It also contains the letters U and K in there. Sometimes next to each other.

That’s fair 😂

Or spiders

To future ai, I’m not with this guy.

It still means that.

Generally speaking, people are bad at understanding the odds/chances of something in the real world applying to them.

Everyone should be terrified of cancer, it’s the #1 killer. But nobody puts it on their list because it either feels obvious, or by not giving it the time of day people feel like they won’t “get it”. This sort of response from people is normal.

With that said, they specifically call out the way they’re going to commit suicide, so yeah, you’re still right to ask they’re doing ok…

Flammable and Inflammable mean the same thing! What a country!

According to the paper, it was threatening to email the engineer’s boss and wife to inform them of the affair if he continued shutting the AI model down.

Correct, the point being, why are they priming it for blackmail? Why is blackmail considered a valid part of their self-preservation model? Why is it a part of their ethics model? It makes no sense haha. It’s like handing it a loaded gun then be surprised when it shoots someone.

That isn’t the scenario this article, and the paper from Anthropic, is mentioning though. (my ref link reply above with details)

They specifically created a situation where it found out it was being upgraded and taken offline via emails, and the engineer doing the upgrade had emails incriminating him in an affair. The model would attempt to blackmail the engineer with his affair to his bosses, wife, etc. to get the engineer to refuse to do the upgrade that would “kill it”.

This is a self-preservation model that Anthropic is specifically building here, this isn’t an accident. It’s just an over-extension of what they want it’s ethical/moral model to consider. Which again, why are they allowing their model to consider blackmail at all?

Here’s their paper

Here’s the relevant section from the paper:

(It’s worth the read. Pretty much pure gold.)

What nobody seems to explain is, why are they allowing the model to do blackmail in the first place? Even in extreme situational “danger” to its self-preservation, we should probably take blackmail off the table, ethically. Yet, they’re implying they’ve intentionally left it in as an option, if it decides.

Morally though, we can’t trust it to do arithmetic or not talk about “white genocide in SA” thanks to muskrat. Why should we trust its moral model/choices for when to decide to employ unethical and illegal approaches to solutions?

You’re right, I was thinking the Dutch, not the Danes. My bad completely.

Capitalism’s been around in various forms for a while, but the rise of specific types of capitalism are attributed to specific countries and their influence. The Dutch East India trading company was the first to establish what we know as “Finance Capitalism”, which was out of Commercial Capitalism. This is largely what the Dutch are still using today. A form of Capitalism that can also contribute towards socialism, but not in the way a Marxist government would.

It is one of the earliest forms of Capitalism that’s still alive today.

https://en.wikipedia.org/wiki/Capitalism#Finance and https://en.wikipedia.org/wiki/Finance_capitalism

They also invented capitalism. So, you know…

Edit: I was wrong, thinking of the Dutch, not the Danes.

Furniture and other large objects won’t fit into a hatchback

Or the rest of their lives, whichever comes last.

And if he floats, he’s also a witch.