New lab preprint! AI assistants are myopically helpful. Unlike caregivers that want to empower people and grow their long term autonomy, AI assistants interrupt independent thinking and jump right to the answer.
Deciding when to jump in and help someone—and when to hold back and let them work through it—is something humans navigate constantly. How do AI assistants handle this tradeoff?
We introduce Int-Bench, a framework for evaluating interventions during problem-solving tasks.