Musings About the Future of Search: A Return to the Past?

TL;DR

The paper explores the evolution of search from direct expert interaction to writing and web search, and discusses how large language models could revolutionize future search experiences by enabling direct engagement with expert models.

Contribution

It proposes reimagining search by leveraging large language models to facilitate direct interaction with expert-like AI systems, moving beyond static content and traditional search paradigms.

Findings

Historical progression from expert conversations to web search

Large language models enable direct engagement with expert systems

Future search may involve interactive AI-driven expert interactions

Abstract

When you have a question, the most effective way to have the question answered is to directly connect with experts on the topic and have a conversation with them. Prior to the invention of writing, this was the only way. Although effective, this solution exhibits scalability challenges. Writing allowed knowledge to be materialized, preserved, and replicated, enabling the development of different technologies over the centuries to connect information seekers with relevant information. This progression ultimately culminated in the ten-blue-links web search paradigm we're familiar with, just before the recent emergence of generative AI. However, we often forget that consuming static content is an imperfect solution. With the advent of large language models, it has become possible to develop a superior experience by allowing users to directly engage with experts. These interactions can of course satisfy information needs, but expert models can do so much more. This coming future requires reimagining search.