x

LESSWRONG

LW

Muhammad Zane A — LessWrong

Muhammad Zane A

Muhammad Zane A

Message

I'm currently working as a Director at latent minds.

My work focuses on the emergence of self models.

1

1mo

Muhammad Zane A

I'm currently working as a Director at latent minds.

My work focuses on the emergence of self models.

Is functional welfare speakable?

If a model has an internal state that changes how it behaves we investigate whether it can talk about that state. In our new post, we test this for a functional welfare direction found in a small open model before and after RL. “Functional welfare” here means an internal direction...