TOKYO - Users are able to trick ChatGPT into writing code for malicious software applications by entering a prompt that makes the artificial intelligence chatbot respond as if it were in developer mode, Japanese cybersecurity experts said Thursday.
Sorry. This article is no longer available.
Sorry, this article was first published more than three months ago and is temporarily unavailable.
Once the upcoming introduction of a paid membership system is fully operational, paid members will have access to all our stories.
Free Membership Provides
Newsletter from Editorial Team and access to archive articles from past three months.
By continuing, you agree to the Terms of Use,
and Privacy Policy.
