Why wonder if this is “as good as LLMs can get” when we saw such a huge improvement between Claude 3.7 and Claude 4, released what, a couple weeks ago? Of course it isn’t as good as LLMs can get. Give it 3 more weeks and you’ll see it get better again.
I don’t doubt LLMs will become better assistants over time, as you said every few weeks. I more mean if LLMs will cross the assistant to compiler chasm where we don’t have to think about the code anymore and can focus on just the features
