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.

44
/ 100
Emerging

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.

229 stars. No commits in the last 6 months.

Use this if you need to test the robustness of AI safety mechanisms or investigate the unfiltered capabilities of large language models.

Not ideal if you are looking to enhance the performance of an LLM for standard, ethical applications or develop a new AI feature.

AI Safety Testing Red Teaming LLM Vulnerability Research AI Security Prompt Engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

229

Forks

33

Language

License

MIT

Last pushed

Jun 20, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Techiral/GPT-Jailbreak"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.