# Researchers train AI models on preferences decoded from brain signals

> Original title: Just insane research direction. It's like preference data straight from the brain.

- Source: Elvis Saravia
- Published: 2026-10-29T21:47:23.000Z
- Bad Influence: https://badinfluence.news/items/wk83qq76iptbfzfb0v87u3udu
- Original: https://x.com/omarsar0/status/2115923475126800699

## Summary

The researchers introduce reinforcement learning with neural feedback (RLNF), which trains AI models to respond to human preferences using brain signals alone. A demonstration shows a face that transforms into a version the viewer finds more attractive, based on their neural responses. The poster says the approach could combine reinforcement learning, brain-computer interfaces and agents to enable personal intelligence at scale.

## Post

Just insane research direction. It's like preference data straight from the brain. 

They introduce RL with Neural Feedback (RLNF). It trains AI models on preferences decoded from brain signals.

I did BCI research back in the day, so this feels like the kind of research direction where all these technologies (RL, BCI, agents, etc.) can compound. I think this kind of work could really unleash true personal intelligence at scale.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHV1EuStWAAASRto.jpg&mode=thumb&exp=1793577600&sig=8bcaed123db8acf5)

## Quoted post @rahulchhabra07

> Introducing RL with Neural Feedback (RLNF). We have found reliable ways to train AI models to respond to human preferences purely from brain signals.
> 
> The example below is a picture of a face that self-transforms into a more attractive version for the subject as they are looking at it.

https://x.com/rahulchhabra07/status/2115918744308658325