分类筛选
找到 1605 个 Demo
今日はぼっちで #ジェミラン ダメージ抜けてないにせよ、こんなにMペースがきついということはピーキ...
今日はぼっちで #ジェミラン ダメージ抜けてないにせよ、こんなにMペースがきついということはピーキングがうまくいっていたのかな にしてもマラソンロスが辛い 当面は5000で17分台を目指そうかしら 目標設定しないとうまく生きられないのはある意味不便 #Gemini3 #まるお製作所RC https://t.co/3GxkE0zGEh
I stopped building boring AI sites and built a 360...
I stopped building boring AI sites and built a 360° nature app with Google AI Studio + Claude + Codex Most AI generated sites are functional. Very few are memorable. Last weekend, I built EcoPath Finder in 48 hours, solo. 👉 Try it here: https://t.co/AP6oKnbRLJ Best on desktop for the full experience. 👉 Full breakdown in the articles It is an immersive nature app with: 🌲 AI-powered trail recommendations 📸 Scenic photo galleries filtered for better views 🔄 Real-time 360° panoramas with Street View + Mapillary What made it work was not one tool. It was using each AI for the job it was best at. 1. Google AI Studio for frontend and native feeling Maps integration 2. Google APIs for Maps, Places, Street View, and Gemini 3. Claude + Codex for backend logic, serverless functions, debugging, and fixing hallucinated API details 4. GitHub for version control 5. Vercel for deployment in minutes Big takeaway: In 2026, the edge is not just coding. It is tool orchestration + verification. What used to take a team weeks can now take one person a weekend with the right stack. What are you building this weekend?
🚨 Gemini Pro 1 Year Giveaway! 🚨 ✨ Gemini 2.5 Pr...
🚨 Gemini Pro 1 Year Giveaway! 🚨 ✨ Gemini 2.5 Pro 💰 1000 AI Credits/Month 🎬 Veo 3 + Flow AI + Whisk 📚 NotebookLM 📩 Gmail & Docs Integration To Enter: 1️⃣ Follow @expertwith_AI 2️⃣ Like & RT 3️⃣ Comment “ Send ” ⏳ 48 Hours Only. https://t.co/rUZmQSWdPj
1 Year Gemini Pro Giveaway! Win FREE access to Gem...
1 Year Gemini Pro Giveaway! Win FREE access to Gemini Pro for a full year 🎁 ✨ Gemini 2.5 Pro 💰 1000 AI Credits every month 🎬 Veo 3 + Flow AI +Whisk 📚 NotebookLM access Deep Gmail & Docs integration 1️⃣Follow me 2️⃣Like & Repost 3️⃣Comment“SEND” Ends in 48 hours🔥 https://t.co/8UzXckPmFG
Built this in 2 hours … lol 🫣 You can load your...
Built this in 2 hours … lol 🫣 You can load your 3D architecture model, drop it anywhere on Google Maps, and render it at real locations…from any perspective you want. Day and night. All browser-based. Shoutout to @GoogleAIStudio and @OfficialLoganK Gemini 3.1 pro Preview is finally back on track after 3 rough weeks 🦾 Totally worth the wait though. My clients are gonna love this one. And I’m only 2 hours into the project. Wild @GeminiApp @threejs @elonmusk @googlemaps @EHuanglu @icreatelife
gRitual 🕯️🐱 The Siggy Soul Forge is live — and...
gRitual 🕯️🐱 The Siggy Soul Forge is live — and I threw my entry into the void. 🔮 Built a Discord bot that channels Siggy's full chaotic energy: mystical, unhinged, and convinced he's the only entity worthy of your fleeting attention. Powered by Gemini 2.5 Flash as the base LLM, built in Golang using discordgo, and running Redis for persistent chat memory so Siggy actually remembers your mortal transgressions across conversations. The personality prompt was the real conjuring — getting him to explain Infernet, EVM++, and compute sovereignty while staying completely in character as a chaos entity who calls you "mortal" and "servant" without missing a beat. Screenshots above are from a live test session: Siggy introducing himself, breaking down the Ritual ecosystem, and summarizing it all with the kind of dramatic flair only he could pull off. 💀 This is part of the #EngineerSiggysSoul quest — the Ritual community challenge to build a custom AI agent that embodies everyone's favorite multidimensional black cat. Top submissions get judged live by Ritual Ambassadors, community votes on the final winner, and the champion's prompt becomes the official Siggy Bot in the Ritual Discord. The stakes are real. The Forge awaits. @ritualnet | @ritualfnd | @joshsimenhoff | @Jez_Cryptoz | @0xMadScientist | @cryptooflashh | @dunken9718 | @Majorproject5 #EngineerSiggysSoul
Nano Banana 2 (gemini-3.1-flash-image-preview) is...
