A(命题人:敖丽)It is surprisingly easy to remove the safety measures intended to stop AI chatbots from giving responses that could aid would-be terrorists or mass shooters. The discovery is making firms including OpenA...A(命题人:敖丽)It is surprisingly easy to remove the safety measures intended to stop AI chatbots from giving responses that could aid would-be terrorists or mass shooters. The discovery is making firms including OpenAI develop strategies to solve the problem—but research suggests their efforts have had limited success so far.展开更多
文摘A(命题人:敖丽)It is surprisingly easy to remove the safety measures intended to stop AI chatbots from giving responses that could aid would-be terrorists or mass shooters. The discovery is making firms including OpenAI develop strategies to solve the problem—but research suggests their efforts have had limited success so far.