Please tell me I’m not the only one that sees the irony in AI relying on classic search.
Obviously LLMs are good at some semantic understanding of the prompt context and are useful, but the irony is hilarious
Obviously LLMs are good at some semantic understanding of the prompt context and are useful, but the irony is hilarious
Navigating the graph, on the other hand, is the perfect task for PageRank.
The semantic understanding capabilities fit well for creating knowledge graphs.
Past the initial sensation, it is pretty linear that "something good at language" (an interface) be integrated with "something good at information retrieval" (the data). (Still sought what comes next, "something to give reliability to processing".)
I work in the LLM-augmented search space, so I might be a little too tuned in on this subject.