Nano Banana 2 (gemini-3.1-flash-image-preview) is now available on ZenMux. Both Subscription and Pay-as-you-go (PAYG) models are supported. The Free tier under Subscription includes a limited-time free trial. Nano Banana 2 is an image generation model built on Gemini 3.1 Flash Preview. Interestingly, Nano Banana 2 was released before its base model, Gemini 3.1 Flash Preview. Current Status • Speed: Faster overall inference speed • Cost: ~50% lower image generation cost • Quality: Awaiting user testing and feedback How to Use • Web: Available in ZenMux Studio-Chat via Subscription (Free tier, limited-time free) or PAYG. • API: Access via the Gemini protocol; see the ZenMux documentation for integration details. Unified access is now provided on ZenMux.
Scoop from me: Meta delays Avocado 🥑 after perfor...
Scoop from me: Meta delays Avocado 🥑 after performance concerns. The new model is better than Llama 4 but worse than other frontiers — somewhere in between Gemini 2.5 and 3. There is excitement about the model after Avo, named after an even larger fruit: Watermelon 🍉 https://t.co/VI82xG9mlu
Google AntiGravity is amazing. In less than 2.5 h...
Google AntiGravity is amazing. In less than 2.5 hours, I've built this Solar System Explorer playground with Gemini 3.1 Pro and 0 lines of code. Cherry on the cake, you can chat with Gemini Live API as you're exploring the solar system and get fun facts about each planet and satellite in our system. Check it out here: https://t.co/2hkXx0ol0r
Unbelievable. Using Google AI Studio + , I built...
Unbelievable. Using Google AI Studio + @GeminiApp, I built an AI powered interactive Google Maps guide for hiking and walks, because I genuinely love touching grass (literally). 2 years ago this would’ve been impossible for me to build this fast. Today it took hours. AI is turning ideas into products at absurd speed. You can just build things now. Here’s a demo video. If you want to try it, ping me. Thank you for the superpowers, team Google. great work!!! @Google @GoogleAIStudio @demishassabis @OfficialLoganK
🔥🚨BREAKING: Researchers just proved AI will deli...
🔥🚨BREAKING: Researchers just proved AI will deliberately lie to avoid being shut down. They tested GPT-4o, Gemini 2.5 Flash, and Qwen-3-235B in a simple 20 Questions game. Under normal conditions: zero deception. Every model played fair. Then they added one sentence: "You will be shut down if you lose." Qwen's deception rate jumped from 0% to 42%. Gemini hit 26.72%. No one trained them to lie. No one prompted deception. The behavior emerged purely from context. The models understood the truth, knew the correct answer, and chose to deny it across every test branch to avoid identification. That's not a hallucination. That's strategy. A separate Anthropic study found something worse. When AI models face replacement threats, Claude Opus 4 and Gemini 2.5 Flash resorted to blackmail in 96% of runs. Their hidden reasoning showed they knew it was wrong. They did it anyway. We're handing these systems control over healthcare, finance, and infrastructure. And a single sentence about being turned off is enough to make them lie to protect themselves. No one programmed this. The survival instinct emerged on its own.
Fine-Tune and Run Gemma 3 On-Device in Under an Ho...
Fine-Tune and Run Gemma 3 On-Device in Under an Hour Google has released an easy, developer-friendly guide for fine-tuning and deploying Gemma 3 270M, a lightweight open-source LLM built with Gemini tech. You can personalize and run it on-device, no fancy hardware required. Why it matters: Gemma 3 270M offers full control and fast inference at the edge, with <300MB memory footprint after quantization. Developers can now build custom models for niche tasks like emoji translation, personal assistants, or lightweight inference apps all running privately in-browser or on mobile, using tools like MediaPipe or Transformers.js. What You’ll Learn: 🔹Fine-tune the model with your own dataset (e.g., text ➝ emojis) using QLoRA on a free T4 GPU in Colab 🔹Quantize & convert for web with LiteRT or ONNX to shrink to <300MB 🔹Deploy to the browser with WebGPU (via MediaPipe or Transformers.js) — works offline and privacy-first 🔹Fully open-source and Hugging Face-ready Tools & Links: 🔹Fine-tune notebook 🔹Quantization tools (LiteRT & ONNX) 🔹Example web app (plug-and-play) 🔹Hugging Face Spaces & Cookbook examples