分类筛选
找到 1096 个 Demo
今日は、#Gemini3 メニューの自主練 坂ダッシュ30m×20 にテンポ6000（4’50→4...
今日は、#Gemini3 メニューの自主練 坂ダッシュ30m×20 にテンポ6000（4’50→4’15）を接続 坂ダッシュは公園横で実施したが、子ども連れ家族で溢れかえる中、私のダッシュは異彩を放っていて、少し怖かったかも知れない ごめんなさい #まるお製作所RC https://t.co/K6LNZHcNw1
4/17（金）40分ジョグ 🗒️8.41km 🔧Free 👟ヴェロシティニトロ4 明日の50...
4/17（金）40分ジョグ 🗒️8.41km 🔧Free 👟ヴェロシティニトロ4 明日の5000mレースに向け調整練 明日は社会人初の5000mなので、記録も狙いたいが、まずは現状どれくらい走れるのかを知るところから #Gemini3 #まるお製作所RC https://t.co/BJIzEBYLEM
Built most of the landing page with Pi + Gemini 3...
Built most of the https://t.co/Ln7RxsfKG1 landing page with Pi + Gemini 3.1 Pro (no Claude, no Codex). It turned on iOS Simulator and Android emulator, took screenshots, adorned them in device outlines, made them 3D-ish, and created the entire hero banner https://t.co/Fo2IehHXB4
Google releases Gemma 4, a family of open models b...
Google releases Gemma 4, a family of open models built off of Gemini 3 https://t.co/q70LQNDYaA
🚨 GOOGLE JUST DROPPED GEMMA 4🔥 Their most inte...
🚨 GOOGLE JUST DROPPED GEMMA 4🔥 Their most intelligent open models ever, built from the same research as Gemini 3. Fully runnable on YOUR hardware. No API tax. No restrictions. Here’s why this is massive: • 4 versatile sizes (2B to 128B) → runs on laptop OR beast rig • 256K context window (insane memory) • Offline high-quality code generation • Multimodal (text + image) • Commercially permissive Apache 2.0 license → build, fine-tune, sell, deploy anywhere.
built a daily show from today's news. 🧠 opus 4.7...
built a daily show from today's news. 🧠 opus 4.7 — plan and writes the jokes 🎙️ gemini 3.1 flash tts — performs them 🛠️ CREAO — glues it all together 📦 …then turns the whole flow into a reusable agent i can schedule every morning https://t.co/2orUh4kYKf https://t.co/sA52eoqdwb
🚨 google just dropped a free AI model that runs o...
🚨 google just dropped a free AI model that runs on your phone and beats models costing $200/month. fits in 3GB. handles text, images, and audio. 256k context. 140+ languages. built from the same research as Gemini 3. and they gave it away for free. the open source AI race just changed forever.
I beat Polymarket using free AI models No subscri...
I beat Polymarket using free AI models No subscriptions. No API bills. Zero cost. GitHub Copilot Pro - free first month Inside: Claude Opus 4.6. Gemini 3.1 Pro. GPT-5.4 Cancel before it charges, keep the models I built a BTC 15-min market bot on Polymarket Fed it live Binance data Claude wrote the logic, I just ran it Limits running out? OmniRoute switches accounts automatically GitHub accounts. One dashboard. Infinite runway. Most people pay $200/month for this I paid nothing Are you still paying for tools you could get for free?
Self-improving agent skills built with Google Agen...
Self-improving agent skills built with Google Agent Development Kit and Gemini 3. This multi-agent system that takes any agent skill, runs it against test scenarios, diagnoses failures, and fixes itself. 100% Opensource. https://t.co/7IZZNBUvfW
Google AI Studio built this entire dashboard in on...
Google AI Studio built this entire dashboard in one shot. Interactive charts, globe included. This is kind of insane. @flavioAd https://t.co/ucpq6fIQIv
毎週水曜日の #Gemini3 練習会 メニュー： 1800m × 7 interval（設定：04...
毎週水曜日の #Gemini3 練習会 メニュー： 1800m × 7 interval（設定：04:00 → 03:40 / km build up、rest：60〜80 sec） 一応、設定はある程度こなせたのかも？ 先週末レースだったことを考えれば、まぁ、最低限の走りは出来たのかな 走る前は厳しいかな、とも思っていたけど意外となんとかなった感じ なんだったら走った直後はむしろ身体が良い感じにリフレッシュした感があった もっと水準を切り上げ、それを楽に走れるようになりたい💪 #まるお製作所RC
We’ve seen some impressive use cases built in Goog...
We’ve seen some impressive use cases built in Google AI Studio. Here are a few of them 🧵