Definitely sounds like clickbait, but this is a genuine problem I've been facing on my more complex projects. I was trying to work around it by making lots of .md files that contain context for various components of the app, as well as ones that "statefully" represent our steps along larger refactors, allowing things to persist across sessions. But that requires the hygiene/discipline of remembering to have the model update those.
Now… how much of our tiny context window does this eat up? And what if we're working on something very different from the previous tasks; might that irrelevant context risk confusing the model?
Also, how does this work if I work on multiple projects across different directories? Will it know to not get those mixed up?
Now… how much of our tiny context window does this eat up? And what if we're working on something very different from the previous tasks; might that irrelevant context risk confusing the model?
Also, how does this work if I work on multiple projects across different directories? Will it know to not get those mixed up?