LLMs have three new capabilities that change the nature of search:
Intuitive leaps: LLMs can answer poorly written questions with spooky-accurate answers. Even when users only vaguely gesture towards what they are trying to say, LLMs can intuit what they actually mean.
Ingest and understand new materials: Because it’s easy to integrate an LLM into
When people engage with LLMs, they ask for suggestions, refer to shared history and context, and build on previous responses. Their top expressed need is for systems to have a back-and-forth with them, to help them learn, to help them narrow things down, and to let them know what the system needs to provide better responses.