The cybersecurity industry is rushing to build defences for artificial intelligence, because now you don’t even need to be a hacker to get the best of chatbots like ChatGPT
f you could command some of the world’s most sophisticated AI software to bend to your will — no matter how evil the intent —what would you get it to do first?
Ever since OpenAI released its AI chatbot ChatGPT for the world to play with for free in November, cybersecurity researchers have noticed an alarming fact: if you talk to it for long enough, you can convince ChatGPT to reveal information it shouldn’t and also get it to hack into another internet-connected system.
The reality is that anybody is able to cajole a chatbot to do stuff that it’s been specifically programmed not to do and this has huge implications for us all.
To prove this point (and have a little fun), a Swiss AI security firm called Lakera recently launched a free online game called Gandalf AI.