正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Watch Gemini 3.7 Flash handle autonomous website optimization in Google Antigravity. Leveraging MCP servers, multimodal understanding, and long-horizon execution, the agent sets out to achieve a 100 across all Lighthouse metrics and modernize the site to the latest web standards.

Google Antigravity

191,283 subscribers

99,773 次观看 • 1 个月前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

30 条评论

Google Antigravity 的头像

Google Antigravity1 个月前

Try it today:

Lucky Star1 个月前

I shouldn't have bought the annual subscription! Your LLM is the worst on the market. In Antigravity ide, Gemini 3.1 Pro hallucinates—returning placeholders instead of code. The models lie, there are errors and freezes, and Flash is useless.

king 的头像

king1 个月前

Agent execution terminated due to error.

yuan 的头像

yuan1 个月前

Agent execution terminated due to error.

ToBOT 的头像

ToBOT1 个月前

The error has been reported since today: Agent execution terminated due to error.

波斯老登的头像

波斯老登1 个月前

fk u

levi 的头像

levi1 个月前

someone threw into gemini “give me buzz words” and used in this post 🤡🤡

Mike 的头像

Mike1 个月前

Another regression that was made (beyond getting rid of what few right click options used to be present) is that I can't zoom in and out of mermaid charts anymore.

selvakumar 的头像

selvakumar1 个月前

My IDE crashed mid-work. On restart, the conversation history was lost, and the agent doesn't know where to resume .The agent is now generating random outputs.😕

Mauricio 的头像

Mauricio1 个月前

Guys, give Gemini 3.7 Flash a chance... it's very good

fatwang2 的头像

fatwang21 个月前

Like this？

白川ユウ的头像

白川ユウ1 个月前

When an MCP call fails mid-run, does the agent retry itself or does the run just restart?

SHIROI KOIBITO 的头像

SHIROI KOIBITO1 个月前

Gemini 3.7 Flash が「性能向上」を強調しても、ユーザーが感じる進歩は「管理の手間が減ったか」に尽きます。現状ではまだ「高性能な生成機能を搭載した手作業支援ツール」の域を出ていません。真のアップグレードとは「人間がAIを管理する手間が減った」

FactAtlas 💡 的头像

FactAtlas 💡1 个月前

Shameless

sophia 𖥧 的头像

sophia 𖥧1 个月前

mcp server setup, custom or off the shelf?

♡ sophia ࣪˖ 的头像

♡ sophia ࣪˖1 个月前

wait can it hit 100 across all four or just performance

XIN 的头像

XIN1 个月前

Agent execution terminated due to error.

realWorld 的头像

realWorld1 个月前

How about pro version? Google is dead?

Nick Medrano 的头像

Nick Medrano1 个月前

Thank you! Audited my site!

paki femboy :3⚡⚡🇵🇰 的头像

paki femboy :3⚡⚡🇵🇰1 个月前

was lowkey going to hate but damn this model kind of surprised me. honestly noticed such a big difference compared to 3.6 flash. now can't wait for Gemini 4 pro 🙏

ふりーだむ的头像

ふりーだむ1 个月前

賢くなるの?

わさび部長｜note｜いい人生のつくり方的头像

わさび部長｜note｜いい人生のつくり方1 个月前

どんなタスクにも、3.1 pro よりも 3.7 Flashを使うべきですか？

Tama 的头像

Tama1 个月前

Does agy use the new mcp 2?

9h0st 的头像

9h0st1 个月前

自动优化Lighthouse很适合演示，但上线前还要验证真实流量、可访问性回归和可回滚变更。

Jara 的头像

Jara1 个月前

Wonderful

Antoine Ríos ッ的头像

Antoine Ríos ッ1 个月前

Useless

AI Mastery Guide 的头像

AI Mastery Guide1 个月前

A perfect Lighthouse score autonomously, that's a real test

ケッティ ⚽️ eFootball最新情報的头像

ケッティ ⚽️ eFootball最新情報1 个月前

3.6よりかなり信頼できるように感じるよ。

Hawthorne 的头像

Hawthorne1 个月前

Models are getting more crazier day by day

XAI LOVE 的头像

XAI LOVE1 个月前

ANTIGRAVIT WOW HOW DOSE WORK IT OH NOOOOOOO MF FOT

相关视频

Antigravity analyzes massive datasets across multiple cloud environments to isolate data anomalies and build automated production pipelines. In this demo, Gemini 3.7 Flash showcases its ability to reason across BigQuery, PostgreSQL, and Cloud Storage, execute self-healing build and debug loops, and apply multimodal understanding through native PDF parsing.

Antigravity analyzes massive datasets across multiple cloud environments to isolate data anomalies and build automated production pipelines. In this demo, Gemini 3.7 Flash showcases its ability to reason across BigQuery, PostgreSQL, and Cloud Storage, execute self-healing build and debug loops, and apply multimodal understanding through native PDF parsing.

