分类筛选
找到 1116 个 Demo
Next-Gen AI is here: Gemini 3.1 Pro dominates reas...
Next-Gen AI is here: Gemini 3.1 Pro dominates reasoning and technical benchmarks. #Gemini3 #AIInnovation #SOTAModel #GoogleGemini https://t.co/t7BLpiDOjn
Congrats to Talki, the Google Gemini track winner...
Congrats to Talki, the Google Gemini track winner of the @lovable AI Showdown hackathon 🎉 Their language learning app integrates both chat and voice. Over 1,000 projects built with Gemini were submitted, highlighting all the incredible work from our dev community!
⚡ We got early access to Gemini 3.1 Pro and built...
⚡ We got early access to Gemini 3.1 Pro and built 12 guided cookbooks that take you from zero to production-ready multi-agent systems. Here's what the progression looks like 🧵
Feeling like reading some short #SciFi story in yo...
Feeling like reading some short #SciFi story in your daily routine? I got you covered with this site: https://t.co/ND9b2M4Zgs Stories are generated by an agent built with #Gemini, #Imagen, and @langchain4j. https://t.co/VCYk8kkQY7
This is my third app built with Gemini 2.0 Flash I...
This is my third app built with Gemini 2.0 Flash Image Generation Experimental The image context step is applied to the sketch… then Gemini draws in the styles prompted The process is frictionless, quick and surprisingly accurate
Gemini 3.1 Pro is live on Poe — Google’s newest Ge...
Gemini 3.1 Pro is live on Poe — Google’s newest Gemini model built to solve your hardest challenges: deep reasoning, synthesis, and complex problem solving. We got early access to a private snapshot and co-developed a custom benchmark to help shape this model with our partners at Google DeepMind. Try it now in the Poe app on all platforms and in the Poe API: https://t.co/PAQoO54FD5
Gemini 3.1 Flash-Lite is here >Most cost-effic...
Gemini 3.1 Flash-Lite is here >Most cost-efficient Gemini 3 model yet >Faster + cheaper than 2.5 Flash >Costs $0.25 per 1M input tokens >Built for agents, high-volume work, UI dashboards & simulations https://t.co/2e51D2oGY2
Google is working on a new model selector for the...
Google is working on a new model selector for the Build section on AI Studio. Currently, all apps are built with Gemini 2.5 Pro, so soon, we will likely see more options over there. Moar Gemini models 👀 https://t.co/d6JqeZWjzv
More progress on my positive-thinking app – Smooth...
More progress on my positive-thinking app – Smoother mesh animations for the “thinking” state – Simplified glass effects – Added model-selection option – No luck using Apple Intelligence. It seems to not be possible. I’ll tweak the algorithm next. Built with Gemini Deep Research, now I will iterate with GPT-5.
Six months ago, building a real-time multiplayer a...
Six months ago, building a real-time multiplayer app required a full engineering team. Last week, someone built one inside Google AI Studio. Alone. In under an hour. That's not an exaggeration. That's the Antigravity update. Here's what changed: → Server-side generation means your work never disappears → Multiplayer apps are now buildable without complex infrastructure → Firebase is built in login systems, databases, all of it → AI agents work in parallel like a dev team running simultaneously → You direct. They build. The gap between "idea" and "working product" just got a lot smaller. Save this video, you'll thank yourself when you start your next project. 🚀
Duolingo, meet your AI-powered challenger: TalkMe...
Duolingo, meet your AI-powered challenger: TalkMe launches the first-ever brand film built with Gemini, Veo 3, and Flow. Open 🧵
Really awesome spatial interface from built with...
Really awesome spatial interface from @poetengineer__ built with Gemini for ideation. 💡🗺️ I think spatial interfaces that let you co-think with AI like this in new ways are really exciting.