原帖引用 · AI 翻译
Rohan Paul@rohanpaul_ai
@rahulchhabra07 Khosla 对押注下一个重大突破颇有心得，这件事意义重大。
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。
原文
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.
· UTC+8