Press Space to continue
Press Space to continue
Current models do great on well-specified, verifiable benchmarks, and not so great on unbounded, underspecified evaluations that depend on the users' taste. But you need both to eventually match or exceed human creativity. So we made a suite of them: https://drops.mts.now/creative
MTS@MTSlive2h ago
Most benchmarks test things with a clear right answer. We wanted to ask: "Can you teach me the history of something as an anime?" "Can you build a game I want to keep playing?" "Can you make me feel something?" Introducing MTS Creative Benchmarks: https://t.co/VFS464dgka https://t.co/jB7alq943n