Neuroscientist Says RLHF Erases Idea Attribution in AI

Computational neuroscientist Konrad Kording observes that AI credits inventors but rarely attributes the original sources of ideas, and argues that RLHF actively erases these traces of provenance in model answers.

2026-09-12 ~ 2026-09-12 · 3 related posts

• Kording Lab: AI credits inventors but almost never credits the original source of an idea — KordingLab · 2026-09-12
• Kording Lab: RLHF strips idea attribution from AI answers because users prefer to feel it's theirs — KordingLab · 2026-09-12
• Kording: RLHF Erases the Original Source of Ideas From AI-Explained Attribution — KordingLab · 2026-09-12