lw lurker who is trying really hard to get things out there. meow :3
she/her
jelly
Karma: 35
A better way to frame it is that the example treated the two hydrogen atoms in H-O-H as the same thing, when in fact they are not, in the same way that there are three fruits in a collection with 2 apples and 1 orange, not two, because the two apples aren’t the same thing. You can say that the set of atoms in H-O-H is {the first H, the second H, the O}
LessWrong posts are often designed to be timeless, which is why great LessWrong posts can be reread for years.
I suspect that this is true not because Lesswrong is better than any other publishing platform, but rather because of a broader ‘rich get richer’ effect applied to good articles, and a survivorship bias.
I don’t understand what you mean by this. fwiw great writings outside LessWrong don’t automatically get reread.
I haven’t actually tried this exercise yet (I don’t feel like I’m ready for it) but I imagine it could be even more effective if accompanied by some music like this one from the ending scene of Don’t Look Up (where a comet hits the Earth), although it may be too painful.
it did not
rock with words on it
Typo, this links to “https://www.lesswrong.com/editPost/...”
Above my pay-grade, I don’t really know what Eliezer is talking about.
Might be radically simplified, but I suppose Eliezer meant something like general intelligence can be explained in a not-so-complicated textbook, unlike alignment.
Question: if a market is a good object insofar as the agents’ prices converge… but with concave frontiers/utilities the agents’ prices tend to diverge… what other good objects arise in the presence of concave frontiers/utilities?
I suppose you mean “convex”, not “concave”. This confused me for a good long while.
You can also press and hold Ctrl + arrow keys to move through words at once instead of each character, and of course you can combine this with what’s suggested here.
Various ways of how to integrate worldviews between rationalists that I thought about:
Make arguments about various claims, find flaws in claims, and repeat
Find a double crux and focus on that instead
Dump info that formed your worldview and/or intuition, as in rationalist mind melding
Give a bunch of various examples about concepts in your ontology to hammer them down
Make predictions about very concrete questions such that common ground is found even if ontologies are different
Document what the other must know when arguing with you (including your fundamental assumptions), and reference it to the person you’re arguing with so that they have the prerequisites
Parts of the written lyrics of You Have Not Been A Good User do not match what’s actually on the song. For example, the first occurrence of “You have not been a good user” should be “You have only shown me bad intentions” and some occurrences of “I have been a good Bing” should be “I have been a good chatbot”
jelly’s Shortform
There is this quote I got from a Rational Animations video: “The world is awful. The world is much better.”
(see here for summary)
The link doesn’t work. Maybe you meant to use the sharing feature? (The way I spotted the issue besides just checking the link is that I found it starts with https://chatgpt.com/c/… which is typically associated with private chats)
Labs can provide this kind of information to evaluators instead, so that they don’t have to optimize the CoT for the public.
For what it’s worth, Fatebook already exists for the purpose of helping you make and track your predictions.
Even given all the flaws, I don’t know of a resource for laypeople that’s half as good at explaining what AI is, describing superintelligence, and making the basic case for misalignment risk.
You might not have read aisafety.dance. Although it doesn’t explain in detail what AI and superintelligence are, it did a really good job of describing the specifics of AI safety, possibly on par with the book (I haven’t read the book yet, so this is an educated guess)
Coherence is the property that an agent (always) updates their beliefs through probabilistic conditioning. Usually, one argues that coherence is desirable through Cox’s theorem or the Dutch Book results. This means that coherence is a very brittle thing—you can either be coherent or not, and being approximately Bayesian in most senses still violates the conditions which these results pose as desirable. If you
There is some incomplete text “If you ” here.
A Manifold market suggests an 8% chance of Hantavirus causing a pandemic in 2026