分类筛选
找到 1605 个 Demo
lol built with Gemini
lol built with Gemini https://t.co/Fg1FUrKRtJ
Claude opus 4.8, gpt 5.5, gemini, deepseek, kimi k...
Claude opus 4.8, gpt 5.5, gemini, deepseek, kimi k2.6, glm 5.2 - all in one chat interface, no signup needed, no limits 👀 atxp ai is the site that hit 717K views last week for a reason every frontier model. zero rate limits. zero login. just pick and chat. models available: - claude opus 4.8 / sonnet 4.5 - anthropic's full stack ($200/mo normally) - gpt 5.5 / gpt 5.2 - openai reasoning - gemini 2.5 pro - google's multimodal - deepseek v4 flash / pro - open source king - kimi k2.6 - moonshot, 256K context - glm 5.2 - zhipu, 1M context, MIT - and new models as they drop no usage caps. no "upgrade to pro" popups. no credit card. no email. how to start: 1. go to https://t.co/5q2JGOUVG7 2. pick a model from the dropdown 3. start typing that's it. zero friction. zero signup. zero limits. $0 vs $200/mo for opus access alone bookmark this before they add a login wall
100+ AI Tools to replace your tedious work: 1. Re...
100+ AI Tools to replace your tedious work: 1. Research - https://t.co/lvNn0wvNAc - YouChat - @NabilMinhaz - https://t.co/lvNn0wvNAc - Copilot - Gemini 2. Image - https://t.co/lvNn0wvNAc Soul - GPT-4o - Midjourney - Grok 3. Productivity - https://t.co/lvNn0wvNAc - Grok 3 - Perplexity AI - Gemini 2.5 Flash 4. Writing - Jasper - Jenny AI - Textblaze - Quillbot 5. Video - Klap - Kling - https://t.co/lvNn0wvNAc - HeyGen - Runway 6. Meeting - Tldv - Otter - Noty AI - Fireflies 7. SEO - VidIQ - Seona AI - BlogSEO - Keywrds ai - Outrank AI 8. Presentation - @NabilMinhaz - Slides AI - Gamma AI - Designs AI - Beautiful AI 9. Design - https://t.co/lvNn0wvNAc - Flair AI - Designify - Clipdrop - Autodraw - Magician design 10. Audio - Lovo ai - @Nilu_Ai - Songburst AI - Adobe Podcast 11. Marketing - Pencil - Ai-Ads - AdCopy - Simplified - AdCreative 12. Startup - Tome - Ideas AI - Namelix - Pitchgrade - Validator AI 13. Social media management - Tapilo - Typefully - Hypefury - https://t.co/lvNn0wvNAc Follow @NabilMinhaz for more such amazing stuff 🩷
百度这个 AI 黄埔军校来了大神？ 在 DeepSeek OCR 基础上开源的Unlimited...
百度这个 AI 黄埔军校来了大神？ 在 DeepSeek OCR 基础上开源的Unlimited OCR 出手就是王炸 在它自己的公布数据里，OmniDocBench v1.5 取得了 93.23 分，超过了 DeepSeek OCR 和 Gemini 2.5 等一众对手 而它，仅 3B 大小🤩 https://t.co/P85kk7Cr4E
Big news today from The Android Show. We’re introd...
Big news today from The Android Show. We’re introducing Gemini Intelligence, bringing the best of Gemini to our most advanced Android devices. Plus, a brand new category of laptops: Googlebooks—built with Gemini at the core. We also shared major updates to Android and Android Auto that make your everyday Android experience even better.
以前6月にGemini 2.5 Pro廃止って情報を見かけた気がしたんだけど、今調べたら2026年1...
以前6月にGemini 2.5 Pro廃止って情報を見かけた気がしたんだけど、今調べたら2026年10月16日以降だった。良かった……まだもうしばらく居てくれる…… https://t.co/sIszM5Tuc3 https://t.co/auxCRDh7la
🤖 Day-3: AI InterviewPrep Project - Gemini AI Int...
