Building a Codebase Classifier with Jev
A developer shares building a codebase classifier with Jev, suggesting it may solve overengineered code from agents, and asks what to test next.
dealer.eth leaked the JEV stack he runs his agents on, noting agents don't fail at writing code but at deciding which file to open, which hunk matters, whether to run a command, and whether they're actually done.
I LEAKED THE JEV STACK I RUN MY AGENTS ON, IT CAUGHT 11 OF THEM IN ONE NIGHT BEFORE THEY BROKE SOMETHING Agents don't fail at writing code, they fail at deciding, which file to open, which hunk matters, whether to run that command, whether they're actually done. Every one of