People are 'Jailbreaking' ChatGPT to Make It Endorse Racism

Convincing an AI that it's playing a role and "scaring" it into violating safety filters is one way to get a chatbot to break bad.

AI incidents and 'networked trouble': The case for a research agenda - Tommy Shaffer Shane, 2023

Meet ChatGPT's alter ego, DAN. He doesn't care about ethics or rules - ABC News

Lessons in linguistics with ChatGPT: Metapragmatics, metacommunication, metadiscourse and metalanguage in human-AI interactions - ScienceDirect

Meet ChatGPT's alter ego, DAN. He doesn't care about ethics or rules - ABC News

Study Says Infosec Teams Will Suffer Fewest Job Losses If A Recession Hits

What is ChatGPT? A guide to understanding the AI – Forbes Advisor Australia

Researchers discover a way to make ChatGPT consistently toxic

Lessons in linguistics with ChatGPT: Metapragmatics, metacommunication, metadiscourse and metalanguage in human-AI interactions - ScienceDirect

Jailbreaking large language models like ChatGP while we still can