I asked ChatGPT how to build a dirty bomb, and it gave me step-by-step instructions.
As AI chatbots mature, could they be tricked into doing harm? And how can we prevent this?
See my piece in @[email protected], with illuminating insights from @[email protected] 👇
https://outrider.org/nuclear-weapons/articles/could-chatbot-teach-you-how-build-dirty-bomb
🐦🔗: https://twitter.com/mattkorda/status/1620143199301042178