GPT-Jailbreak and gpt_jailbreak_status

These are **complements** — one provides jailbreak techniques/methods while the other tracks their effectiveness and current status across different GPT versions, making them useful together for understanding the landscape of GPT vulnerabilities.

GPT-Jailbreak
44
Emerging
gpt_jailbreak_status
34
Emerging
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 18/25
Maintenance 0/25
Adoption 10/25
Maturity 8/25
Community 16/25
Stars: 229
Forks: 33
Downloads:
Commits (30d): 0
Language:
License: MIT
Stars: 939
Forks: 65
Downloads:
Commits (30d): 0
Language: HTML
License:
Stale 6m No Package No Dependents
No License Stale 6m No Package No Dependents

About GPT-Jailbreak

Techiral/GPT-Jailbreak

This repository contains the jailbreaking process for GPT-3, GPT-4, GPT-3.5, ChatGPT, and ChatGPT Plus. By following the instructions in this repository, you will be able to gain access to the inner workings of these language models and modify them to your liking.

This project helps AI safety researchers and red teamers understand and exploit vulnerabilities in large language models like GPT-3, GPT-4, and ChatGPT. It provides specific prompts and instructions that, when entered into these models, can bypass their safety features. The output is an LLM that behaves outside its intended guardrails, which is useful for security analysis or exploring model limitations.

AI Safety Testing Red Teaming LLM Vulnerability Research AI Security Prompt Engineering

About gpt_jailbreak_status

tg12/gpt_jailbreak_status

This is a repository that aims to provide updates on the status of jailbreaking the OpenAI GPT language model.

This project keeps you informed about the current ability to bypass the safety features of OpenAI's GPT models. It takes in various methods and attempts to 'jailbreak' the AI, and outputs whether those methods are currently working or have been patched. It's for anyone interested in the boundaries and limitations of large language models, particularly AI researchers, ethicists, and prompt engineers exploring AI behavior.

AI-safety prompt-engineering large-language-models AI-ethics AI-research

Scores updated daily from GitHub, PyPI, and npm data. How scores work