Technology
OpenAI’s developer tool for its GPT-4 large language model can be misused to trick the AI into providing information to aid would-be terrorists, and fixing the problem won’t be easy
By Jeremy Hsu
AI chatbots can be fine-tuned to provide information that could help terrorists plan attacks
salarko/Alamy
It is surprisingly easy to remove the safety measures intended to prevent AI chatbots from giving harmful responses that could aid would-be terrorists or mass shooters. The discovery seems to be prompting companies, including OpenAI, to develop strategies to solve the problem. But research suggests their efforts have been met with only limited success so far.
OpenAI worked with academic researchers on a so-called…
More from New Scientist
Explore the latest news, articles and features
Leave a Reply