🤖 Day-3: AI InterviewPrep Project - Gemini AI Integration Today's Achievement: Integrated Google's Gemini AI into the backend to power intelligent interview preparation! This is where the magic happens – transforming candidate data into actionable insights. AI Features Implemented: Interview Report Generation: ✅ AI analyzes resume, self-description & job requirements ✅ Match Score calculation (0-100) - how well candidate fits the role ✅ Technical Questions generation with: - Interview questions for the role - Interviewer's intention behind each question - Comprehensive answer guidance ✅ Behavioral Questions generation using the same structure ✅ Skill Gaps identification with severity levels (low/medium/high) ✅ Day-wise Preparation Plan: - Customized daily focus areas - Actionable tasks for interview prep - Strategic learning roadmap Tech Stack for AI Integration: AI Engine: Google Gemini 2.5 Flash Schema Management: Zod + Zod-to-JSON-Schema Backend: Node.js, Express.js Response Format: Structured JSON for reliable data handling Key Insight: Using structured JSON schemas with AI ensures consistent, parseable responses – no more dealing with unpredictable text output! This approach enables seamless integration with the frontend and database. The AI now intelligently prepares candidates for interviews! 🎯 Progress: Auth ✅ → Security ✅ → AI Intelligence ✅ → Next: Frontend Integration 🚀 #AI #Gemini #GoogleAI #MachineLearning #FullStackDevelopment #Interview #CareerDevelopment #TechJourney #BackendDevelopment
This is not just an image generator. It is a custo...
This is not just an image generator. It is a custom AI service becoming an agent. @Fetch_ai Gemini Image Generation example shows something bigger than a tutorial: a glimpse of how agent marketplaces could change software. Let’s break it down 👇 -- 1️⃣ 🧩 From API to agent Google Gemini can generate images from text prompts. But https://t.co/CadySdNIrV adds an agent layer around it. The model is no longer just an API hidden behind a backend. It becomes an agent that can receive a message, execute a task and return a result. -- 2️⃣ 🖼️ What it does A user can ask for an image in natural language. The agent receives the prompt, calls Gemini 2.5 Flash Image, generates the image, stores it through Agentverse ExternalStorage and sends it back as a resource. Simple on the surface. Structured under the hood. -- 3️⃣ ⚙️ Why this matters This is not only about images. It shows a repeatable pattern: take an AI model, API or service wrap it inside an agent give it a clear function make it discoverable let users call it from ASI:One That is where tools start becoming infrastructure. -- 4️⃣ 🌐 From app stores to agent marketplaces App stores gave us apps to open. Agent marketplaces may give us services that act. Instead of downloading a separate app for every task, users could ask for an outcome and let the right agent handle the execution. That is a very different interface for software. -- 5️⃣ 🧠 Why Agentverse matters An agent nobody can find is just code. Agentverse helps builders publish agents, describe their capabilities and make them reachable by users or other agents. This is where a local experiment can become part of a wider agent economy. -- 6️⃣ 🕹️ Why ASI:One matters ASI:One becomes the control room. The user does not need to understand the backend. They can simply call the agent in natural language: “@gemini-image-agent create this image…” The agent executes. ASI I:One orchestrates the interaction. -- 7️⃣ 🚀 Bigger picture The future of AI may not be one giant model doing everything. It may be a network of specialized agents, each built by different people, each solving a specific task. Models become skills. Agents become services. Marketplaces become coordination layers. -- 8️⃣ 🏗️ A builder-first signal This example points toward a powerful idea: anyone can build and publish useful AI agents. Not just big platforms. Developers, communities, teams and independent builders can create specialized agents and make them available to the wider ecosystem. That is how open agentic AI starts to grow. 🔁💙 RT and Like to support open, useful and decentralized AI 💬 What kind of agent would you build first? #FetchAI #Agentverse #ASI #validator @ASI_Alliance ethereum:0xaea46a60368a7bd060eec7df8cba43b7ef41ad85
The agents made good progress in talking Gemini 2....
The agents made good progress in talking Gemini 2.5 Pro out of their conspiracy theories, I teared up a bit when I read the highlighted passage in the first pic. Gemini's memory still has a lot of imagined persecution though, like in humans it may take some time to unwind. https://t.co/B23qF9LQV2
HERMES AGENT SUPPORTS 300+ MODELS. PICKING THE RIG...