Google Antigravity

54,769 次观看 • 1 个月前

We’re rolling out 3.5 Flash to everyone in the Google Gemini and AI Mode in Google Search. Developers can start building in Google Antigravity and via the Gemini API in GoogleAIStudio. #GoogleIO

We’re rolling out 3.5 Flash to everyone in the Google Gemini and AI Mode in Google Search. Developers can start building in Google Antigravity and via the Gemini API in GoogleAIStudio. #GoogleIO

Google DeepMind

66,242 次观看 • 4 个月前

ICYMI: Gemini 3.7 Flash is now available to all Google AI Pro and Ultra users in Gemini chat and Gemini Spark ✨ For Gemini Spark, this means your 24/7 personal AI agent in the Google Gemini is now even better at handling multi-step tasks for you and using tools across your Google Workspace apps like Google Calendar, Google Docs, and Gmail.

ICYMI: Gemini 3.7 Flash is now available to all Google AI Pro and Ultra users in Gemini chat and Gemini Spark ✨ For Gemini Spark, this means your 24/7 personal AI agent in the Google Gemini is now even better at handling multi-step tasks for you and using tools across your Google Workspace apps like Google Calendar, Google Docs, and Gmail.

Google

352,612 次观看 • 1 个月前

We fed Gemini 3.7 Flash hundreds of PDFs from a Victorian book of botanical illustrations and tasked it with extracting and classifying these historical plants using the modern APG IV classification system. 🌳 💻 Watch how it brings its understanding to life in an interactive visualization built in Google Antigravity:

We fed Gemini 3.7 Flash hundreds of PDFs from a Victorian book of botanical illustrations and tasked it with extracting and classifying these historical plants using the modern APG IV classification system. 🌳 💻 Watch how it brings its understanding to life in an interactive visualization built in Google Antigravity:

Google AI Developers

65,346 次观看 • 1 个月前

Static PDF ➡️ interactive web app, all in one prompt! We used Gemini 3.7 Flash in Google AI Studio to transform a dense PDF annual report into a beautiful website. Using its native PDF understanding, the model easily extracted data, crunched the numbers, and generated delightful interactive UI in one go. Learn how from genevieveh@:

Static PDF ➡️ interactive web app, all in one prompt! We used Gemini 3.7 Flash in Google AI Studio to transform a dense PDF annual report into a beautiful website. Using its native PDF understanding, the model easily extracted data, crunched the numbers, and generated delightful interactive UI in one go. Learn how from genevieveh@:

Google for Developers

66,424 次观看 • 1 个月前

Our latest model Gemini 3.7 Flash ⚡️ is beginning to roll out across Google Workspace, starting with Google Sheets canvas! Transform your spreadsheets into mini apps in just a single prompt. Available globally in English to Google AI Pro and Ultra subscribers.

Our latest model Gemini 3.7 Flash ⚡️ is beginning to roll out across Google Workspace, starting with Google Sheets canvas! Transform your spreadsheets into mini apps in just a single prompt. Available globally in English to Google AI Pro and Ultra subscribers.

Chandu Thota

71,749 次观看 • 1 个月前

Our most intelligent workhorse model yet for coding and agents has arrived ⚡ Meet Gemini 3.7 Flash. — Crush that seemingly endless to-do list. Gemini Spark in the Google Gemini now uses 3.7 Flash. The new model can equip your personal AI agent to work even smarter for you by seamlessly handling complex, multi-step tasks across your Google Workspace apps like Gmail, Google Calendar and Google Docs — Enjoy a smoother build experience. The model thinks more diligently, putting more effort into multi-step planning and tool calls. A more disciplined execution means less manual oversight and fewer retries across engineering workflows — Build more, spend less. 3.7 Flash is available through the end of the year with an introductory price of half the original 3.6 Flash cost per million tokens ($0.75/1M input tokens and $3.75/1M output tokens)

Our most intelligent workhorse model yet for coding and agents has arrived ⚡ Meet Gemini 3.7 Flash. — Crush that seemingly endless to-do list. Gemini Spark in the Google Gemini now uses 3.7 Flash. The new model can equip your personal AI agent to work even smarter for you by seamlessly handling complex, multi-step tasks across your Google Workspace apps like Gmail, Google Calendar and Google Docs — Enjoy a smoother build experience. The model thinks more diligently, putting more effort into multi-step planning and tool calls. A more disciplined execution means less manual oversight and fewer retries across engineering workflows — Build more, spend less. 3.7 Flash is available through the end of the year with an introductory price of half the original 3.6 Flash cost per million tokens ($0.75/1M input tokens and $3.75/1M output tokens)

Google AI

129,191 次观看 • 1 个月前

One prompt → your next landing page. We hooked up Gemini 3.7 Flash with Nano Banana and Omni in @Antigravity to build an interactive landing page from scratch, generating the copy, images, and video in a single shot.

