> For best results, our project structure needs to be set up with LLM workflows in mind. Specifically, we should carefully manage and keep the cognitive load required to understand and contribute code to a project at a minimum.
What's the main barrier to doing this all the time? Sounds like a good practice in general.
The article had a lot of high level talk about how they are using AI and other companies use “hard coded rules” that break on edge cases. What I don’t understand is how using either extreme could be true. An all ML approach wouldn’t follow things like stoplights or speed limits and an all “3D map” approach couldn’t account for any changes in the road.
I currently use a website to read hacker news that provides a similar function. http://hckrnews.com will let you browse the top x% of posts from each day.
What's the main barrier to doing this all the time? Sounds like a good practice in general.