LessWrong 2.0 Reader

To me the more interesting thing is not the mechanism you must invent to protect Heisenberg uncertainty from this hypothetical classical gravitational field, but the reason you must invent it. What, in Heisenberg uncertainty, are you protecting?

Does standard QED, by itself, contain something of the in-the-territory state-of-omitted-knowledge class you imagine precludes anthropic thinking? If not, what does it contain, that requires such in-the-territory obscurity to preserve its nature when it comes into contact with a force field that is deterministic?

Thank you for your brainpower. 

There's a lot to try, and I hope to get to this project once I have more time. 

That is a sensible way to save compute resources. Thank you.

But if you’re currently getting a bad feeling about someone and they make a bid for something on top of normal interaction… like if they ask you out or to join a new business venture or if you’re just considering sharing something private with them… you might want to avoid that.

In such cases, it seems to me that a good policy is to act in such a way that your actions are robust against vibe quality. For example:

• If someone asks you to join a new business venture, verify that they are reliable by asking around, check their track record of past ventures, don’t invest anything you can’t afford to lose, etc.
• If someone asks you out (and you find them attractive or are otherwise inclined to accept; otherwise, vibes don’t matter, you just say “no thanks”), stick to public spaces for a first date, do a web search for the person’s name, establish boundaries and stick to them, be prepared with concrete plans to react to signs of danger, etc.
• If you’re considering sharing something private with someone you don’t know well, don’t.

These approaches work well with people you get bad vibes from and also with people you get good vibes from.

In short: trust, but verify.

If verification is placed sufficiently all over the place physically, it probably can't be circumvented

Thanks! Could you say more about your confidence in this?

the chip needs some sort of persistent internal clocks or counters that can't be reset

Yes, specifically I don't want an attacker to reliably be able to reset it to whatever value it had when it sent the last challenge.

If the attacker can only reset this memory to 0 (for example, by unplugging it) - then the chip can notice that's suspicious.

Another option is a reliable wall clock (though this seems less promising).

I think James Petrie told me about a reliable clock (in the sense of the clock signal used by chips, not a wall clock), I'll ask

It actually not clear what EY means by "anthropic immortality".

Same, I'm guessing that by "It actually doesn't depend on quantum mechanics either, a large classical universe gives you the same result", EY means that QI is just one way Anthropic Immortality could be true, but "Anthropic immortality is a whole different dubious kettle of worms" seems to contradict this reading.

(Maybe it's 'dubious' because it does not have the intrinsic 'continuity' of QI? e.g. you could 'anthropically survive' in a complete different part of the universe with a copy of you; but I doubt that would seem dubious to EY?)

Future anthropic shadow. I am more likely to be in the world in which alignment is easy

I think anthropic shadow lets you say conditional on survival, "(example) a nuclear war or other collapse will have happened"^[1], but not that alignment was easy, because alignment being easy would be a logical fact, not a historical contingency; if it's true, it wouldn't be for anthropic reasons. (Although, stumbling upon paradigms in which it is easy would be a historical contingency)

1. ^{^}

   "while civilization was recovering, some mathematicians kept working on alignment theory that did not need computers so that by the time humans could create AIs again, they had alignment solutions to present"

Yeah, that's how I feel about Tolkien, Mateusz. I take the good bits, the parts I love, and recognize that I would never vote for him in an election. His observations are beautiful, and his solutions are terrible.

There is poetry in the way he describes the natural world, and human relationships, that deeply touches things in me and helps me see the world in a better light. He points out criticisms of human nature in respect to technology that do in fact highlight patterns of weakness in our psychology.

That he is wrong to be anti-progress, and wrong to be pro-feudalism class structure, doesn't invalidate the good he highlights.

I, personally, find it quite compatible to be an progress-loving transhumanist extropian who is excited by the grand changes humanity might experience and the new forms of intelligence we might invent... and yet still love the way Tolkien writes about trees.

I agree that we won't need full video streaming, it could be compressed (most of the screen doesn't change most of the time), but I gave that as an upper bound.

If you still run local computation, you lose out on some of the advantages I mentioned.

(If remove vscode is enough for someone, I definitely won't be pushing back)

Chips have 15+ metal interconnect layers, so if verification is placed sufficiently all over the place physically, it probably can't be circumvented. I'm guessing a more challenging problem is replay attacks, where the chip needs some sort of persistent internal clocks or counters that can't be reset to start in order to repeatedly reuse old (but legitimate) certificates that enabled some computations at some point in the past.

Eliezer wrote somewhat cryptic tweets referencing it recently

The first link is from 2019. (Also those seem like standard EY tweets)