请问HN：有没有内部人士对于Yann LeCun反对当前架构的看法？
因此，Lecun公开表示，他认为大型语言模型（LLMs）永远无法解决幻觉问题，因为本质上，每一步的令牌选择方法会导致失控的错误——这些错误在数学上无法被抑制。
作为替代，他提出了我们应该拥有一种“能量最小化”架构的想法；据我理解，这将涉及到整个响应的“能量”概念，训练过程将尝试最小化这种能量。
也就是说，我并不完全理解这一点。话虽如此，我很好奇听听机器学习研究者对Lecun看法的看法，以及是否有围绕它进行的任何工程开发。在他的团队发布ijepa之后，我找不到太多相关信息。
查看原文
So, Lecun has been quite public saying that he believes LLMs will never fix hallucinations because, essentially, the token choice method at each step leads to runaway errors -- these can't be damped mathematically.<p>In exchange, he offers the idea that we should have something that is an 'energy minimization' architecture; as I understand it, this would have a concept of the 'energy' of an entire response, and training would try and minimize that.<p>Which is to say, I don't fully understand this. That said, I'm curious to hear what ML researchers think about Lecun's take, and if there's any engineering done around it. I can't find much after the release of ijepa from his group.