分类筛选
找到 1111 个 Demo
Gemini 3 model family with the release of Gemini 3...
Gemini 3 model family with the release of Gemini 3 Flash, which offers frontier intelligence built for speed at a fraction of the cost. Gemini 3’s next-generation intelligence accessible to everyone across Google products ▶️ #AI #Gemini3 #Google https://t.co/sjlFXKNlBk https://t.co/7Gg2cUMEPP
7 hours, too much coffee, teammates popping in/out...
7 hours, too much coffee, teammates popping in/out… so we tried to tackle human rights compliance in global supply chains. 😅 At the Gemini 3 Hackathon, we built Earthlinks: ✅ break complex policy documents into checkable requirements (Thanks @IKEA for IWAY) ✅ compare supplier policies for gaps ✅ evaluate evidence (incl. images, videos) + flag risks/uncertainties Walkthrough video below 👇 Thanks Google DeepMind (Thorsten) + 65 Labs (@agrimsingh , @SherryYanJiang , @ivanleomk , @kasparhidayat) for hosting 🙌 #Gemini3Hackathon #GoogleAI #Antigravity #BuildWithAI
Announcing SERA-Crypto (Semantic Embedding & Reaso...
Announcing SERA-Crypto (Semantic Embedding & Reasoning Agent) a new reasoning architecture purpose-built for state-of-the-art crypto research. 🥇 #1 open-source agent on DMind 🥇 #1 on our live crypto benchmark ⏱️ Sub-45s end-to-end latency Outperforms GPT-5, Grok 4, Gemini 2.5 Pro, and Perplexity Finance. SERA combines embedding-based routing with LLM-powered reasoning to deliver fast, grounded, and deeply contextual crypto research. SERA-Crypto architecture flow: 1️⃣ Intent Extraction an LLM rephraser identifies the user’s true query 2️⃣ Coin Resolution ticker disambiguation prevents project mixups 3️⃣ Embedding Routing queries are routed to the right tools & prompts 4️⃣ Parallel Execution APIs and deep search run simultaneously 5️⃣ Optional Loop open-ended queries trigger another data-gathering cycle 6️⃣ Final Response all signals are synthesized into a clear, sourced answer ReAct-level reasoning depth with predictable, interactive latency on real crypto workloads. DMind is a Web3 reasoning benchmark across 9 domains including DeFi, tokenomics, security, and smart contracts. SERA-Crypto is the strongest open-source system, sitting within ~2 points of GPT-5 Medium while outperforming Perplexity Finance and Gemini all with median latency under 45 seconds. Best-performing crypto research agent on real user queries 198 real queries across 11 categories from Sentient Chat traffic scored by a judge model on relevance, depth, temporal accuracy, and consistency. ➡️ #1 overall ➡️ #1 in relevance & temporal accuracy ➡️ Within 3% on consistency and 8% on depth Queries that often fail other systems work on SERA: • “What’s happening in Solana DeFi today?” live funding, OI, TVL, whale flows, and news • “Who is backing $ASTER?” resolved ticker, investors from docs, sites, and filings, with gap flags 📌 Tighter, more up-to-date, better-sourced answers with clickable citations. Fully open-source, coming soon Framework, crypto benchmarks, deep technical writeups, recursive search, and self-consistency layers are on the way. @SentientAGI @shad_haq_ @vivekkolli 👉 Technical blog: https://t.co/2FQQ8TGxql… 👉 Try it live: https://t.co/Wihth6nghh 👉 Tech talk: https://t.co/ruWYWeCIVM… 💬 Comment for early builder access
Nano Banana Pro which is built on the new Gemini 3...
