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.
More from AGI Musings
- Robotaxi at 20-30 cents per mile could make parking garages obsolete within 10-15 years — SumitGup · 2026-09-06
- The opposite of agency is waiting — for permission, timing, and to feel ready — intellectronica · 2026-09-06
- Gary Marcus Gives Limited Endorsement to PauseAI, Podcast Incoming — GaryMarcus · 2026-09-06
- We're now in a 'trust can't verify' era, argues Kolt Regaskes — koltregaskes · 2026-09-06
- Sam Altman: Curing Cancer With AI Is 'Not Enough', Industry Should Aim Higher — SydSteyerhart · 2026-09-06
- Andrew Ng: prompting will be dead in 6 months, graphs are replacing it — nikola_mr64990 · 2026-09-06