Back Rohan Paul

Rohan Paul· @rohanpaul_ai · X· 2026-10-30 06:25 · Original publication time AI score41

RLNF demonstrates face image adjustments using brain signalsMachine translation

Automatically verified and published · Generated and evidence-checked automatically; not reviewed by a human.

AI introduction

RLNF's introducers say they have found ways to train AI models to respond to personal preferences using brain signals alone. In the example shown, a face image changes as a subject looks at it, moving toward a version the subject finds more attractive; the material gives no study size or independent validation results.

Original post · AI translation

Rohan Paul@rohanpaul_ai

Translation · refer to the original

这真是更上一层楼的东西。

基于神经反馈的强化学习（RLNF）

一个 AI 图像模型会在你观看图片时读取你的大脑反应，了解你个人觉得什么有吸引力，然后改变图片以获得更高评分，而无需你提供评分、点击或提示词。https://t.co/FzbepNthA3

QuoteRahul Chhabra@rahulchhabra07

Translation

隆重介绍基于神经反馈的强化学习（RLNF）。我们已经找到了可靠的方法，能够仅凭大脑信号训练 AI 模型，使其响应人类偏好。下面的示例是一张人脸图片；当受试者看着它时，图片会自行变成对该受试者更有吸引力的版本。

Original

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.

View this post on X ↗

06:25 · 2026-10-30 · UTC+8

Found an error? Send a correction