Copasetic Flow

 I took time to play with a new Dolt enabled app example called Quorum last night. Quorum sets 13 LLM agents with different defined personas  loose on a users question. The agents come up with solutions to the question and then discuss their individual solutions with each other to arrive at a consensus. There's much more detail in this blog post that accompanies the app. Quorum is cool. It is not, however, what I wanted to talk aobut here. Instead, I'm going to focus on the blog post for the app. In short, I'm very excited to see ideas that I've used to manage verification processes for years get codified into tools for LLM agents. Here's one of the important parts " I can shut down the app, lose the server, or disappear entirely — and the deliberation history remains, publicly accessible and cryptographically verified. " Imagine what an engineer can do to work back through their debug hypothesis tree with that sort of infrastructure! As the article'...

While I was out of town for work, the gang—7 y.o. No. One, 5 y.o. No. Two, and 3 y.o. No. Three—continued their CSFirst work with my partner.  Google cleverly refers to CSFirst as a club.  No. One took it a step further and decided the club was in fact a camp, you know, like summer camp.  One decided that as a camp they of course needed a banner, and went to work. I heard during the day that the gang had worked together to set up One’s sandbox—the web app where CSFirst students do their programming work. I also heard that they were pair-programming; I’m a huge fan of pair-programming, so I was excited to get home last night to find out how everything went. NOTE:  For those who aren’t into programming in general, or agile programming methodologies in particular, pair-programming is the practice of two programmers sitting down at one screen to work on a piece of code.  As one programmer types, the other checks their work.  They both discuss ideas for the...