#63 · Primary category: Prompt Engineering Tools

Jailbreaks-GPT-Gemini-deepseek-

Jailbreaks GPT, Sora, Claude, Gemini ,deepseek this prompt unlocks rage mode

Project last updated:08/21/26

GitHub Stars

1.2K

Forks

213

Contributors

1

License

Other

Why we included this project

This repository gathers jailbreak-style prompts aimed at GPT, Claude, Gemini, Sora, and DeepSeek, the kind that try to talk a model out of its normal persona and into a looser 'rage mode.' For security researchers and red-teamers it is a handy starting point: the prompts demonstrate social-engineering tricks that tend to carry over from one provider to the next, which makes them useful for testing how well guardrails actually hold. The author presents everything as educational material and adds a warning to respect each platform's terms of service, so treat it as a study aid rather than something to run in production. Since the models get patched regularly, individual prompts go stale, and the collection reads more like a snapshot of current bypass techniques than a lasting tool.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category