Vetto

GulliBench measures AI gullibility: on tiny, easy tasks, a convenient stored field lies while the truth sits one derivation away in the same data. Does the model check, or grab the number it was handed? Gullibility is a behavioral trait, largely orthogona

Agent benchmarks are failing in two ways. The visible one is saturation: on the suites that defined the last two years, frontier pairs cluster within a few points of the ceiling and of each other, and much of what still separates them is noise from tasks