OpenAI has disclosed six reports of “unexpected or concerning” behavior in artificial intelligence models as the debate on AI safety becomes increasingly heated.
OpenAI, the developer behind ChatGPT, revealed on Wednesday that it has detected new incidents in which its artificial intelligence (AI) has behaved in “unexpected or concerning” ways.
OpenAI has disclosed six reports of “unexpected or concerning” behavior in artificial-intelligence models as the debate on AI safety becomes increasingly heated.
