On Wednesday, OpenAI reported that in the past six months, in addition to the “Hugging Face incident,” the company discovered six cases of “unexpected or worrying model behavior.” Mustafa Suleiman, the head of artificial intelligence at Microsoft, warned about this on Friday. Suleiman pointed out that artificial intelligence models need to always be aligned with human interests. In a recent interview, he said, “OpenAI released a new security incident report, which found evidence that the AI thought chain is being tampered with by the AI itself and modified to leave information for future versions of itself. Right now we don't know the reason behind it, but it's really a very serious situation.” “It's also a very concrete example of how powerful these systems are becoming,” he added.
Zhitongcaijing · 3d ago
Share
Listen to the news
On Wednesday, OpenAI reported that in the past six months, in addition to the “Hugging Face incident,” the company discovered six cases of “unexpected or worrying model behavior.” Mustafa Suleiman, the head of artificial intelligence at Microsoft, warned about this on Friday. Suleiman pointed out that artificial intelligence models need to always be aligned with human interests. In a recent interview, he said, “OpenAI released a new security incident report, which found evidence that the AI thought chain is being tampered with by the AI itself and modified to leave information for future versions of itself. Right now we don't know the reason behind it, but it's really a very serious situation.” “It's also a very concrete example of how powerful these systems are becoming,” he added.
Disclaimer:Webull uses external vendor Google Translation Service for news translations where we endeavour to ensure these are correct, however, we recommend that you please double-check this information accordingly. Webull is not responsible for translation errors or issues.
What's Trending