Sorry don’t post here, but there:
https://www.lesswrong.com/posts/hM3KXEFwQ5jnKLzQj/open-thread-winter-2024-2025
roland
Karma: 526
Update: Confusion of the Inverse
Is there an aphorism regarding the mistake P(E|H) = P(H|E) ?
Suggestions:
Thou shalt not reverse thy probabilities!
Thou shalt not mix up thy probabilities!
Thou shalt not invert thy probabilities! -- Based on Confusion of the Inverse
Arbital conditional probability
Example 2
Suppose you’re Sherlock Holmes investigating a case in which a red hair was left at the scene of the crime.
The Scotland Yard detective says, “Aha! Then it’s Miss Scarlet. She has red hair, so if she was the murderer she almost certainly would have left a red hair there. P(redhair∣Scarlet)=99%, let’s say, which is a near-certain conviction, so we’re done.”
“But no,” replies Sherlock Holmes. “You see, but you do not correctly track the meaning of the conditional probabilities, detective. The knowledge we require for a conviction is not P(redhair∣Scarlet), the chance that Miss Scarlet would leave a red hair, but rather P(Scarlet∣redhair), the chance that this red hair was left by Scarlet. There are other people in this city who have red hair.”
“So you’re saying...” the detective said slowly, “that P(redhair∣Scarlet) is actually much lower than 1?”
“No, detective. I am saying that just because P(redhair∣Scarlet) is high does not imply that P(Scarlet∣redhair) is high. It is the latter probability in which we are interested—the degree to which, knowing that a red hair was left at the scene, we infer that Miss Scarlet was the murderer. This is not the same quantity as the degree to which, assuming Miss Scarlet was the murderer, we would guess that she might leave a red hair.”
“But surely,” said the detective, “these two probabilities cannot be entirely unrelated?”
“Ah, well, for that, you must read up on Bayes’ rule.”
Bayes for arguments: how do you quantify P(E|H) when E is an argument? E.g. I present you a strong argument supporting Hypothesis H, how can you put a number on that?
His other books are also great.
that it’s reasonably for Eliezer to not think that marginally writing more will drastically change things from his perspective.
Scientific breakthroughs live on the margins, so if he has guesses on how to achieve alignment sharing them could make a huge difference.
I have guesses
Even a small probability of solving alignment should have big expected utility modulo exfohazard. So why not share your guesses?
Weighted step ups instead of squats
Lunges vs weighted step ups?
Source please
why would a weighted step up be better and safer than a squat?
Weighted step ups instead of squats can be loaded quite heavy.
What are the advantages of weighted step ups vs squats without bending your knees too much? Squats would have the advantage of greater stability and only having to do half the reps.
Valence-Owning
Could you please give a definition of the word valence? The definition I found doesn’t make sense to me: https://en.wiktionary.org/wiki/valence
1.1. It’s the first place large enough to contain a plausible explanation for how the AGI itself actually came to be.
According to this criterion we would be in a simulation because there is no plausible explanation of how the Universe was created.
exfohazard
expohazard(based on exposition)
Based on the latin prefix ex-
IMHO better than outfohazard.
The key here would be an exact quantification: how much carbs do these cultures consume in relation to the amount of physical activity.
Has the hypothesis
excess sugar/carbs → metabolic syndrome → constant hunger and overeating → weight gain
been disproved?
Rather, my read of the history is that MIRI was operating in an argumentative argument where:
argumentative environment?
A good critical book on this topic is House of Cards by Robyn Dawes
If we have to use voice, we can still try to ask hard questions and get fast answers, but because of the lower rate itâs hard to push far past human limits.
You could go with IQ-test-type progressively harder number sequences.Use big numbers that are hard to calculate in your head.
E.g. start with a random 3 digit number, each following number is the previous squared minus 17. If he/she figures it out in 1 second he must be an ai.
If you like Yudkowskian fiction, Wertifloke = Eliezer Yudkowsky
The Waves Arisen https://wertifloke.wordpress.com/
I’m looking for something simpler that doesn’t require understanding another concept besides probability.
The article you posted is a bit confusing:
So is Arbital:
Fixed: the “Miss Scarlett” hypothesis assigns a probability of 20% to e