Tag
A software engineer discusses the etiquette of sharing AI-generated content with teammates, proposing the principle that if you request human attention, you should demonstrate human effort by adding your own commentary.
This paper tests whether varying inference-time reasoning effort affects the alignment between large reasoning models' chain-of-thought lengths and human reaction times. Results show alignment is invariant to effort perturbations, suggesting it is a training-time achievement.
This paper introduces engagement forecasting for intelligent tutoring systems, predicting weekly minutes practiced and new skills mastered using interaction logs from 425 middle-school students. Feature-based models reduce error by 22-33% over heuristic baselines, offering explainable patterns for tutor-learner goal setting.