Unsurprising, agents' solution to everything is writing more code. They'll happily reinvent the universe (a really crappy one).

Bug? More code. Unexpected behavior - read the docs? Couldn't find anything. Let's try another 1000 lines of workarounds. Still doesn't work? Write another 1000 lines to monkey-patch behavior. It sort of works now.

The actual solution is removing those 2000 lines and passing the correct argument on line 25 which is clearly documented. Most humans would never do that because we're too lazy but it's so easy to generate slop at an exponential rate and blow up the LOC metrics.

I think that in my career I have absolutely seen multiple times people making absolutely horrible architectural approaches where passing a parameter would suffice. Inventing and building basically whole universe instead of doing a bit of research.

With LLM coding I already have seen agent pointing out easier solutions because agent is not scared of or tired by reading existing code. Whereas most of developers want to write „their code” not read someone’s else’s code.