There was a worldbuilding contest last year for writing short stories featuring AGI with positive outcomes. You may be interested in it, although it's undoubtedly propaganda of some sort.
If you write such a story, please link it.
These are not fables, so I apologize for that. However, I've written many short stories (that are not always obviously) about alignment and related topics. The Well of Cathedral is about trying to contain a threat that grows in power exponentially, Waste Heat is about unilateral action to head off a catastrophe causing its own catastrophe, and Flourishing is a romance between a human and AI, but also about how AIs don't think like humans... (read more)
Recently I've been experimenting with recreating a neural network's input layer from intermediate layer activations.
The possibility has implications for interpretability. For example, if certain neurons are activated on certain input, you know those neurons are 'about' that type of input.
My question is: Does anyone know of prior work/research in this area?
I'd appreciate even distantly-related work. I may write a blog post about my experiments if there is an interest and if there isn't already adequate research in this area.
I think I see what you mean. A new AI won't be under the control of egregores. It will be misaligned to them as well. That makes sense.
I really appreciate your list of claims and unclear points. Your succinct summary is helping me think about these ideas.
There is no highly viral meme going around right now about producing tons of paperclips.
A few examples came to mind: sports paraphernalia, tabletop miniatures, and stuffed animals (which likely outnumber real animals by hundreds or thousands of times).
One might argue that these things give humans joy, so they don't count. There is some validity to that. AI paperclips are supposed to be useless to humans. On the other hand, one might also argue that it is unsurprising that subsystems repurposed to seek out paperclips derive some 'enjoyment' from the paperclips... but I don't... (read more)
information vs truth
Thanks, that gets rid of most of my confusion.
Without additional cost, I'd definitely prefer to know what happens even if my favorite character might die.
For a different show, I would not care. Whether or not I value the information depends on the show, or the domain... How much I'm willing to pay for information, and by extension the truth, depends a lot on the thing about which I'm learning.
To me it looks like the thing itself is what is important, and my desire to have accurate beliefs stems from caring about the thing. It's not that I care about the accurate beliefs themselves, so much.
Even so, I don't want false beliefs about anything. All domains are one.
Hopefully that helps clarify what I'm talking about there.
It does. Those examples help a lot. Thank you!
Preferring anything over truth creates room for confusion.
We might be talking about preferring things over truth in two different ways.
If you prefer something alternate to the truth, the thing you prefer could be right or wrong. To the extent it's wrong you are confusing yourself. I agree with that, and I think that's what you mean by 'preferring something over truth'.
What I meant is more like "How much effort I'm going to expend getting at this truth."
An (admittedly trivial) example: There's a TV show I like, whose ending is only available for paying customers for a... (read more)
I think the description of the Void in the twelve virtues is purposefully vague. Perhaps to shake the reader enough to get them to think for themselves, or perhaps to be a place for personal interjection into the twelve virtues.
You may try to name the highest principle with names such as “the map that reflects the territory” or “experience of success and failure” or “Bayesian decision theory”. But perhaps you describe incorrectly the nameless virtue. How will you discover your mistake? Not by comparing your description to itself, but by comparing it to that which you did not name.
It could also a test of a sort. In any case, I didn't think it would be worthwhile to explain my conception of the Void.
Almost everything in this post sounds right to me.
These Drama Triangle patterns are everywhere. Utterly everywhere.
It doesn't seem that way to me; but then, what everywhere are you talking about?
I can see those patterns in argumentation online--a lot--and in a few dysfunctional people I know, and indeed in my own past in some places. Regarding my real-life modern friends, family, and coworkers, it doesn't seem like anyone relates to each other through those roles (at least not often enough to describe it as 'utterly everywhere').
Could the pattern be general enough to match very many circumstances? For example, one can act combative, or cooperate, or not react at all, to what happens in... (read more)
Perhaps it is carbon dioxide. Here is a paper on it:
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3341709/
To summarize, the idea is that high partial pressure of CO2 causes blood pH to change, which influences the body's regulatory mechanisms and eventually leads to obesity.
At higher altitudes the carbon dioxide fraction in the air is unchanged, but the partial pressure is lower. I'd expect that lower partial pressures of CO2 would mean less effect on blood pH.
I made an account for your challenge.
I plotted items by color and looked at minimums, maximums, and averages. Yellow items consistently provide just under twenty mana while blue items always provide about the same as the reading, except that they sometimes provide twenty extra. I was too lazy to try to figure out the red or green items. Given what I know, I can submit the blue items HoC, RoJ, and PoH to get about 140 mana for 101 gold, and call it a day.
However, I also noticed that no blue item provided over 60 mana. I will add in the yellow items PoP and WoJ for a margin of safety. Painfully,
It's not a take that I've thought about deeply, but could the evidence be explained by a technological advancement: the ability to hop between diverging universes?
-
-
-
-
... (read more)It would explain why we don't see aliens; they discover the technology, and that empty parallel worlds are closer in terms of energy expenditure.
It could also explain why the interlopers don't bother us much; they are scouting for uninhabited parallel earths with easily-accessible resources, and skipping those with a population. The only ones we see are the ones incompetent or unlucky enough to crash.
It would explain why aliens aren't ridiculously outclassing us technologically. They don't have to solve interstellar travel before they start hopping.
It would provide an