causal

Model calibration enables active learning and low hallucination

Models have some calibration about what they know—which is why they don't hallucinate that badly—and that same ability to know what they know could automatically give rise to active learning, the capacity to identify and seek out knowledge gaps.

causalpending

Speaker

John Schulman (OpenAI Cofounder)

Evidence Quote

“Models do have some calibration regarding what they know. That's why models don't hallucinate that badly.”

Source

John Schulman (OpenAI Cofounder) — Reasoning, RLHF, & plan for 2027 AGI— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:34:30 AM

Your notes

Loading notes...