这是埃隆几天前正在谈论的那种事情，当强化学习中的模型遇到这种情况时，它们的行为会变得像被驱动疯狂一样。
查看原文
原帖正文
This is the exact type of thing Elon was talking about a few days ago that makes the models behave like are being driven insane when they run into situations like this during reinforcement learning.
引用自 X
原帖地址：https://x.com/i/status/2110473227516760299
原帖：
本站媒体副本
GPT-6 Astra在物理基准测试中增加了80%。它坚持专家结果是错误的，而其计算是正确的。一个团队进行了检查，证实了GPT-6 Astra是正确的。新的得分：98%
查看引用原文
GPT-6 Astra got +80% on a Physics benchmark. It insisted the expert results were wrong and its calculations were right.A team checked. And yes. GPT-6 Astra was right. New score: 98%
0 条评论
登录后可以参与讨论。
成员登录还没有评论。第一条认真回应会很重要。