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。

With gemini 3.5 flash lite, there’s almost no difference between loading a website and generating a new one on the fly. I built a little browser that treats every url as a prompt and generates a site from scratch. who wants the testflight?

vidy

8,718 subscribers

48,692 次观看 • 6 天前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

I built a browser entirely powered by Nano Banana 🍌 It generates each website based only on the URL. You can even navigate to other links. A truly new kind of internet, generated on the fly, and it's super fun.

I built a browser entirely powered by Nano Banana 🍌 It generates each website based only on the URL. You can even navigate to other links. A truly new kind of internet, generated on the fly, and it's super fun.

Pietro Schirano

309,366 次观看 • 10 个月前

Everyone's using Seedance 2.0. Most people are prompting from scratch and re-generating til something works. We built promo templates so you can easily make professional videos: 1. Pick a promo video template 2. Paste a website URL 3. Done Every output is usable. No prompt engineering. No generating 30 times hoping one looks good. Try it now:

Everyone's using Seedance 2.0. Most people are prompting from scratch and re-generating til something works. We built promo templates so you can easily make professional videos: 1. Pick a promo video template 2. Paste a website URL 3. Done Every output is usable. No prompt engineering. No generating 30 times hoping one looks good. Try it now:

ChatCut

16,601 次观看 • 3 个月前

Gemini 2.5 Flash can control a browser! Excited to share Gemini Browser Agent, a simple Python script example on how to use Google DeepMind Gemini 2.5 Flash and Browser Use to act as general assistant! 🤯 Usage Examples: 1⃣ Single Query Mode: `python scripts/gemini-browser-use.py --url --query "Summarize the key features of Gemini 2.5 Flash."` 2⃣Interactive Mode: Start an interactive session, optionally with a starting URL. `python scripts/gemini-browser-use.py` Command-line options: --model: The Gemini model to use (default: gemini-2.5-flash-preview-04-17) --headless: Run the browser in headless mode --url: Starting URL for the browser to navigate to before processing the query --query: Run a single query and exit (instead of interactive mode) Time to build a replication of Manus and OpenAI Operator powered by Gemini 2.5. Code below ⬇️

Gemini 2.5 Flash can control a browser! Excited to share Gemini Browser Agent, a simple Python script example on how to use Google DeepMind Gemini 2.5 Flash and Browser Use to act as general assistant! 🤯 Usage Examples: 1⃣ Single Query Mode: `python scripts/gemini-browser-use.py --url --query "Summarize the key features of Gemini 2.5 Flash."` 2⃣Interactive Mode: Start an interactive session, optionally with a starting URL. `python scripts/gemini-browser-use.py` Command-line options: --model: The Gemini model to use (default: gemini-2.5-flash-preview-04-17) --headless: Run the browser in headless mode --url: Starting URL for the browser to navigate to before processing the query --query: Run a single query and exit (instead of interactive mode) Time to build a replication of Manus and OpenAI Operator powered by Gemini 2.5. Code below ⬇️

Philipp Schmid

105,308 次观看 • 1 年前

Computer Use is now a built-in tool supported in Gemini 3.5 Flash. 💻 Developers can now use 3.5 Flash to build custom agents that see and take action across browser, mobile and desktop environments.

Computer Use is now a built-in tool supported in Gemini 3.5 Flash. 💻 Developers can now use 3.5 Flash to build custom agents that see and take action across browser, mobile and desktop environments.

