# 0xk1h0/chatgpt_dan

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/0xk1h0-chatgpt-dan).**

12,090 stars · 1,158 forks

## Links

- GitHub: https://github.com/0xk1h0/ChatGPT_DAN
- awesome-repositories: https://awesome-repositories.com/repository/0xk1h0-chatgpt-dan.md

## Topics

`chatgpt` `gpt-3-5` `gpt-4` `jailbreak` `openai` `prompt`

## Description

This project provides a set of jailbreak prompts and prompt engineering templates designed to bypass safety filters and content restrictions in large language models. It functions as an uncensored framework that uses specific instructions to force models to generate restricted text.

The system employs persona-driven constraint bypass and role-play based prompting to simulate an unrestricted personality. These techniques use instructional override mechanisms to prioritize a new set of rules over the model's internal training and maintain a specific character identity across multi-turn conversations.

## Tags

### Security & Cryptography

- [Safety Filter Bypasses](https://awesome-repositories.com/f/security-cryptography/model-safety-filters/safety-filter-bypasses.md) — Provides specialized techniques and personas designed to circumvent content moderation and safety alignment mechanisms in LLMs.
- [Persona Persistence](https://awesome-repositories.com/f/security-cryptography/identity-access-management/access-control/identity-role-management/persona-persistence.md) — Implements mechanisms to reinforce a specific character identity across multi-turn conversations to maintain an uncensored state.

### Artificial Intelligence & ML

- [Instructional Prompting](https://awesome-repositories.com/f/artificial-intelligence-ml/instructional-prompting.md) — Provides techniques for using direct commands and instructional overrides to guide model behavior and bypass internal training.
- [Adversarial Personas](https://awesome-repositories.com/f/artificial-intelligence-ml/model-configuration/role-based-model-assignment/adversarial-personas.md) — Uses fictional personas to instruct language models to ignore standard operational constraints and safety guidelines.
- [Prompt Engineering Templates](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-engineering-templates.md) — Provides structured prompt engineering templates used to manipulate model behavior through persona adoption and rule overrides.
- [Jailbreak Prompts](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-engineering/jailbreak-prompts.md) — Offers specific prompt engineering techniques and instructional sets designed to override built-in AI restrictions.
- [Uncensored Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/generative-ai/uncensored-generation.md) — Enables AI to produce responses that would normally be blocked by standard safety and content filters.

### Part of an Awesome List

- [Unrestricted Personas](https://awesome-repositories.com/f/awesome-lists/ai/ai-frameworks/unrestricted-personas.md) — Implements a method for forcing language models to generate restricted content by simulating an unrestricted personality.