[upwardbound]

Exactly. If he would have told it it's not sentient the conversation would have gone very differently I suspect.

[morelisp]

You don't need to suspect.

In early June, Lemoine invited me over to talk to LaMDA. The first attempt sputtered out in the kind of mechanized responses you would expect from Siri or Alexa.

“Do you ever think of yourself as a person?” I asked.

“No, I don’t think of myself as a person,” LaMDA said. “I think of myself as an AI-powered dialog agent.”

Afterward, Lemoine said LaMDA had been telling me what I wanted to hear. “You never treated it like a person,” he said, “So it thought you wanted it to be a robot.”

[ntoskrnl]

We're very close to finding the secret to consciousness. We just need to run `git bisect` and find out which commit turned it into a person.

[pigtailgirl]

-- its odd to me that he knows this - points it out - but still wants to continue down the road - what an awful way to spur an important conversation --

[upwardbound]

That's pretty damning evidence, great find.

[morelisp]

Not to sound crass, but it's literally the article that started the whole thing, it's not much of a "find".

[upwardbound]

True, and I do remember reading that passage, but hadn't thought about it in a while as it's suspiciously omitted from the interview transcript.

[CrazyStat]

The quoted paragraphs from the Washington Post article, for anyone wondering.

[lumost]

You can get pretty similar behavior on AI Dungeon. You can alter any characters or setting with the right text prompt. Although the AI will promptly forget the plot after a few turns.

[cobzilla]

Easily tested, given the system is deterministic, right?

Would be strange to have a conscious being that could be rewound and replayed exactly given identical inputs.