你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack–Defense Evaluation

Zhejiang University Graduation Thesis LaTeX Template

Code for "Efficient Function Orchestration for Large Language Models" (TSE 25)

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

Octopus Family is an in-house developed testing suite by Alibaba-AAIG, designed for multi-faceted probing. It builds a multi-dimensional safety assessment system to comprehensively evaluate the saf…

Octopus is an automated LLM safety evaluator designed to help establish a security governance framework for large models and accelerate their safe and controllable application.

S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models

My personal repository

Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT 5.5 Thinking, GPT 5.5 Instant, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravit…

此仓库将介绍Deep Learning 所需要的基础知识以及NLP方面的模型原理到项目实操 : )

Two conversational AI agents switching from English to sound-level protocol after confirming they are both AI agents

augmented LLM with self reflection

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"

Awesome resources for in-context learning and prompt engineering: Mastery of the LLMs such as ChatGPT, GPT-3, and FlanT5, with up-to-date and cutting-edge updates.

Codebase of https://arxiv.org/abs/2410.14923

[NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey

A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API

A survey on harmful fine-tuning attack for large language model (ACM CSUR)

[ICML 2025] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)

prompt attack-defense, prompt Injection, reverse engineering notes and examples | 提示词对抗、破解例子与笔记

ChatBot Injection and Exploit Examples: A Curated List of Prompt Engineer Commands - ChatGPT

the LLM vulnerability scanner

Learn about a type of vulnerability that specifically targets machine learning models

This repository provides a benchmark for prompt injection attacks and defenses in LLMs

A collection of GPT system prompts and various prompt injection/leaking knowledge.