Not clamp per se, but there are enough tiny snippets which can have off by one or other issues not relevant to when you think about the problem description.
Senior engineer: "you shouldn't have to use llm to do simple things"
Their boss: "hey I need you to write this thing in Go for performance reasons"
Senior engineer: "you shouldn't make me learn new languages, js is plenty performant for this task just install a new server. why are they making us use all these new tools? everything is new again, blah blah excuses excuses"
vs.
Boss: "hey can you write this in go"
Vibe Coder: "write this loop to ignore the first semicolon in this response", and then proceeds to move on with life.
It seems like when people evaluate the merits of what a code generation ai agent should and shouldn't do, they leave out a lot of their implicit assumptions about how project should work and their own theory of mind around coding.
Sure. Then all the common tools that you need should be bundled into a library. I should not be importing 1000 string manipulation libs with a single function each.
