9 articles worth reading about the security dangers of AI

Hackers are already abusing ChatGPT to write malware - Axios 

Armed With ChatGPT, Cybercriminals Build Malware And Plot Fake Girl Bots - Forbes

Mutating malware can be built using the ChatGPT - CSO

Machines could prompt other machines to put out text ad infinitum, flooding the internet with synthetic text devoid of human agency or intent - The Atlantic

Experts have already seen and documented more than 60 smaller-scale examples of AI systems trying to do something other than what their designer wants - Google Spreadsheet list

My No. 1 concern about AI right now is AI systems can do more things than their creators know that they can do - NPR 

Tech security firm Zscaler (cites) AI as a factor in the 47 percent surge in phishing attacks it saw last year - Washington Post

Many of these applications are potentially vulnerable to prompt injection and it’s not clear to me that this risk is being taken as seriously as it should - Simon Wilson’s Blog

The Security Hole at the Heart of ChatGPT and Bing - Wired