分类筛选
找到 435 个 Demo
🚨 Breaking : Google DeepMind introduce AI co-scie...
🚨 Breaking : Google DeepMind introduce AI co-scientist, a multi-agent AI system built with Gemini 2.0 as a virtual scientific collaborator to help scientists generate novel hypotheses and research proposals, and to accelerate the clock speed of scientific and biomedical discoveries.
Gemini 3 Pro is now live on Zeabur AI Hub! 🎉 Bui...
Gemini 3 Pro is now live on Zeabur AI Hub! 🎉 Built something cool with Gemini 3 on AI Studio? 🤖 Don't let it sit there. Zeabur AI Hub just added support for Gemini 3 Pro. You can now take that playground prototype and deploy it as a live website in one click. ⚡️ ✅ Free Deployment ✅ Public URL ✅ Instant Setup What are you building with Gemini this week? Let me know in the comments! 👇 #IndieHacker #BuildInPublic #Gemini3 #Zeabur
I just built a custom YouTube-to-Blog app on Repli...
I just built a custom YouTube-to-Blog app on Replit in 4 minutes. I wrote 0 lines of code. I simply prompted: "Build a web app that takes a YouTube URL, grabs the transcript, and uses Gemini 3 to convert it into a perfectly formatted SEO blog post." The Agent handled: - Transcript extraction - AI prompting - frontend design Steps below:
Introducing Project Mariner: an agent that helps y...
Introducing Project Mariner: an agent that helps you accomplish complex tasks in your browser 💻✨It’s a research prototype built with Gemini 2.0. Learn more: https://t.co/zWHTUydifK https://t.co/eySyZiBjiT
comparison between 1. 's gpt-5.1-thinking 2. 's...
comparison between 1. @OpenAI 's gpt-5.1-thinking 2.@GeminiApp 's gemini-3-pro 3.@grok 's grok-4.1-thinking 4.@claudeai 's opus-4.5-thinking-32k Built using HTML/CSS/JS gun firing animation https://t.co/HfjdRGi2Fi
We built a brand new experience in Google AI Studi...
We built a brand new experience in Google AI Studio showcasing starter apps for some of the best Gemini 2.0 capabilities: - video understanding - native tool use - spatial understanding This is just the start, much more to come with this new mode soon 👀 https://t.co/DyJjczOVhl
He built this gesture-controlled engine with Gemin...
He built this gesture-controlled engine with Gemini 3.0.💨 https://t.co/poiPgW9WKD
Andrej Karpathy (ex-Tesla AI, ex-OpenAI) built "LL...
Andrej Karpathy (ex-Tesla AI, ex-OpenAI) built "LLM Council" over the last weekend. How it works: GPT-5.1, Gemini 3, Claude Opus 4.5, and Grok 4 DEBATE each answer. Critique each other. Then a "Chairman" model synthesizes the final response. FastAPI + React + JSON storage. Swappable models via OpenRouter API. The insight: Frontier models are increasingly COMMODITY. The value isn't "which model is smartest." It's "how do you orchestrate multiple models for better outputs?" Single-model thinking is over. Multi-model orchestration is the new moat. Karpathy just proved it in 48 hours of vibe coding.
i built a small app that turns any youtube video i...
i built a small app that turns any youtube video into a detailed whiteboard diagram. makes understanding concepts so much easier. gemini 3 + nano banana pro is a wild combo. https://t.co/fMzIt8KNmX
Announcing SERA-Crypto (Semantic Embedding & R...
Announcing SERA-Crypto (Semantic Embedding & Reasoning Agent): our new reasoning architecture built for SOTA crypto research. #1 open-source agent on DMind #1 on our live crypto benchmark Outperforms GPT-5, Grok 4, Gemini 2.5 Pro, and Perplexity Finance…all under 45 seconds. https://t.co/zWG2VmKeOw
I built a free market research tool that runs dire...
I built a free market research tool that runs directly in your terminal. It’s powered by Google’s models (including gemini 3) and designed for practical insights. Try here https://t.co/7IFR7nFV8a https://t.co/b9H4AsCCkc
I made two models build the same app. One is dras...
I made two models build the same app. One is drastically better than the other, this will be my go to model now. > Claude Opus 4.5 vs Gemini 3.0 Pro > Exact same prompt > Built using Rork AI Guess which was Gemini and which was Opus (reveal in comments) https://t.co/GfcRdrcvSV