AI Personal Learning
and practical guidance
讯飞绘镜
Total 29 articles

Tags: PROMPTS aids

Prompt越狱手册:突破AI限制的提示词设计指南-首席AI分享圈

Prompt Jailbreak Manual: A Guide to Designing Prompt Words That Break AI Limitations

General Introduction Prompt Jailbreak Manual is an open source project hosted on GitHub and maintained by the Acmesec team. It focuses on teaching users how to break the limits of the AI macromodel through well-designed prompt words (Prompt), helping technology enthusiasts and security researchers explore the potential capabilities of AI. The project is based on ...

Matrix:黑客帝国为主题的沉浸式提示词破解游戏-首席AI分享圈

Matrix: Matrix-themed immersive cue word hacking game

Matrix is an innovative AI security challenge platform created by Repello AI, aiming to let users experience and test the security of AI systems through interactive games. The platform is based on the future science fiction background, set in the year 2099, AI has taken full control of the world's virtual scenarios, with...

Agenta:集成到AI应用的提示词与模型效果评估工具-首席AI分享圈

Agenta: a tool for evaluating the effectiveness of cue words and models integrated into AI applications

Comprehensive Introduction Agenta is an open source AI model management tool specialized in helping users easily experiment with cue words, test model effects and monitor runs. It is suitable for people who want to develop AI applications quickly, providing a platform that is simple to operate. You can use it to try the effect of different cue words, compare multiple AI...

Basalt:快速构建和优化AI应用中的提示词-首席AI分享圈

Basalt: quickly build and optimize cue words in AI applications

General Introduction Basalt is a cue building and management focused platform designed to help teams efficiently build high-quality AI cues and apply them to their products. It provides a code-free editor, smart optimization suggestions, and versioning features that enable product managers, engineers, and domain experts to quickly set...

Confident AI:自动化大语言模型评估框架,对比不同大模型提示词输出质量-首席AI分享圈

Confident AI: A Framework for Automated Large Language Model Evaluation, Comparing the Output Quality of Different Large Model Cue Words

Comprehensive Introduction DeepEval is an easy-to-use open source LLM evaluation framework for evaluating and testing large language modeling systems. It is similar to Pytest, but focuses on unit testing of LLM output.DeepEval combines the latest research results with metrics such as G-Eval, phantom detection, answer correlation, RAGAS, and...

ChainForge:测试和评估大型语言模型提示效果的开源可视化编程环境-首席AI分享圈

ChainForge: An Open Source Visual Programming Environment for Testing and Evaluating the Effectiveness of Large Language Model Hints

General Introduction ChainForge is an open source visual programming environment designed for testing and evaluating the effectiveness of prompts for Large Language Models (LLMs). It provides a data-flow cueing engineering environment through which users can quickly explore and analyze the impact of different cues on the quality of LLM responses.Chain...

Promptimizer:优化大模型提示词的实验性库,自动优化 Prompt-首席AI分享圈

Promptimizer: an experimental library for optimizing large model prompt words, automatically optimizing Prompt

General Introduction Promptimizer is an experimental cue word optimization library designed to help users systematically improve the cue words of their AI systems. By automating the optimization process, Promptimizer can improve cue word performance on specific tasks. Users only need to provide the initial cue word, dataset and custom...

Fabric:集成众多提示词的AI开源工作流框架,高效处理各种事务-首席AI分享圈

Fabric: an AI open source workflow framework that integrates many cue words to efficiently handle a variety of transactions

General Introduction Fabric is an open source AI framework developed by Daniel Miessler to simplify and automate everyday computer tasks and make artificial intelligence easier to use. It helps users efficiently handle a variety of tasks such as content summarization, data extraction through modular design and preset prompt words (Patterns)...

Shire Run:共享AI编码智能体辅助工具-首席AI分享圈

Shire Run: a shared AI coding smartbody aid

General Introduction Shire provides a simple AI coding and agent language that enables communication between LLMs and control IDEs for automated programming. Shire Run is a platform focused on sharing and downloading AI coding intelligences. The platform allows users to share, download and execute a variety of programming intelligences...

en_USEnglish