🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

No more waiting. o1's is officially on Chatbot Arena! We tested o1-preview and mini with 6K+ community votes. 🥇o1-preview: #1 across the board, especially in Math, Hard Prompts, and Coding. A huge leap in technical performance! 🥈o1-mini: #1 in technical areas, #2 overall.

Love the idea to package compute leftover into a full-fledge LLM inference service!

🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in

🎙️Chainlit Realtime is here! 🎙️ Featuring first-class WebSocket support for realtime audio interactions in Chainlit applications. We’ve added support for OpenAI real-time API to unlock a whole new UX for devs building intelligent, responsive assistants.

💡 When using an LLM-as-a-Judge scorer, who goes first: the rationale or the score? 📏 An LLM-as-a-Judge scorer produces both a score and a rationale based on a rubric. Ideally, the score is categorical (A, B, C, D, etc.), which you can map to values between 0 and 1. 🥇Whether

🚀 New LiteLLM (YC W23) Integration 🚀 Track & log all your LiteLLM calls with Literal AI in just 2 lines of code! LiteLLM allows you to interact with 100+ LLMs (OpenAI, Anthropic, Mistral AI, etc.) seamlessly using a consistent OpenAI-compatible format, either use their python

Great talk by merve at dotAI on the growing open-source ecosystem in Hugging Face! With the new Mistral AI 3B & 8B Ministrals models, customized edge LLM-based applications are becoming more accessible than ever💡

We are thrilled to announce a case study of a successful internal deployment of LlamaIndex at NVIDIA, an internal AI assistant for sales 🧑‍💼🤖 * Uses Llama 3.1 405b for simple queries, 70b model for document searches * Retrieves from multiple sources: internal docs, NVIDIA site,

Ollama Supports Llama 3.2 Vision: Talk to ANY Image 100% Local! 📚 Step-by-step Hands-on tutorial ⚡ How to Install? ollama 🏃‍♂️ How to Run? Meta @aiatmeta 🔌 How to Integrate in your App? 🎮 How to Create UI? Chainlit 📈 Analyse charts and graphs

🏃‍♂️ Overheard someone say “How do you track your runs?” Me wondering what type of AI agents they are building Them: “I use Strava.” 🤦

🚀 Exciting demo with humanlayer and OpenAI 🚀 Build a next-gen customer support agent that handles queries but loops in a human for critical actions—ensuring precision with a human touch!

Today OpenAI announced o3, its next-gen reasoning model. We've worked with OpenAI to test it on ARC-AGI, and we believe it represents a significant breakthrough in getting AI to adapt to novel tasks. It scores 75.7% on the semi-private eval in low-compute mode (for $20 per task

AI right now

🔥 Chainlit now supports Anthropic's Model Control Protocol (MCP)! Check out our demo with @Stripe's MCP. Compatible with popular frameworks like LangChain. Link to the code at the end of the thread 👇

Chainlit Anthropic Stripe LangChain lots of MCPs out there, but not enough clients 👇 `chainlit run app.py` launches a FastAPI chat application with chain-of-thought that can connect to any MCP server 🔥

Excited to announce the integration of Linkup’s search in Chainlit's conversational AI. In a minute, add a “🌐Search web” button to your chatbot and give it access to fresh grounding content for accurate answers. cc Dan Constantini Literal AI

How to set up a remote MCP server and connect it to ChatGPT deep research:

new mcp spec just dropped: 1. auth is fixed! at last! 2. elicitation now makes it possible for a server to ask an end-user for more info, enabling more agentic behaviors 3. structured tool outputs makes it easier to reason about tool responses 4. more security documentation