AI Personal Learning
and practical guidance
CyberKnife Drawing Mirror

Articles by Yang Fan

Kheish:多角色智能体,审查、验证和格式化输出以生成高质量结果-首席AI分享圈

Kheish: multi-actor intelligences that review, validate and format output to produce high quality results

Comprehensive Introduction Kheish is an open source multi-role agent designed for Large Language Model (LLM) tasks that require structured, step-by-step collaboration.Kheish is more than just a simple coordinator, it is an intelligent agent in its own right, requesting modules on demand, integrating user feedback across different...

AI ContentCraft:生成短故事、对话脚本、配音、配图的多功能AI内容创作工具-首席AI分享圈

AI ContentCraft: a versatile AI content creation tool for generating short stories, dialog scripts, voiceovers, and graphics

General Introduction AI ContentCraft is a versatile content creation tool that integrates text generation, speech synthesis, image generation and more. It helps creators quickly generate stories, podcast scripts, and accompanying audio and video content. The tool supports multiple language conversions, can batch process content, and is extremely...

Unigraph:构建本地运行的知识图谱和个人搜索引擎-首席AI分享圈

Unigraph: building locally running knowledge graphs and personal search engines

General Introduction Unigraph is a local-first universal knowledge graph and personal search engine designed to provide users with an integrated workspace to help manage and search for a wide variety of data in their personal lives. With Unigraph, users can integrate data from different sources into a unified knowledge graph...

对标 Cursor 的 AI编辑器 Trae 上手体验-首席AI分享圈

Hands-on with Trae, the AI editor that benchmarks Cursor

  Chinese deep customization Based on the Chinese use of the environment for a large number of deep customization, whether it is the interface or interaction, or the content inside, completely Chinese culture. Use and get started without difficulty directly from VScode or Cursor in the import configuration This is from the Edge to learn the digging technique it ...

AI News
实现 LLM 记忆系统的五种方式-首席AI分享圈

Five ways to realize the LLM memory system

When building large language modeling (LLM) applications, memory systems are one of the key technologies to enhance conversation context management, long-term information storage, and semantic understanding. An efficient memory system can help the model maintain consistency over long conversations, extract key information, and even have the ability to retrieve historical conversations...

AI knowledge
Trae:字节跳动推出的免费AI编程工具-首席AI分享圈

Trae: a free AI programming tool from ByteHopper

Comprehensive Introduction Trae is a free AI programming tool from ByteDance, designed as an integrated development environment (IDE) for Chinese developers. It helps developers quickly generate, optimize and debug code by leveraging advanced AI models such as Claude 3.5 and GPT-4o.Trae supports native Chinese interface, provides b...

海螺语音国内上线,可能是最好的中文语音配音产品-首席AI分享圈

Conch voice domestic launch, may be the best Chinese voice dubbing products

Domestic has not been a content production for the production of excellent voice-over products, either can only use the API or the product is okay sound model can not. For example, the overseas ElevenLabs, although the English is okay, but the Chinese is really pulling across, the main problem of the open source model is the relatively poor quality of the model, as shown in the...

AI News

Matching the right writer and writing style to the writing topic

Background The English-speaking world has a lot of writers who are good at writing for the web, with very different styles and a large training corpus, and AI is very good at imitating them. With the writing style of these people, the content is more understandable or has a logical framework, and it is easier to write explosive text. Features Input the writing topic, AI automatically analyzes the most matching 1...

Unsloth:高效微调和训练大语言模型的开源工具-首席AI分享圈

Unsloth: an open source tool for efficiently fine-tuning and training large language models

General Introduction Unsloth is an open source project designed to provide efficient tools for fine-tuning and training large language models (LLMs). The project supports a wide range of well-known models, including Llama, Mistral, Phi, and Gemma, etc. Unsloth's main features are the ability to significantly reduce memory usage and speed up training...

Learning: Performing workflow "state changes" in natural language (state machines)

Background In the design of customer service related dialogs, it is often necessary to let the user confirm the completion of the current action, and then perform the next action, there are two ways to achieve: 1.Routing 2.Prompts 1.Routing Generally by the large model to determine the user's state, and then perform the corresponding node service, which is the same as orchestrating the "Intelligent Customer Service...

en_USEnglish