Measuring progress toward AGI: A cognitive framework

6 hours ago

Artificial General Intelligence (AGI) has potential to accelerate scientific discovery and solve pressing human problems.
A new paper titled 'Measuring Progress Toward AGI: A Cognitive Taxonomy' provides a scientific foundation for understanding AI cognitive capabilities.
The framework identifies 10 key cognitive abilities important for AGI, including perception, generation, attention, learning, memory, reasoning, metacognition, executive functions, problem solving, and social cognition.
A three-stage evaluation protocol is proposed to benchmark AI system performance relative to human capabilities.
A Kaggle hackathon is launched to design evaluations for five cognitive abilities with the largest evaluation gaps: learning, metacognition, attention, executive functions, and social cognition.
The hackathon offers a total prize pool of $200,000, with submissions open from March 17 to April 16, and results announced on June 1.

Hasty Briefsbeta