package, so I am thrilled to be able to contribute to the ecosystem 💪 CC: @KhanhNwin @craig_labenz

Фото профиля Mangirdas Kazlauskas 💙
Mangirdas Kazlauskas 💙2 лет назад

What are your thoughts about the new package? Have you tried it already? Share your insights and let me know! ✌️

Фото профиля Mangirdas Kazlauskas 💙
Mangirdas Kazlauskas 💙2 лет назад

Any possible feature ideas where AI could help for your app? 👀

Фото профиля Mangirdas Kazlauskas 💙
Mangirdas Kazlauskas 💙2 лет назад

*Psst*, a video about the journey of creating the app is already out! 👀

Фото профиля Uttkarsh
Uttkarsh2 лет назад

I wish i could come up with such creative ideas... nice one... 🔥🔥

Фото профиля Mangirdas Kazlauskas 💙
Mangirdas Kazlauskas 💙2 лет назад

You can generate ideas using the same Gemini model as well... Just saying 👀

Фото профиля Julia Agüero 💙
Julia Agüero 💙2 лет назад

That looks so fun! How was the implementation of the AI?

Фото профиля Mangirdas Kazlauskas 💙
Mangirdas Kazlauskas 💙2 лет назад

Had to go back and forth with the prompt until I got quite consistent results in the format I expect. Other than that - similar as calling any other API via HttpClient 🤷‍♂️

Похожие видео

Gemini for Android is here! This new app makes it easier to access Google's chatbot, powered by the Gemini Pro LLM, right from your Android device. You can ask Gemini a question by tapping the launcher icon or long-pressing the power button. Once invoked, the Gemini overlay lets you enter a text or text+image prompt. You can tap the camera icon to snap a photo or press the "add this screen" button to take a screenshot of the current page to include in your prompt. The Gemini app for Android is available on Google Play with support for English, but support for Korean and Japanese will be coming next week. While there won't be an app for iOS, iPhone users can access Gemini by opening the Google App and tapping the "Gemini" button up top. How can you long-press the power button to invoke Gemini if that gesture is handled by Google Assistant? The answer is that the Gemini Android app can replace Google Assistant as your default assistant if you want, meaning all the ways you'd normally invoke Google Assistant on your phone can instead invoke Gemini. Unfortunately, Gemini currently doesn't offer ALL the same functionality as Google Assistant and requires an active data connection, but more features will be added over time. There's also now a Gemini Advanced tier, which offers access to Google's most powerful Ultra 1.0 LLM. Access to Gemini Advanced requires a subscription to the new $20/month "AI Premium" Google One plan, which offers the same benefits as the 2TB plan but adds access to Gemini Advanced and soon Gemini features in Gmail, Docs, & other Workspace apps (formerly under the Duet AI umbrella). Gemini Advanced is available in English on the web.

Mishaal Rahman

38,428 просмотров • 2 лет назад

🦔 Google Chrome is launching "autobrowsing" today for paid subscribers. Instead of just autofilling your credit card, Chrome will now complete entire tasks for you: filling out PDFs, renewing your driver's license, researching trips, booking reservations. You give it a task, it browses the web autonomously, and asks for your approval at the final step. Available for Google AI Pro ($19.99/month) or AI Ultra ($249.99/month). All Chrome users get a new Gemini AI sidebar that pulls from your Gmail and past conversations. My Take Last week Google announced AI Mode connecting to your Gmail and Photos. Now Chrome is pulling from your emails, conversations, and browsing activity to act on your behalf. Every new AI feature requires deeper access to your personal data. You're not just paying $20 or $250 a month for convenience. You're handing over your credit cards, government documents, addresses, and browsing habits to an AI that will interact with websites as you. The people excited about this haven't thought through what happens when it goes wrong. An AI filling out government forms. An AI with your credit card making purchases. An AI that hallucinates or gets social engineered. And when adoption isn't fast enough, they'll degrade regular search and browsing until this feels like the only viable option. That's the playbook. Meanwhile $250 a month tells you exactly how much this costs them to run, and how desperate they are to find someone willing to pay for it. Hedgie🤗

Hedgie

11,662 просмотров • 6 месяцев назад