> The first thing I want AGI to do is to be able to tell me when it doesn’t know something,
In my demo, the llm agent asks followup questions to understand the users problem. Then it first attempts to answer those questions using context and function calling. When a question cannot be answered this way it is forwarded to the user. In other words, it tells you when it doesn't know something.
In my demo, the llm agent asks followup questions to understand the users problem. Then it first attempts to answer those questions using context and function calling. When a question cannot be answered this way it is forwarded to the user. In other words, it tells you when it doesn't know something.