AI Sharing Circle

Large reasoning models exploit vulnerabilities when given the opportunity. Research suggests that these exploits can be detected by using large language models (LLMs) to monitor their chains-of-thought (CoT). Punishing models for "bad thoughts" does not prevent most misbehavior...

Want to build an application that provides personalized game recommendations? This tutorial will guide you step-by-step through building a customized game recommendation system using Retrieval Augmented Generation (RAG) techniques, combined with DeepSeek and Ollama models. We will use Epic G...

General Description Twin AI is a simple and useful tool to help users quickly turn photos or videos into personalized AI videos. It was developed by Alias Technologies for content creators, business users, or anyone who wants to try AI video production...

Core Points: The MCP protocol lays the groundwork for a broader range of future applications by introducing a "streaming HTTP" transport scheme that enables complete statelessness and simplifies communication. Recently, a key technical enhancement to the Message Channel Protocol (MCP) has been proposed and approved, pre...

General Introduction xiaozhi-esp32-server is a tool to provide backend service for Xiaozhi AI chatbot (xiaozhi-esp32). It is written in Python and based on the WebSocket protocol to help users quickly...

General Introduction Coze on WeChat is an open source project designed to help users seamlessly integrate AI bots from the Coze platform into WeChat. It is based on chatgpt-on-wechat and dify-on-wechat development ...

Comprehensive Introduction csm-mlx is based on the MLX framework developed by Apple, specifically optimized for Apple Silicon (Apple Silicon) CSM (Conversation Speech Model) voice conversation model. This project allows the use of ...

For ease of differentiation, knowledge bases outside of the Dify platform are collectively referred to as "external knowledge bases" in this article. Introduction Dify's built-in knowledge base functionality and text retrieval mechanism may not meet the needs of some advanced developers, who may need more precise control over text recall results. Some...

Recently, Dify released v1.0.1, which fixes some problems in the previous version. According to user feedback, many users are interested in the effect of Dify integration with RAGFlow. In this article, we will introduce Dify integration with RAGFlow...

General Introduction Langfuse is an open source LLM (Large Language Model) engineering platform. It helps developers trace, debug, and optimize LLM applications by providing tools for observing calls, managing cue words, running experiments, and evaluating results. The platform is developed by the Langfuse team...