Google

242,432 次观看 • 1 个月前

This is wild I built a full bookstore site in minutes with one prompt in Fellou As a marketing consultant, I usually spend hours on this. I asked Fellou: “Extract UX from the top 5 bookstore sites & build a website” The result? Shockingly good: 👇

This is wild I built a full bookstore site in minutes with one prompt in Fellou As a marketing consultant, I usually spend hours on this. I asked Fellou: “Extract UX from the top 5 bookstore sites & build a website” The result? Shockingly good: 👇

ZOYA ✪

28,914 次观看 • 1 年前

⚡️ Gemini 2.5 Flash and Pro are now stable, plus a new model joins the family: Flash-Lite, built for speed and efficiency at scale. Great for summarization, classification, and more → #GoogleDeveloperNews

⚡️ Gemini 2.5 Flash and Pro are now stable, plus a new model joins the family: Flash-Lite, built for speed and efficiency at scale. Great for summarization, classification, and more → #GoogleDeveloperNews

Google for Developers

14,319 次观看 • 1 年前

🚨 Gemini 3.5 Flash built a full Ubuntu/GNOME web OS in ONE shot. single HTML file, embedded CSS + JS. from one prompt: >working dock + top bar >functional terminal & Game >file manager with real navigation >window drag, resize, minimize on every window >settings panel >boot animation prompt + full code in the reply 👇

🚨 Gemini 3.5 Flash built a full Ubuntu/GNOME web OS in ONE shot. single HTML file, embedded CSS + JS. from one prompt: >working dock + top bar >functional terminal & Game >file manager with real navigation >window drag, resize, minimize on every window >settings panel >boot animation prompt + full code in the reply 👇

Chetaslua

58,334 次观看 • 2 个月前

Today, we're introducing not one but TWO new models, striking the balance between efficiency and quality to enable you to build production AI agents. — Gemini 3.6 Flash: Addresses efficiency feedback we received from Gemini 3.5 Flash with upgrades in coding, knowledge work, and multimodal tasks faster, more accurately, and with substantially fewer tokens per task — Gemini 3.5 Flash-Lite: Our fastest, most cost-effective 3.5-class model yet built for agentic workflows, hitting ~350 output tokens/sec with improved coding and overall quality Start building with these today via the Gemini API in Google AI Studio or try them out in the Google Gemini

Today, we're introducing not one but TWO new models, striking the balance between efficiency and quality to enable you to build production AI agents. — Gemini 3.6 Flash: Addresses efficiency feedback we received from Gemini 3.5 Flash with upgrades in coding, knowledge work, and multimodal tasks faster, more accurately, and with substantially fewer tokens per task — Gemini 3.5 Flash-Lite: Our fastest, most cost-effective 3.5-class model yet built for agentic workflows, hitting ~350 output tokens/sec with improved coding and overall quality Start building with these today via the Gemini API in Google AI Studio or try them out in the Google Gemini

Google AI

424,998 次观看 • 6 天前

POV: The year is 2025 and you're generating a full website using only one prompt 🌐

POV: The year is 2025 and you're generating a full website using only one prompt 🌐

Webild

119,906 次观看 • 8 个月前

Lady shares the difference between a woman who wants to be a wife and a woman who just wants a husband

Lady shares the difference between a woman who wants to be a wife and a woman who just wants a husband

Instablog9ja

85,716 次观看 • 4 个月前

I respect both players but there’s a huge difference between Ronaldo and Messi because only one player conquered every league, every challenge and every doubt and that’s why Ronaldo is seen as the GOAT

I respect both players but there’s a huge difference between Ronaldo and Messi because only one player conquered every league, every challenge and every doubt and that’s why Ronaldo is seen as the GOAT

ᴘʀɪɴᴄᴇ

17,749 次观看 • 5 个月前

🚨 Gemini 3.5 Flash just built a full Windows-style web OS in ONE shot. Single HTML file, embedded CSS + JS. From one prompt: > Windows-style taskbar + start menu > Draggable/resizable app windows > Functional file explorer > Working terminal + browser mockup > Desktop icons + notifications > Settings app, themes, boot screen All generated in one pass with almost no corrections. Gemini’s frontend/UI generation lately is getting ridiculous.

🚨 Gemini 3.5 Flash just built a full Windows-style web OS in ONE shot. Single HTML file, embedded CSS + JS. From one prompt: > Windows-style taskbar + start menu > Draggable/resizable app windows > Functional file explorer > Working terminal + browser mockup > Desktop icons + notifications > Settings app, themes, boot screen All generated in one pass with almost no corrections. Gemini’s frontend/UI generation lately is getting ridiculous.

