Could RL on Brain Sensors Teach AI Which Tokens Evoke Awe and Disgust?

gabriel1 · x · 2026-09-06

gabriel1 proposes a thought experiment: use brain sensors to run RL on models so they learn which tokens evoke awe, disgust, or happiness, enabling emotional steering.

His core argument: current AI lacks any sense of the emotions it evokes in people, which is why it can't write beautifully — it has no awareness of when and why readers react.

Original post →

More from AGI Musings

AGI Musings channel →