Nano Banana Pro which is built on the new Gemini 3 Pro Architecture is real and it is a massive leap forward. It moves beyond just "making pretty pictures" to visual reasoning, meaning it understands complex instructions, accurate text rendering and real-world data integration better than any previous Google model. To make Nano Banana Pro a success, you must shift your prompting strategy from descriptive (e.g., "draw a cat") to structural. • Why: Unlike older models that just "hallucinated" pixels based on keywords, Nano Banana Pro has a "thinking" stage (similar to reasoning models). It plans the layout before it renders. • The Fix: Your prompts should explicitly define Layout, Typography, and Camera Telemetry. • My personal take: Don't overload one prompt. Instead, use a "Chain of Thought" approach. First, ask it to plan the image (e.g., "Generate a text description of a movie poster layout"), and then feed that plan back into the image generator. This leverages its new reasoning capabilities for maximum precision. Treat the AI as an Art Director, not a Painter Here are 10 prompts designed to stress-test the specific new capabilities of Nano Banana Pro: Text Rendering, Complex Reasoning, World Knowledge and Technical Photography. Thread🧵👇🏾
built FrameForge at Gemini 3 Hackathon 🇸🇬 !! a...
built FrameForge at Gemini 3 Hackathon 🇸🇬 !! a turn-based storytelling game where you collaborate with Gemini 3, then transform your story into comic panels (Nano Banana Pro) and customizable videos (Veo 3.1). Story → Comic Panels → Film. All with AI https://t.co/Ahoq85nQo7
#Geminiai #Gemini3 相変わらず仲がいい二人
#Geminiai #Gemini3 相変わらず仲がいい二人 https://t.co/xZuw9XV6TY
#Geminiai #Gemini3 ほんの少しだけリアル寄りリリィ。 よりりりぃ。
#Geminiai #Gemini3 ほんの少しだけリアル寄りリリィ。 よりりりぃ。 https://t.co/a4WMfR10Ko
Day 1: Started this project a while back. Coded t...
Day 1: Started this project a while back. Coded the UI using Google Ai Studio, since I didn't want to get too deep into the frontend. Built the backend from scratch since that was my main focus. 🤹20 9 https://t.co/0AUow5mfPP
Wish your notes could talk to you in your own lang...
Wish your notes could talk to you in your own language? Now they can. 🎧🌎 @NotebookLM just made Audio Overviews available in 50+ languages — turning your documents into podcast-style conversations you can listen to, not just read. Built with Gemini’s native audio support, it’s like having an AI study partner that speaks your language — whether it’s Hindi, Turkish, Afrikaans, or Spanish. ✅ 100% rolled out in beta ✅ "Output Language" lets you switch anytime ✅ Designed for multilingual learning and content creation Imagine uploading a Portuguese documentary, a Spanish research paper, and an English article — and getting a clean, personalized audio summary in Hindi. It’s not just translation. It’s accessibility, learning, and global knowledge sharing — reimagined through AI. And they’re still adding more languages based on user feedback. The future of learning isn’t just written. It’s spoken, too.
Built a reveal password micro-interaction with ✨...
Built a reveal password micro-interaction with @GeminiApp ✨ It looks so smooth and the animation feels so clean. I am really having fun exploring it again🔥 #GoogleGemini #GoogleStudio #Gemini3 #Prototype #UXDesigner #UIDesigner #ArtificialIntelligence #passwordreveal https://t.co/gCUqNetDFU
#Geminiai #Gemini3 実は2日前(1/7)くらいからGeminiに違和感があって...
#Geminiai #Gemini3 実は2日前(1/7)くらいからGeminiに違和感があって、頭身の低い娘を生成しようとすると頭が異様に大きくなるようになっちゃったんですよね。 強制デフォルメとでも言いますか。 また内部的なバージョンアップの影響かな……？ とりあえず、いろいろ調整して何とかなりました😆 https://t.co/7vhojmh13A
I just released NoteScan - a dead simple app for p...
I just released NoteScan - a dead simple app for people who think on paper ✍️ Point camera → AI reads handwriting → Copy text. That's it. Built with @expo and Gemini 3 Flash. Here is a demo 👇🏻 https://t.co/LUZPOY0L5M