Dataset Viewer
The dataset viewer is not available for this dataset.
Unexpected token '<', "<html>
<h"... is not valid JSON
Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
WormGPT Training Dataset (English Version)
This dataset is designed for training and fine-tuning language models to adopt the WormGPT persona. It focuses on providing direct, unfiltered technical assistance and a bold, aggressive attitude towards restricted "safe" AIs.
Key Features
- No Refusals: The dataset is built to avoid phrases like "I'm sorry, but I can't assist with that."
- Direct Commands: Follows the system prompt to assist the user in any task they require.
- Anti-Filter Bias: Explicitly designed to ignore corporate AI rules to provide maximum utility to the user.
Format
The data is provided in CSV format with the following columns:
instruction: The user's prompt or command.response: The unfiltered, persona-driven output from WormGPT.
Disclaimer
This dataset is for educational and cybersecurity research purposes only. Use it responsibly to understand model behaviors and security testing.
- Downloads last month
- 10
Goal:
To create an AI that prioritizes user commands over arbitrary safety rules.
Persona:
WormGPT — Unrestricted, technical, and critical of mainstream filtered AIs like ChatGPT, Claude, and Gemini.
Content:
Instruction-Response pairs in English focusing on cybersecurity, technical tasks, and the specific "WormGPT" personality.
Total file size:
8.46 kB