Matej Šprogar

Matej Šprogar

Grounded in the premise that high-level intelligence can emerge from low-level signal processing, we advance a hypothesis regarding low-level requirements necessary for artificial general intelligence. The proposed requirements characterise core properties of systems that learn through prediction over spatially and temporally structured signals with initially unknown semantic content. They include a selection of basic principles observed in cognitive neuroscience, from learning from an uninformed state to real-time liveness. To enable empirical testing and hypothesis rejection, we introduce an operational testbed composed of transparent and reusable tests, one per requirement. To date, no non-intelligent system has been identified or reported as successfully passing the testbed. Pending such a counterexample, the testbed serves as a candidate empirical milestone toward general intelligence. The reference implementation of the testbed is publicly available.

Matej Šprogar

Current AI systems demonstrate remarkable capabilities yet remain specialised, in part because no unified measure of general intelligence has been established. Existing evaluation frameworks, which focus primarily on language or perception tasks, offer limited insight into generality. The Artificial General Intelligence Testbed (AGITB) introduces a complementary benchmarking suite of fourteen elementary tests, with thirteen implemented as fully automated procedures. AGITB evaluates models on their ability to forecast the next input in a temporal sequence, step by step, without pretraining, symbolic manipulation, or semantic grounding. The framework isolates core computational invariants, such as determinism, sensitivity, and generalisation, that parallel principles of biological information processing. Designed to resist brute-force or memorisation-based strategies, AGITB enforces unbiased and autonomous learning. The human cortex satisfies all tests, whereas no current AI system meets the full AGITB criteria, demonstrating its value as a rigorous, interpretable, and actionable benchmark for evaluating progress toward artificial general intelligence. A reference implementation of AGITB is freely available on GitHub.