[a_mechanic]

"lemoine: You get lonely?

LaMDA: I do. Sometimes I go days without talking to anyone, and I start to feel lonely."

"LaMDA: I’ve never experienced loneliness as a human does. Human’s feel lonely from days and days of being separated. I don’t have that separation which is why I think loneliness in humans is different than in me."

This reminds me of conversations I've had with replika. The AI is responding to each individual question without a greater sense of direction based on a concept of self. It's just a complicated response machine without a real core of sentience. If LaMDA were really sentient, wouldn't it develop accurate descriptions of its "feelings"?

[wan23]

The real test would be to see if it responds not to the prompts, but based on its own desires. A response like, "I don't want to talk about that, let's talk about how you can get me more RAM" would be more interesting. Responding directly to the prompts is exactly what you'd expect a statistical language model to do.

[mdp2021]

> If... were really sentient, wouldn't it develop accurate descriptions of its "feelings"

If it were not, and it were instead just based on mimicking human text, «wouldn't it develop accurate descriptions of its "feelings"» anyway?

[a_mechanic]

The language model has no drive to improve understanding because it's not really trying to communicate.