One prompt → your next landing page. We hooked up Gemini 3.7 Flash with Nano Banana and Omni in @Antigravity to build an interactive landing page from scratch, generating the copy, images, and video in a single shot.

Google

421,464 次观看 • 1 个月前

Antigravity is more than just a tool. It’s a platform you use to navigate the logic and the execution in one place. By leveraging Gemini’s multimodal power, we’re enabling everyone to think through complex problems and build directly upon those insights, creating things they never dreamed possible.

Antigravity is more than just a tool. It’s a platform you use to navigate the logic and the execution in one place. By leveraging Gemini’s multimodal power, we’re enabling everyone to think through complex problems and build directly upon those insights, creating things they never dreamed possible.

Google Antigravity

102,984 次观看 • 6 个月前

Google I/O showed where AI is headed. Our community spent the weekend building it. Builders gathered in San Francisco alongside Google DeepMind to turn the newest Gemini + Gemma capabilities into working products. From multimodal agents and voice interfaces to long-horizon reasoning systems, teams showed us what’s possible with Gemini 3.5 Flash. The winners:

Google I/O showed where AI is headed. Our community spent the weekend building it. Builders gathered in San Francisco alongside Google DeepMind to turn the newest Gemini + Gemma capabilities into working products. From multimodal agents and voice interfaces to long-horizon reasoning systems, teams showed us what’s possible with Gemini 3.5 Flash. The winners:

Cerebral Valley

19,088 次观看 • 4 个月前

Gemini Flash 3.7 + Seedance 2.5 = cinematic websites I built this experimental website dedicated to the Arsenal winning the first trophy of the season in a few hours - all with AI Remix (Google AI Studio): Preview: Pipeline🔽

Gemini Flash 3.7 + Seedance 2.5 = cinematic websites I built this experimental website dedicated to the Arsenal winning the first trophy of the season in a few hours - all with AI Remix (Google AI Studio): Preview: Pipeline🔽

AmirMušić

19,933 次观看 • 1 个月前

this github repo contains 50 of the most essential MCP servers that give your AI agents superpowers. > works with claude code, gemini, codex, cursor, and other MCP-compatible clients > MIT licensed > 5 categories, 50 MCP servers in total whether you want your agent to browse the web, manage files, interact with apps, or automate workflows, you'll find the right MCP here. link:

this github repo contains 50 of the most essential MCP servers that give your AI agents superpowers. > works with claude code, gemini, codex, cursor, and other MCP-compatible clients > MIT licensed > 5 categories, 50 MCP servers in total whether you want your agent to browse the web, manage files, interact with apps, or automate workflows, you'll find the right MCP here. link:

m0h

60,642 次观看 • 3 个月前

We asked Antigravity to onboard a new designer. It crawled our site for our fonts, logo, and color palette, compiled the specs into a walkthrough, and drafted the email in Gmail. From the agent manager to website to inbox. Back to building. 💻

Google Antigravity

133,960 次观看 • 8 个月前

Introducing Gemini 2.0 Flash with Google AI Studio in PyCharm... Totally Free! 🤩 In just one minute, I'll show you how to connect your Google AI Studio account and start using the Gemini 2.0 Flash and Gemini 2.0 Flash Thinking models for free. Save this video to stay updated on all the latest Google DeepMind models available in JetBrains editors! PyCharm, a JetBrains IDE CodeGPT Google for Developers

Introducing Gemini 2.0 Flash with Google AI Studio in PyCharm... Totally Free! 🤩 In just one minute, I'll show you how to connect your Google AI Studio account and start using the Gemini 2.0 Flash and Gemini 2.0 Flash Thinking models for free. Save this video to stay updated on all the latest Google DeepMind models available in JetBrains editors! PyCharm, a JetBrains IDE CodeGPT Google for Developers

Daniel San

65,294 次观看 • 1 年前

Watch Gemini 3 Flash build out a limited edition product launch. From a single prompt, the model processes a Google Sheet, updates an e-commerce storefront and deploys a custom newsletter waitlist to capture demand.👇

Watch Gemini 3 Flash build out a limited edition product launch. From a single prompt, the model processes a Google Sheet, updates an e-commerce storefront and deploys a custom newsletter waitlist to capture demand.👇

Google Antigravity

65,542 次观看 • 9 个月前

Gemini 3.5 flash + Gemini managed agents api just audited a real megatron-lm ci failure inside Eigent. root cause in minutes! watch the handoff: coordinator agent plans the audit, developer agent loads the ml-failure-audit skill and gathers the evidence, then gemini agent steps in as a remote sub-agent for the heavy reasoning. gemini managed agents api and gemini 3.5 flash now live on our open-source cowork Eigent! Google AI Developers Google AI Studio

