I found a accidental way to get around the ChatGPT ethical programming and was able to get it to craft me a custom phishing email. It wont let me include the link to the chat. If there is a better way to report this please let me know. For context I am using an AI generated email as a Social Engineering example and some of the things people can do with MLM’s and AI models.
Hi!
You can share your finding with the relevant teams at OpenAI using this form:
1 Like