But this seems like the standard in my experience. Which is odd, because it really isn’t be that hard to say things which are both positive and true.

I think people are drawn towards the lies because it’s a more active form of self gaslighting.

Phrased like that, it almost seems impossible - doesn’t an ontology shift by definition entail throwing away your old abstractions and replacing them with new (hopefully better) ones?

Well, Guaranteed Translatability (tho it does have some strong assumptions which we need to grapple with) wants to say something like this: if two different agents are both modeling a certain section of the world correctly, then you should be able to translate both ways between their concepts which explain that section.

This works with one agent which is learning, comparing between two different times: if an agent had a good model of a part of the world back in the day with its naive ontology, and now it has a bigger or different ontology which is still making the same predictions over this part of the world, its old concepts should be expressible in terms of the new concepts and vice versa!

In other words, you have guaranteed translatability between the ontologies of past and future versions of the same agent, insofar as both versions of the agent make the same predictions and are using natural abstractions; and you can restrict this to a subset of observables.

So two agents don’t have to agree on absolutely everything in the world, just on one bit of it; and they don’t get translatability everywhere, just with regards to this particular bit of the world which they agree on.

I have my first XL socks coming in the mail tomorrow… I can’t wait to no longer have to struggle when I take off my socks.

But I gotta say after trying out Antigravity 2, I appreciate the speed. It is quite nice.

If we want to pause, it’s +EV for China to agree to a coordinated pause even if they don’t take x-risk seriously, as long as they recognize that if we continue the way we are currently going and there is no catastrophe, the US will develop transformative AI first which will give it a huge and lasting economic and military advantage over China.

Youtube

We don’t have an explicit utility function, but we have a set of reward signals and pretend that there is some true hidden utility function which we try to model with uncertainty. Then we use our reward signals to update our map of a (fictional) utility function.

This lets us protect against value drift and wireheading by resisting things which would cause our reward signals to give us worse information about our imagined true utility function.

Specifically the intuition that qualia are irreducible is a priori reasonable but leads to all sorts of paradoxes

And since we have no principled reason to believe it it should be quite cheap to discard

This does not mean there aren’t lots of things about consciousness which I am confused about and find mysterious

Anyway if you think you can explain something I am missing contact me