zlacker

>>net01+(OP)
Check in unreviewed slop straight into the codebase. Awesome.

>>r0ckar+v3
Now developers can produce 20x the slop and refactor at 5x speed.

>>postal+04
In my experience in VSCode, Claude 3.7 produced more unsolicited slop, whereas GPT-4.1 didn't. Claude aggressively paid attention to type compatibility. Each model would have its strengths.