I disagree. They don't need to be reasonable so much as I now have a big stick to beat the journalist with if they aren't.

"I can't change my headlines"
"But it is your responsibility right?"
"No"
"Oh were you lying when you said it was"

I have 2 so far. One journalist agreed with no bother. The other frustratedly said they couldn't guarantee that and tried to negotiate. I said I was happy to take a bond, they said no, which suggested they weren't that confident.

Thanks to the people who use this forum.

I try and think about things better and it's great to have people to do so with, flawed as we are. In particularly @KatjaGrace and @Ben Pace. 

I hope we can figure it all out.

So far a journalist just said "sure". So n = 1 it's fine.

Trying out my new journalist strategy.

Did you reformat all the footnotes or do you have a tool for that?

My main takeaway from this series is that Carlsmith seems to be gesturing at some important things where I want a more diagrammy, mathsy approach to come along after. 

What does "Green" look like in more blue terms? When specifically might we want to be paperclippers and when not? Where are the edges of the different concepts?

So by my metric, Yudkowsky and Lintemandain's Dath Ilan isn't neutral, it's quite clearly lawful good, or attempting to be. And yet they care a lot about the laws of cognition.

So it seems to me that the laws of cognition can (should?) drive towards flouishing rather than pure knowledge increase. There might be things that we wish we didn't know for a bit. And ways to increase our strength to heal rather than our strength to harm. 

To me it seems a better rationality would be lawful good. 

Yeah I find the intention vs outcome thing difficult.

What do you think of "average expected value across small perturbations in your life". Like if you accidentally hit churchill with a car and so cause the UK to lose WW2 that feels notably less bad than deliberately trying to kill a much smaller number of people. In many nearby universes, you didn't kill churchill, but in many nearby universes that person did kill all those people.

Here is a 5 minute, spicy take of an alignment chart. 

What do you disagree with.

To try and preempt some questions:

Why is rationalism neutral?

It seems pretty plausible to me that if AI is bad, then rationalism did a lot to educate and spur on AI development. Sorry folks.

Why are e/accs and EAs in the same group.

In the quick moments I took to make this, I found both EA and E/acc pretty hard to predict and pretty uncertain in overall impact across some range of forecasts.