The performance on programming tasks is impressive, but I think the limited context window is still a big problem.
Very few of my day-to-day coding tasks are, "Implement a completely new program that does XYZ," but more like, "Modify a sizable existing code base to do XYZ in a way that's consistent with its existing data model and architecture." And the only way to do those kinds of tasks is to have enough context about the existing code base to know where everything should go and what existing patterns to follow.
But regardless, this does look like a significant step forward.
I would imagine that good IDE integration would summarise each module/file/function and feed high-level project overview (best case: with business project description provided by the user) and during CoT process model would be able to ask about more details (specific file/class/function).
Humans work on abstractions and I see no reason to believe that models cannot do the same
Very few of my day-to-day coding tasks are, "Implement a completely new program that does XYZ," but more like, "Modify a sizable existing code base to do XYZ in a way that's consistent with its existing data model and architecture." And the only way to do those kinds of tasks is to have enough context about the existing code base to know where everything should go and what existing patterns to follow.
But regardless, this does look like a significant step forward.