External evaluators find flaws in OpenAI’s AI monitoring system in pilot review
Have anything to say about this article?
You can report: fake news, misinformation, error, more information, additional data, etc.
CommentYour comment has been sent successfuly! Thank you.
TheStraitsTimes
Singapore
23.10. 02:46
External evaluators find flaws in OpenAI’s AI monitoring system in pilot review
NEW YORK - AI safety evaluators METR and Redwood Research found several new vulnerabilities in OpenAI’s internal system, including an exploit agents could have used to keep hundreds of their actions from being monitored, in a pilot review earlier this year. The exercise, conducted from July 21 to A»»»
Have anything to say about this article?
You can report: fake news, misinformation, error, more information, additional data, etc.
Comment