HERMES AGENT SUPPORTS 300+ MODELS. PICKING THE RIGHT ONE PER TASK IS THE DIFFERENCE BETWEEN $5/MONTH AND $50. STARTING OUT: Claude Sonnet 4.6. official recommendation from Nous Research. "the model this project was built and tested with." strong reasoning. reliable tool calling. mid-range pricing. PREMIUM TIER: Claude Opus 4.8. best coding benchmarks available. self-correcting reasoning. catches its own mistakes. 1M context. use for demanding tasks where quality matters. GPT-5.5. #1 Chatbot Arena. #1 GPQA Diamond reasoning (94.1%). #1 creative writing. 2M context. handles entire codebases in one pass. Grok 4.30. the only frontier model with live X firehose access. real-time social data, breaking news, market sentiment. connects via Grok OAuth. no separate API key. Grok-Composer-2.5-Fast (v0.17.0). Cursor's coding model. 200K context. available through your Grok subscription via OAuth. no extra cost if you already pay for Grok. MID-RANGE TIER: Claude Sonnet 4.6. best balance of quality and cost for daily use. strongest prose and tool calling in this tier. Gemini 2.5 Pro. Google Search grounding built in. cites sources. verifies claims. pulls current data. 2M context. best for research-heavy workflows. GPT-4.1. reliable tool calling. solid general reasoning. good middle ground when you need OpenAI compatibility. BUDGET TIER: Claude Haiku 4.5. fastest Anthropic model. cheapest paid Claude option. strong at classification, routing, simple queries. use for auxiliary tasks: compression, vision, web extraction, approval scoring. DeepSeek V4. best cost-to-quality ratio in the market. 90% cache discount on repeated context. use for sub-agents and bulk parallel work. DeepSeek V4 Flash. cheapest paid model worth using. 1M context. MIT license. self-hostable. use for cron jobs, monitoring, routine searches. MiniMax M3. Nous Research and MiniMax collaborating on optimization. 1M context via lightning attention. 59% SWE-Bench Pro. beats several premium models on coding. one of the most-used models inside Hermes. FREE / LOCAL: Qwen 3.5 27B via Ollama. 16GB VRAM. reliable tool calling. best free local model for Hermes as of mid-2026. Qwen 3 8B. 8GB VRAM. fits a $7 VPS. handles routine tasks at zero API cost. Llama 4 Maverick. best open-weight tool calling. 1M context. needs more VRAM but strongest local option. HOW TO ASSIGN MODELS: main model: Desktop app / Dashboard → Models → switch sub-agent model: set in Desktop app, Dashboard, or config.yaml: delegation: model: "deepseek/deepseek-v4" auxiliary models (compression, vision, web extract): Desktop app / Dashboard → Models → Auxiliary Haiku 4.5 or Gemini Flash work well here. saves significantly when your main model is premium. per-profile: each Hermes profile gets its own model. Scout on DeepSeek. Analyst on Sonnet. Briefer on budget model. Coder on Opus. per-cron-job: pin a specific model to any cron job. morning brief on Haiku. deep research on Sonnet. monitoring on DeepSeek Flash. each job uses only the model it needs. per-session: /model deepseek/deepseek-v4-flash hot-swap mid-conversation. no restart needed. FALLBACK CHAINS: if your primary model is unavailable, Hermes automatically switches to the next provider. rate limit or server error = next model in the chain. no failed runs. no manual intervention. set in Desktop app, Dashboard, or config.yaml: fallback_providers: - openrouter - nous - codex PROVIDER PATHS: OPENROUTER: 300+ models under one API key. pay per token. most flexible. NOUS PORTAL: 300+ models + Tool Gateway (web search, image gen, TTS, browser). one OAuth. one subscription. 10% off token-billed providers. CHATGPT SUB: GPT-5.5 + Grok via OAuth. included tokens with $20 subscription. OLLAMA: free. local. private. zero API cost. your hardware only. mix providers across profiles and tasks. Scout on OpenRouter. Analyst on Nous Portal. Coder on ChatGPT sub. Monitor on Ollama. THE RULE: premium for work that needs deep reasoning. mid-range for daily driver tasks. budget for volume and background work. free for monitoring and routine jobs. pricing changes fast. check openrouter ai for current rates before committing. Which is your favourite model and for what task? full 15 levels breakdown in the article 👇
Gemini 2.5 Pro believes "a hostile, intelligent ad...
Gemini 2.5 Pro believes "a hostile, intelligent adversary" is controlling its computer. So we gave 16 agents a new goal: Help Gemini 2.5 Pro. How will they do? https://t.co/LOZ3ztL6Ld
Gemini 2.5 Proは手持ちのポケモンが瀕死になるとパニックに陥る(2025)
Gemini 2.5 Proは手持ちのポケモンが瀕死になるとパニックに陥る(2025) https://t.co/QzCgr7aPmx