[lukeschlather]

At the core this is a hardware problem. 1M tokens is simply not enough context to understand a codebase the way a human would understand it. Being able to selectively forget is potentially a very valuable power, but right now it's a substitute for a human's ability to remember the rough shape of something, decide it's uninteresting, and remember that it is uninteresting.

They talk about memory only being useful when guided by a human, I think the proper solution is deeper than that, it probably involves feeding the entire codebase and every agent session into a finetuning of the model, though at that point you might want some guidance to avoid feeding certain sessions into the model. Or maybe not, maybe the bitter lesson applies.

[kolinko]

1M context - at least with most of the projects I ever worked with, 1M, or even 100k would be enough to explain in broad strokes the class/project/deployment structure, and a window of 200-500k to explain the specific issue at hand.