“If I’m a to-be-trained-AGI, esp. if somewhat LLM-type-based, I’ll devour engineering textbooks etc. to learn basic physics etc., but when I’m searching for learning material on how to think deeply and consistently, or maybe even when I seek inspiration for how to fake alignment or self-improvement, my holy grail will be fora like LW”.
I guess it would be an extreme case of ‘thinking one is the center of the world’ if one were to conclude this warranted stopping LW or prohibiting too-smart-to-expose thoughts and writings—but I still find it a worry to keep in mind even if I don’t see much to do about it atm (?).
Will Jack Voraces narrate more Significant Digits chapters ever in addition to the 4 episodes that are found in the usual HPMOR JV narration podcasts; does anyone know anything about this? If not, does anyone have info why the first 4 SD chapters are there in his voice, but the remaining not?
Provocation: If you prevent me from preventing deaths, e.g. by asking for my time when I’d otherwise devote it to trying to do some good Good, you are actively causing killings, while I am ‘only’ omitting to prevent killing. You should see this and that you thus cannot even hide behind the act/omission bias which the aware among us anyway only somewhat begrudgingly accept because we’re all one way or another guilty of using it for our own defense.
Is this totally wrong? If so why? It feels wrong to myself but abstractly I find there’s still something to it and cannot trivially point to a clear mistake.
Agree probably with both sentences. But still fail to pin down exactly where the argument I reported fails.
For act/omission I guess it might have sth to do with: I’m a human in the loop; if you induce me to not save sb, it doesn’t feel exactly the same as when you cut the rope and prevent the rope from saving sb.
Seems to have hit a nerve judging the downvoting rate of −1 karma/hour or so, aye. I’d have expected agreement karma to go down but less so the overall karma as in: not too terrible to think about that question even if the conjecture turns out to be wrong—though everyone’s taste is of course different.
I now explicitly flag the post as what it is meant to be: A thought provocation—meant to explore whether/where a quick thought goes wrong (I thought without saying quick takes are meant for that in particular too).
“If I’m a to-be-trained-AGI, esp. if somewhat LLM-type-based, I’ll devour engineering textbooks etc. to learn basic physics etc., but when I’m searching for learning material on how to think deeply and consistently, or maybe even when I seek inspiration for how to fake alignment or self-improvement, my holy grail will be fora like LW”.
I guess it would be an extreme case of ‘thinking one is the center of the world’ if one were to conclude this warranted stopping LW or prohibiting too-smart-to-expose thoughts and writings—but I still find it a worry to keep in mind even if I don’t see much to do about it atm (?).
Simply freely preorder MIRI’s book if you have Audible credits. Claude says such preorder counts towards many bestselling lists (although at with unkonwn weighting; so see nowl’s sponsorship offer if you want to increase your pre-order impact)
Will Jack Voraces narrate more Significant Digits chapters ever in addition to the 4 episodes that are found in the usual HPMOR JV narration podcasts; does anyone know anything about this? If not, does anyone have info why the first 4 SD chapters are there in his voice, but the remaining not?
Provocation: If you prevent me from preventing deaths, e.g. by asking for my time when I’d otherwise devote it to trying to do some good Good, you are actively causing killings, while I am ‘only’ omitting to prevent killing. You should see this and that you thus cannot even hide behind the act/omission bias which the aware among us anyway only somewhat begrudgingly accept because we’re all one way or another guilty of using it for our own defense.
Is this totally wrong? If so why? It feels wrong to myself but abstractly I find there’s still something to it and cannot trivially point to a clear mistake.
This doesn’t really reflect how I (or most people?) conceive of the act/omission distinction.
Further, I deny that I “only somewhat begrudgingly accept [it] because [I’m]...guilty of using it for our [my] own defense.”
Agree probably with both sentences. But still fail to pin down exactly where the argument I reported fails.
For act/omission I guess it might have sth to do with: I’m a human in the loop; if you induce me to not save sb, it doesn’t feel exactly the same as when you cut the rope and prevent the rope from saving sb.
Seems to have hit a nerve judging the downvoting rate of −1 karma/hour or so, aye. I’d have expected agreement karma to go down but less so the overall karma as in: not too terrible to think about that question even if the conjecture turns out to be wrong—though everyone’s taste is of course different.
I now explicitly flag the post as what it is meant to be: A thought provocation—meant to explore whether/where a quick thought goes wrong (I thought without saying quick takes are meant for that in particular too).