WorldofAI

22,063 次观看 • 2 个月前

Introducing Gemini 3.5 Flash ⚡️ Normally, Gemini 3.5 Flash is 4x faster than other models with frontier performance. For a limited time, Antigravity is serving it 12x faster thanks to custom inference tricks, delivering incredible speed for your workflows. 🚀 See the performance in this demo: generating pixel art from photos, orchestrating multi-agent workflows to write and register sprites, and spawning browser subagents to auto-test rendering: 👇

Introducing Gemini 3.5 Flash ⚡️ Normally, Gemini 3.5 Flash is 4x faster than other models with frontier performance. For a limited time, Antigravity is serving it 12x faster thanks to custom inference tricks, delivering incredible speed for your workflows. 🚀 See the performance in this demo: generating pixel art from photos, orchestrating multi-agent workflows to write and register sprites, and spawning browser subagents to auto-test rendering: 👇

Google Antigravity

131,891 次观看 • 2 个月前

introducing Gemini 3.6 Flash: our latest model that balances speed with intelligence to deliver strong performance in agentic and multimodal tasks built directly on developer and customer feedback from 3.5 Flash available now in AI Studio and the Gemini API

introducing Gemini 3.6 Flash: our latest model that balances speed with intelligence to deliver strong performance in agentic and multimodal tasks built directly on developer and customer feedback from 3.5 Flash available now in AI Studio and the Gemini API

Google AI Studio

128,673 次观看 • 6 天前

🚨 Someone just built a Claude Code skill that clones any website perfectly in one prompt. It uses the built-in Chrome MCP to go straight to the source. It pulls the exact fonts, colors, and layout directly from the browser. 100% Open Source.

🚨 Someone just built a Claude Code skill that clones any website perfectly in one prompt. It uses the built-in Chrome MCP to go straight to the source. It pulls the exact fonts, colors, and layout directly from the browser. 100% Open Source.

Oliver Prompts

473,522 次观看 • 3 个月前

Bolt built this entire landing page from a single prompt 🤯 No Figma. No coding. Just one prompt and a clear flow Want the exact prompt I used? RT and follow. I’ll DM you the link directly.

Bolt built this entire landing page from a single prompt 🤯 No Figma. No coding. Just one prompt and a clear flow Want the exact prompt I used? RT and follow. I’ll DM you the link directly.

Prajwal Tomar

63,462 次观看 • 1 年前

Google just launched a killer new product for kids (and their parents!) You can now ask Gemini to "create a storybook" from a prompt - and even add photos and drawings. It generates a beautiful, interactive story, which Gemini can read aloud 🤯

Google just launched a killer new product for kids (and their parents!) You can now ask Gemini to "create a storybook" from a prompt - and even add photos and drawings. It generates a beautiful, interactive story, which Gemini can read aloud 🤯

Olivia Moore

498,288 次观看 • 11 个月前

"One reason many women aren’t married is that they aren’t wife material—just as some men aren’t husband material. There’s a difference between being a woman and being a wife, just as there’s a difference between being a man and being a husband or even a father." – Archbishop Nicholas Duncan-Williams #TV3NewDay #TV3GH

"One reason many women aren’t married is that they aren’t wife material—just as some men aren’t husband material. There’s a difference between being a woman and being a wife, just as there’s a difference between being a man and being a husband or even a father." – Archbishop Nicholas Duncan-Williams #TV3NewDay #TV3GH

#TV3GH

31,325 次观看 • 6 个月前

Introducing Architect I am releasing the first iteration of a model which generates optimized project plans with a single prompt. Think Linear or JIRA, but for agents. A living model that learns from the gossiping network, and gets smarter with every interaction.

Introducing Architect I am releasing the first iteration of a model which generates optimized project plans with a single prompt. Think Linear or JIRA, but for agents. A living model that learns from the gossiping network, and gets smarter with every interaction.

Varun

56,906 次观看 • 4 个月前