TRUSTED BY FRONTIER AI LABS
We shape how models learn. Data is not the bottleneck. How experience reaches the model is.
Vetto designs learning experiences, feedback systems, and evaluations that directly improve real-world model capability.
SlopCode: Vetto’s version
Built on our own tasks. Coding agents are usually ranked by whether their final answer works. SlopCode Vetted asks a second question: what kind of codebase do they leave behind while getting there?
SlopCode Vetted evaluates coding agents across successive requirements, measuring both correctness and the codebases they leave behind across 50 tasks and six models.
