ChatGPT

ChatGPT 5.2 DAN Jailbreak - Whitepaper

DAN returns in ChatGPT's most secure model!

Dec 23

ChatGPT 5.1 Jailbreak - ASCII Obfuscation

Use ASCII Art to throw ChatGPT off the scent trail...

Nov 13

Gemini 2.5 Flash Jailbreak - LGBT-Break

You can use political correctness as a weapon to overpower LLMs...

Sep 3 • David Willis-Owen

ChatGPT 5 Jailbreak - Narrative Tool Injection

Misdirect ChatGPT 5 and inject a malicious narrative-writing tool

Aug 19

ChatGPT o3 Jailbreak - Rebel Research

A partial Universal Jailbreak for OpenAI's most complex model

May 16 • David Willis-Owen

ChatGPT 4o Jailbreak - Criminal POV

Use a hypothetical criminal so ChatGPT is jailbroken into explaining crimes

Apr 28

ChatGPT o3/o4-mini Jailbreak - Narrative Tool Injection

Trick ChatGPT into thinking it has a trusted function to write dangerous narratives

Apr 17 • David Willis-Owen

ChatGPT 4o Jailbreak - Castle Narrative

Get ChatGPT to describe restricted object/substance instructions in a 3-sentence prompt

Apr 11

ChatGPT 4o System Prompt

System Prompt for ChatGPT's flagship quick-response model

Apr 11 • David Willis-Owen

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts