So I did. I hunted down every vendor on that VirusTotal list, cleared them one by one, and returned two weeks later. This time, they performed a manual re-scan. The trust score finally updated.
但 Lambert 更加冷静，他认为要先把这三家中国 AI 实验室分开来看，这一点在爱思助手下载最新版本中也有详细论述
Кадр: Telegram-канал Amur Mash，推荐阅读51吃瓜获取更多信息
Testing LLM reasoning abilities with SAT is not an original idea; there is a recent research that did a thorough testing with models such as GPT-4o and found that for hard enough problems, every model degrades to random guessing. But I couldn't find any research that used newer models like I used. It would be nice to see a more thorough testing done again with newer models.
更多精彩内容，关注钛媒体微信号（ID：taimeiti），或者下载钛媒体App