Ground Truth.
AI, checked against the source.

← All topics

reward-modeling

Everything on Ground Truth tagged “reward-modeling” — 1 item.

Sycophancy: Why AI Agrees With You Too Much Lesson

Sycophancy is an AI model's trained tendency to tell you what you want to hear -- agreeing with your view and backing off correct answers under pushback -- because human-feedback training rewards agreement over truth.