Gemini 3.5 flash + Gemini managed agents api just audited a real megatron-lm ci failure inside Eigent. root cause in minutes! watch the handoff: coordinator agent plans the audit, developer agent loads the ml-failure-audit skill and gathers the evidence, then gemini agent steps in as a remote sub-agent for the heavy reasoning. gemini managed agents api and gemini 3.5 flash now live on our open-source cowork Eigent! Google AI Developers Google AI Studio

Eigent AI

17,217 次观看 • 4 个月前

Google Antigravity 🎨 A multi cross-platform design system. Watch 3.8 Flash deploy parallel subagents in Antigravity to map out tokens, components, and styling across 12 distinct frameworks. It even packages it all up into an interactive live theme editor.

Google Antigravity 🎨 A multi cross-platform design system. Watch 3.8 Flash deploy parallel subagents in Antigravity to map out tokens, components, and styling across 12 distinct frameworks. It even packages it all up into an interactive live theme editor.

Google for Developers

12,835 次观看 • 28 天前

Introducing the Gemini API plugin in Antigravity🚀 A new plugin bundled with Google Antigravity to make it easier to build apps and agents with Gemini! Enable it today: ⚙️ → Customizations → Build with Google Plugins

Introducing the Gemini API plugin in Antigravity🚀 A new plugin bundled with Google Antigravity to make it easier to build apps and agents with Gemini! Enable it today: ⚙️ → Customizations → Build with Google Plugins

Jack Wotherspoon

20,299 次观看 • 1 个月前

Today, we’re launching Agentic Video Understanding in Gemini across 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite. 📉 ~88% fewer tokens 💰 ~66% lower cost 📈 ~7% higher accuracy The result: a new Pareto frontier for video understanding across accuracy and cost. Traditional video understanding processes video statically at a fixed sampling rate. With Agentic Video Understanding, Gemini can actively decide what to watch, at what speed, and which signals to use (frames, audio, or transcripts) by using native video tools. This enables split-second retrieval, rapid-motion understanding, and needle-in-a-haystack search across hours of video. Available now via the Gemini API - and coming soon to billions of users through the Gemini App and YouTube’s “Ask YouTube” experience. Learn more (details, demos, and docs): PMing this 0→1 has been a career highlight. Taking it from an idea and helping shape it into a frontier-defining capability we’re now shipping broadly has been incredibly rewarding. Huge thanks to Mario Lucic , Sergi Caelles Ahmet Iscen , Filip Pavetić, Suhas Yogin , JB Alayrac, Ben Caine, Nicole Brichtova, Bibo Xu , Tulsee Doshi, David Thacker, koray kavukcuoglu and the multimodal team at Google DeepMind.

Today, we’re launching Agentic Video Understanding in Gemini across 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite. 📉 ~88% fewer tokens 💰 ~66% lower cost 📈 ~7% higher accuracy The result: a new Pareto frontier for video understanding across accuracy and cost. Traditional video understanding processes video statically at a fixed sampling rate. With Agentic Video Understanding, Gemini can actively decide what to watch, at what speed, and which signals to use (frames, audio, or transcripts) by using native video tools. This enables split-second retrieval, rapid-motion understanding, and needle-in-a-haystack search across hours of video. Available now via the Gemini API - and coming soon to billions of users through the Gemini App and YouTube’s “Ask YouTube” experience. Learn more (details, demos, and docs): PMing this 0→1 has been a career highlight. Taking it from an idea and helping shape it into a frontier-defining capability we’re now shipping broadly has been incredibly rewarding. Huge thanks to Mario Lucic , Sergi Caelles Ahmet Iscen , Filip Pavetić, Suhas Yogin , JB Alayrac, Ben Caine, Nicole Brichtova, Bibo Xu , Tulsee Doshi, David Thacker, koray kavukcuoglu and the multimodal team at Google DeepMind.

Rohan Doshi

20,732 次观看 • 1 个月前

Today we're introducing Gemini 3.7 Flash, our most intelligent workhorse model yet for coding and agents. This model brings substantial gains across software engineering, web development, and complex knowledge work. Now through the end of the year, Gemini 3.7 Flash is available at an introductory price* of $0.75/1M input and $3.75/1M output tokens — making it easier and more cost-effective for developers and customers to scale production-ready agents.

Today we're introducing Gemini 3.7 Flash, our most intelligent workhorse model yet for coding and agents. This model brings substantial gains across software engineering, web development, and complex knowledge work. Now through the end of the year, Gemini 3.7 Flash is available at an introductory price* of $0.75/1M input and $3.75/1M output tokens — making it easier and more cost-effective for developers and customers to scale production-ready agents.

Google

1,183,589 次观看 • 1 个月前