Stephen Gruppetta

Read Stephen's Preface to Agents Unpacked if you're new here. You have used a large language model. You know the deal: a careful prompt gets a careful answer. A vague prompt gets a vague one. And the model itself does not keep anything from one conversation to the next, unless something external is holding that context for it. Agents work differently. They have parts that do things a plain LLM does not. These parts are what make an agent an agent. It is not just the model underneath.

“Great start by <athlete so and so>” “<Athlete so and so> got a poor start” You hear this in most commentary for 100m races. But as I’ve been learning more about sprinting biomechanics and how it links to the 100m race strategy, I started to disagree with commentators. And I’m not the only one. Then you start noticing a pattern: in most well-balanced 100m races, the athlete leading at 10m or 20m often does not win the race. And now I know why this makes sense.

My injuries in my first career were due to many reasons. Many of them connected. Part of the puzzle was the chain of events that a flat, weak foot led to. The postural issues led to poor form, injuries, and, even after my retirement, lower back issues. In my non-athletics years, I was curious about things and I explored different type of footwear. The literature was never too clear, in part because it’s nearly impossible to do gold-standard RCTs with things like footwear.