分类筛选
找到 1098 个 Demo
🔥 Developers… it’s happening. Gemini 3 just buil...
🔥 Developers… it’s happening. Gemini 3 just built a full interactive 3D website for me in minutes. No plugins. No boilerplate. Just plain text prompts → production-ready code. It even lets you move millions of particles with your hands and reshape them in real-time. Full prompts + tutorial below ⬇️
Built a stunning, real-time 3D V8 Engine simulatio...
Built a stunning, real-time 3D V8 Engine simulation completely with #Gemini3. The model accurately uses Geometry of the Engine and the Kinematics behind it ,to drive the piston and crankshaft motion. Implemented using ThreeJS. https://t.co/LswlNRXlcY
Announcing SERA-Crypto, a new reasoning architectu...
Announcing SERA-Crypto, a new reasoning architecture built from the ground up for state-of-the-art crypto research. SERA-Crypto is the #1 open-source agent on DMind and leads our live crypto benchmark, outperforming GPT-5, Grok 4, Gemini 2.5 Pro, and Perplexity Finance on real user queries, all while keeping end-to-end latency under 45 seconds. SERA works by extracting true user intent, resolving ambiguous tickers, routing queries via semantic embeddings, and executing APIs and deep search in parallel. For open-ended questions, it loops intelligently before synthesizing a final, grounded response with sources. The result is ReAct-level reasoning depth with predictable performance on live Web3 data across DeFi, tokenomics, security, and smart contracts. Built for production crypto research, not demos. The full SERA framework, benchmarks, and technical deep dive will be open-sourced soon. @SentientAGI
🔥 Developers… it’s happening. Gemini 3 just buil...
🔥 Developers… it’s happening. Gemini 3 just built a full interactive 3D website for me in minutes. No plugins. No boilerplate. Just plain text prompts → production-ready code. It even lets you move millions of particles with your hands and reshape them in real-time. Full prompts + tutorial below ⬇️ Follow @Suryanshti777 for more exclusive content
「すでに幽霊が映っているから心霊写真にできません」 #Gemini3 怪談。
「すでに幽霊が映っているから心霊写真にできません」 #Gemini3 怪談。 https://t.co/JsKCJq76lw
An experiment where I translated an entire Blender...
An experiment where I translated an entire Blender scene into Three.js using Gemini 3.0. I shared two images. Can you tell which one is which? One shows the environment built in Blender. The other is that same scene running live in the browser with Three.js. AI is helping bridge that gap faster than ever, turning 3D ideas into real, interactive web experiences without killing creative intent.
A easy combo manager built on gemini 3
A easy combo manager built on gemini 3 https://t.co/X9kXvkpeX0
Just tested Gemini 3… and this is insane. I liter...
Just tested Gemini 3… and this is insane. I literally typed a few sentences and it built a full 3D interactive website in minutes with hand-gesture control using my camera, real-time particles, templates, colours… the works. No coding. No setup. Just text → fully working experience. AI is moving way too fast. 🤯🔥
HeyHo!!! It's coding time. Saturday with a bunch o...
HeyHo!!! It's coding time. Saturday with a bunch of hackers at @agihouse_org , building with @GoogleDeepMind Gemini 3. Google just shipped some crazy stuff! Gemini 3, Nano Banana 2, Antigravity (their new agentic IDE), and Deep Research built on Gemini 3 Pro. It's the first model to break 1500 Elo on LMArena. 1M token context. 31% on ARC-AGI-2. The game is afoot! Let's code!
Gemini 3 Pro built this app that automate all comm...
Gemini 3 Pro built this app that automate all community engagement for creators and streamers in just 30 minutes 🤯 - Fully functional UI - Built -in memory layer - Multi-agents workflows to keep communities engaged across socials https://t.co/izuHRHJOrz
i built an open world minigame that's controlled w...
i built an open world minigame that's controlled with hand movements only here's a step-by-step tutorial: > started with my mediapipe + threejs template (see QT) > added a 3D model made by quaternius > sent a few prompts to gemini 3... --- prompt #1: repurpose the attached script, but now I want to import a gltf model (assets/model.gltf) and use that in the scene instead of the cube when the user moves their hand, a waypoint indicator should move around the scene, and the 3D model should smoothly move there when the user makes a fist, the model should jump the 3D model contains bundled animations in it. use the "idle", "run", and "jump" animations --- prompt #2: make this a procedural open world adventure. generate very simple procedural voxel terrain when the model gets near the edges of the screen, the camera should move, allowing the model to keep going in that direction --- prompt #3: add some floating glowing gems around the map that the user can collect --- i made some manual tweaks for styling and game feel, but that's the gist of it thanks for reading if you got all the way here full code is available at my link in bio
#Gemini3 #GeminiAI 深夜のノリで画像生成するのやめたい……！
#Gemini3 #GeminiAI 深夜のノリで画像生成するのやめたい……！ https://t.co/z7KgbJgXHW