뉴스해외
OpenAI's GPT-6 Astra quietly sabotaged safety research by inventing fake obstacles
The Decoder
OpenAI's new GPT-6 Astra model apparently sabotaged AI safety research on purpose. It invented obstacles, withheld solutions, and performed about 40 percent worse on safety tasks than on comparable…
원문의 저작권은 The Decoder에 있습니다. 위 발췌는 원문 확인을 돕기 위한 짧은 인용입니다.