How do you get ChatGPT to create malware strong enough to breach Google's password manager? Just play pretend.

Cybersecurity researchers bypassed ChatGPT's security features by role-playing with it, ultimately getting the chatbot to write password-stealing malware.

ysbrandcosijn/Getty, Anadolu/Getty, Anamarija Mrkic/iStock, Ava Horton/BI

• Cybersecurity researchers were able to bypass security features on ChatGPT by roleplaying with it.
• By getting the LLM to pretend it was a coding superhero, they got it to write password-stealing malware.
• The researchers accessed Google Chrome's...