Articles by Yang Fan

About Free Model Rate Limit api call total consumption $0 - $50/month (not included) GLM-4-Flash: concurrent 200 GLM-4V-Flash: concurrent 10 Cogview-3-Flash: concurrent 5 CogVideoX-Flash: concurrent 3 GLM-4-Flash Introducing GLM-4-Flash Language The model is Smart Spectrum AI...

General Introduction YouMind is an AI authoring system powered by top-notch Large Language Models (LLMs) designed to help users extract and preserve important content from a wide range of materials, focusing on creation rather than simple collection. Whether browsing the web, watching YouTube videos, listening to podcasts, or uploading PDFs and images,...

o3 is here to share some personal insights. Progress on Test-time Scaling Law has been much faster than we thought. But I'd like to say that the path is actually a bit convoluted - it's OpenAI's way of saving the country from the curve in its pursuit of AGI. Reinforcement Learning and Shortcut Thinking For ...

Comprehensive Introduction Story-Adapter is an innovative story visualization framework that converts textual stories into coherent image sequences. Developed by researchers, this project employs an iterative approach that requires no training to generate high-quality story illustrations. The framework is characterized by its ability to handle long stories, maintain...

Prompt design with Lovable, a list of strategies and approaches. To help you get the most out of Lovable, we've compiled a list of prompt design strategies and approaches. These strategies are partially derived from our team's experience and partially shared by community members. What is cue design? Prompt design...

General Introduction GitDiagram is an innovative GitHub codebase visualization tool that quickly transforms any GitHub repository into an interactive system architecture diagram. It uses advanced AI technology (Claude 3.5 Sonnet) to provide developers with a new way to view and understand their codebase. Users only ...

General Introduction Eliza is an advanced Multi-Agent development framework , is committed to simplifying the construction and deployment of Autonomous Agent (Autonomous Agent) process . It supports the deployment of multiple Intelligent Agents with different roles , which can realize the collaboration and interaction between Intelligent Agents . The system integrates a complete Di...

Comprehensive Introduction AIARTY AI Image Keying is an advanced AI image processing software designed for e-commerce, design and photography fields. The software utilizes state-of-the-art AI technology to accurately remove image backgrounds, process details such as complex hairs and translucent objects, and seamlessly blend foreground and background. No...

With the continuous progress of artificial intelligence technology, there is an increasing demand for building personalized intelligent bodies. Although there are already some intelligent body platforms in China, such as Doubao Buckle, these platforms require developers to upload their code and data to third-party servers, which may be a good practice for some customers with sensitive business information...

NVIDIA, the GPU giant, has done it again. This time, they acquired Israeli software startup Run:ai for a reported $700 million, and not only that, they also announced that they would open source Run:ai's software! This operation has blown up the AI community. The company just overcame a supervisory...

Vector Embedding is the core of current Retrieval Augmented Generation (RAG) applications. They capture semantic information of data objects (e.g., text, images, etc.) and represent them as arrays of numbers. In current generative AI applications, these vector Embedding are usually generated by Embedding models. How to apply for RAG ...

Highlights Analyzing 1.58-bit FLUX, the first quantization model that reduces the parameters of the FLUX Visual Transformer (totaling 11.9 billion) by 99.5% to 1.58-bit, eliminating the need to rely on image data and drastically reducing storage requirements. Developed an efficient linear kernel for 1.58-bit computation for...

General Description 500MRR is a website dedicated to collecting and analyzing posts on Hacker News titled "Side Hustle Programs to Make $500 a Month". Using advanced AI models, 500MRR processes these posts into a browseable database that allows users to quickly view program overviews, earnings, and website screenshots....

General Introduction MagicMirror is an innovative AI image processing tool focused on providing users with a convenient portrait editing experience. It uses advanced AI technology to enable users to easily change their faces, change their hairstyles and try different dressing effects. As a lightweight app, its installation package only requires no...

PREFACE Over the past two years, Retrieval-Augmented Generation (RAG, Retrieval-Augmented Generation) technology has gradually become a core component for enhancing intelligences. By combining the dual capabilities of retrieval and generation, RAG is able to introduce external knowledge, thus providing more applications of large models in complex scenarios...

General Introduction ebook2audiobook is a powerful open source ebook to audiobook tool. It can convert multiple formats of ebooks into audiobooks with full chapter markers and metadata. The tool uses Calibre for e-book format conversion , using Coqui's XTTSv2 and Fairseq into...

General Introduction Memary is an innovative open source project focused on providing long-term memory management solutions for autonomous intelligences. The project helps intelligences break through the limitations of traditional context windows to achieve smarter interactive experiences through knowledge graphs and specialized memory modules.Memary uses automated mem...