力学概论


1986年出版的《力学概论》提出,寻求统一的出发点不是思辨而应是运动现象。

我想,之所以方老师这么说,他肯定认为坐而论道是空洞无用的,只有“躬身格物”才是认识世界的唯一正确的道路。

随着llm的出现,我潜意识里,觉得llm也许真是认识这个世界的钥匙,llm是语言的统计学抽象,而语言恰恰是我们认识世界的所有工具的一个表述,当然数学,通过对这个表述的抽象,甚至可以说,是对抽象的进一步抽象,我们可以在更高维度来分析世界面对的真实问题,也许在更高维度里发现的解决方案,也能反过来映射到真实世界中的问题中去。

前几周在昆明西山,参观美术馆里

neo4j的cto描绘知识图谱的光明前景–一篇GraphRAG的宣言

Neo4J的cto,在火热朝天的大模型背景下,是如何来描绘知识图谱价值的呢?

为什么要使用知识图谱

因为不管fine tune还是rag,都不能提供具备一定置信度的正确答案(Vector-based RAG – in the same way as fine-tuning – increases the probability of a correct answer for many kinds of questions. However neither technique provides the certainty of a correct answer.)

把真正的知识(things not strings)与统计的文本技术结合,就能突破天花板。(bring knowledge about things into the mix of statistically-based text techniques)。

使用知识图谱的好处

  1. There’s a robust body of research proving that it gives you better answers to most if not ALL questions you might ask an LLM using normal vector-only RAG.
  2. That alone will be a huge driver of GraphRAG adoption. In addition to that, you get easier development thanks to data being visible when building your app.
  3. A third major advantage is that graphs can be readily understood and reasoned upon by humans as well as machines.

原文链接
https://neo4j.com/blog/graphrag-manifesto/