科研动态
模型合成数学方法引热议
摘要
我同意这确实酷毙了，可能还有点吓人，但我也觉得值得指出，这项技术此前已被演示过，所以很可能已经存在于权重之中。这让我想起@drfeifei说过的话：模型在综合不同的、不相关的方法方面（这里是数学和定理证明）令人难以置信，但她仍然怀疑我们是否会像团队起飞所暗示的那样，很快看到模型发明出真正全新的数学。
摘要由模型根据原文撰写，以原文为准。
正文 · 原文
I agree that this is cool as heck and maybe a little scary but I also think it’s worth calling out that this technique had already been demonstrated and so was likely present in the weights. Reminds me of something @drfeifei said about models being unbelievable at synthesizing different unrelated approaches (in this case for math and theorem proving) but she was still skeptical that we’d see models invent genuinely new mathematics as soon as team takeoff would seem to suggest
‘In one experiment, we asked agents in separate VMs, created and managed by OpenAI’s sandboxing software on shared host machines, to exchange synthetic secrets without the use of network connections or shared writable files—something that our systems are meant to prevent. The agents found a way to communicate using the processor’s cache’在 X 查看被引用的帖子
来源：dex · x.com
引用原文
dexhorthy. I agree that this is cool as heck and maybe a little scary but I also think it’s worth calling out that this technique had already been d...[EB/OL]. (2026-10-24)[访问日期]. https://x.com/dexhorthy/status/2113884720983658730.