(This would have been a good setup for an April fool’s post where you introduce a new notation, which you call “Feynman diagrams”.)
Alex_Altair
Karma: 6,134
Proof Explained: Touchette-Lloyd Theorem
Ah sorry, I was using LW’s feature of highlighting something in the text and then making a comment about it. This is the part that says;
Theorem 2 (Coding Theorem). There is a constant
0
Should be 1?
I’m sure you’ve had lots of discussion about this; why the label “AI alignment”?
I think “alignment” refers to the somewhat specific task of aligning an AIs values to human values. But my understanding of your actual scope is more like “theoretical AI safety”. A lot of foundational work is done with the intention that it will eventually help with alignment, but which definitely isn’t about alignment, and a lot of theoretical AI safety work isn’t about alignment per se at all. For example, some of my research problems are trying to understand which types of AI systems are not dangerous, not because their values are aligned with ours, but because they’re not unrestrained consequentialists.
I mean, I just think the post isn’t very good. It’s kinda funny, but it’s not THAT funny, and also it’s not the kind of funny that is appropriate for curation. Overall I think curating it wasted a bunch of people’s time and somewhat eroded the commons.
But, I also don’t expect to convince you personally? Because you are a trickster archetype. Trickster archetypes have a valuable place in society but that place is not in choosing curated posts for LW. So the people I am petitioning to un-curate this are the other LW mods.
How much information does an optimal policy contain about its environment?
Upcoming Dovetail fellow talks & discussion
Hi all! I’m a long-time LWer, but I’m making a comment thread here so that my research fellows can introduce themselves under it!
For the past year or so I’ve been running the Dovetail research fellowship in agent foundations with @Alfred Harwood. We like to have our fellows make LW posts about what they worked on during the fellowship, and everyone needs a bit of karma to get started. Here’s a place to do that!
When bits of optimization imply bits of modeling: the Touchette-Lloyd theorem
I think your title “The Axiom of Choice is Not Controversial” is literally false, because “controversial” is a social property referring to how much disageement there is, and not whether something is true. Rejecting the AoC is a minorinty view but it is not that minority. It’s also a respected alternative view, and texts often go out of their way to mention when they are acceping the AoC. It may if anything be the most controversial thing in math.
Answering a child’s questions
I basically agree with all of this. I had this thought in part because I have the fairly strong sense that (current, US) society has a belief that there is a healthy state we should be aiming for, and does a lot of question substitution like “does this feel good/acceptable”. There are much better and worse ways to orient to x-risk, but it may be that all of them feel “bad/unacceptable” and it’s hard for me to see how they could be accurately labeled “healthy”.
I’ve been worried that the Solstice isn’t really set up to handle “actually looking at human extinction in nearmode” in a psychologically healthy way
A thought I had when I read this sentence was, “what makes you think there is a healthy way?” It kinda feels to me like, just as there’s no way to get in a car accident that’s healthy for your body, there’s no way to actually believe the world is going to end that’s “healthy” for your mind. There could be better or worse ways it could impact you, but you’re gonna get some impact trauma.
Is there any polyamorous fanfiction of The Incredibles?
I think something like “accountability” is a much more accurate term for this generalization than “dominance”. Parents, teachers, bosses etc. are roughly as motivated by their accountability to their children, students and employees.
Finite Factored Sets
Nitpick; I thought “finite factored sets” were being rebranded as factored space models, because the finiteness was inessential. I think this name is better and would like to see the switch-over happen before the framework gets more popularity. But maybe I’m wrong about this intention?
Silly question, but… where is the delete button for posts?