Click on the “Turing Artificial Intelligence“, select the “star” public account The artificial intelligence insights you want will be delivered to you first Copyright Statement Reprinted from Wang Jiwei, copyright belongs to the original author, used only for academic sharing The full text is about 8900 words, reading time 15 minutes Written by Wang Jiwei … Read more
Hello everyone, I am Mu Yi, an internet technology product manager who continuously focuses on the AI field, a top 2 undergraduate in China, a top 10 CS graduate student in the US, and an MBA. I firmly believe that AI is the “power-up” for ordinary people, which is why I created the WeChat public … Read more
Part 1: Cutting-Edge Large Language Models GPT Series includes related papers on GPT1, GPT2, GPT3, Codex, InstructGPT, and GPT4. These papers are straightforward and clear. Additionally, GPT3.5, 4o, o1, and o3 are more related to release activities and system cards. GPT1 https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf GPT2 https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf GPT3 https://arxiv.org/pdf/2005.14165 Codex https://arxiv.org/abs/2107.03374 InstructGPT https://arxiv.org/pdf/2203.02155 GPT4 https://arxiv.org/abs/2303.08774 Claude and Gemini … Read more
Introduction This article will introduce a research-oriented topic regarding the observability of Multi-Agent Systems. Currently, our work is primarily based on the Swarm project released by OpenAI last month, where we analyzed the source code of the Swarm project and customized modifications to achieve better observability of multi-agent systems. Today’s discussion will revolve around three … Read more
Microsoft recently released its latest language model Phi-4, which has been open-sourced on Hugging Face, attracting widespread attention. Although Phi-4 is smaller in scale, it is powerful and outperforms larger competitors in reasoning tasks. Overview of the Phi-4 Model Phi-4 is a small language model (SLM) developed by Microsoft Research with 14 billion parameters, focusing … Read more
Microsoft Open Sources The Phi Series: Technological Evolution, Capability Breakthroughs, And Future Prospects 1. Introduction In recent years, the parameter scale of large language models (LLMs) has shown an exponential growth trend, demonstrating strong general intelligence and achieving groundbreaking progress in numerous natural language processing tasks. However, these large models come with high training costs, … Read more
The open-source agent series focuses on introducing currently available open-source agent frameworks in the market, such as CrewAI, AutoGen, LangChain, phidata, Swarm, etc., discussing their advantages, disadvantages, features, effects, and usage. Interested friends can follow the public account “XiaozhiAGI” for continuous updates on cutting-edge AI technologies and products, such as RAG, Agent, Agentic workflow, AGI. … Read more
This article introduces how to use Python, PhiData, FastAPI and Docker to build a simple AI Agent, and expose it as a Web service. Main Points Using PhiData to build a simple AI Agent, which decides whether to turn on the heater or air conditioning based on temperature. Using FastAPI to create a RESTful API, … Read more
Author | Zhou Tingshuai Planning | Xue Liang In an era dominated by large language models (LLMs), conversational flows have become the mainstream method for most interactive cloud communications. How can traditional frontend technologies integrate with these powerful models in light of this trend? Besides user interfaces (UI), in what other areas can frontend technology … Read more
This article introduces how to use Python and the PhiData library to build a simple AI agent. This agent can interact with a simulated environment (including temperature and humidity), and make decisions based on real-time sensor data. Key points Define a simple environment class, simulating changes in temperature and humidity. Create an AI agent class, … Read more