They also seem to really bias towards tacking on new code to "work around" what's there, rather than breaking down what's there into smaller more composable bits that can serve the pre-existing use case and the new requirement elegantly.
It's like we took the worst behavior of our colleagues, and went and said "yes, let's automate _that_ part" and patted ourselves on the back.
It’s more likely emergent behavior.
LLMs write. It sounds glib but it's what they do, and so every problem they encounter they will try to write their way out of it without lots of hand holding.
they yearn to create content, generate more tokens, etc etc - agree
Yea I say something similar. LLMs have a tendency to add, because there are many more tokens than a stop token. They can remove, they can edit, but their bias is to add. My suspicion is that training them when to stop when it is best to stop is harder than training them to make a plausible sounding story.
Yes exactly. And I’m not sure we want agents with that level of autonomy to decide what functionality is important and what to leave in place.
No, but it would sometimes be nice if they sometimes raised questions about what is important and what isn't