I don’t want to fetch information from multiple sources. The information that I want and need has to come to me. And that’s what AI agents are helping me do right now.
I want to know what’s going on in the tech space by going to Hacker News, but I don’t want to get curious about huge number of toxic comments. So I want that information to come to me. One of the tasks my agent does now is visit Hacker News and grab summaries of anything with 200 points or higher. It pushes the summary to my blog, so now I have one place where I go read summaries of hot topics. No comment sections. No rabbit holes. Just the signal.
Now I just think about what to ask, how to ask.
I am just trying to figure out ways to ask questions “better.” In some ways, I want my first question to use tons of tokens because it’s so original, so different than any other question that was asked to an LLM. But in other ways, I want my questions to be token-efficient because they were crafted so well through years of experience, domain knowledge, and my brain’s raw power.
But the important thing is that I am always learning through actually using AI every day.