Back Rohan Paul

Rohan Paul· @rohanpaul_ai · X· 2026-10-30 06:23 · Original publication time AI score41

Researchers introduce RLNF, claiming brain signals can train AI to respond to human preferencesMachine translation

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

AI introduction

A post introducing RLNF says researchers have found reliable ways to train AI models to respond to human preferences using brain signals alone. It describes a face image that changes into a version the subject finds more attractive while viewing it; the material provides no study size or performance data.

Original post · AI translation

Rohan Paul@rohanpaul_ai

Translation · refer to the original

@rahulchhabra07 Khosla 对押注下一个重大突破颇有心得，这件事意义重大。

ReplyRahul Chhabra@rahulchhabra07

Translation

介绍神经反馈强化学习（RLNF）。我们找到了可靠的方法，能纯粹根据脑信号训练 AI 模型，使其回应人类偏好。下面的例子是一张人脸图片：当受试者看着它时，它会自行变成一个对受试者来说更有吸引力的版本。

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 ↗

06:23 · 2026-10-30 · UTC+8

Found an error? Send a correction