How does it work to optimize for realistic goals in physical environments of which you yourself are a part? E.g. humans and robots in the real world, and not humans and AIs playing video games in virtual worlds where the player not part of the environment. The authors claim we don't actually have a good theoretical understanding of this and explore four specific ways that we don't understand this process.
Hangnails are both annoying and painful, often snagging on things and causing your fingers to bleed. Typical responses to hangnails include:
Instead, use a drop of superglue to glue it to your nail plate, IMO a far superior option. It's $10 for 12 small tubes on Amazon. Superglue is also useful for cuts and minor...
The history of science has tons of examples of the same thing being discovered multiple time independently; wikipedia has a whole list of examples here. If your goal in studying the history of science is to extract the predictable/overdetermined component of humanity's trajectory, then it makes sense to focus on such examples.
But if your goal is to achieve high counterfactual impact in your own research, then you should probably draw inspiration from the opposite: "singular" discoveries, i.e. discoveries which nobody else was anywhere close to figuring out. After all, if someone else would have figured it out shortly after anyways, then the discovery probably wasn't very counterfactually impactful.
Alas, nobody seems to have made a list of highly counterfactual scientific discoveries, to complement wikipedia's list of multiple discoveries.
To...
~Don't aim for the correct solution, (first) aim for understanding the space of possible solutions
A friend has spent the last three years hounding me about seed oils. Every time I thought I was safe, he’d wait a couple months and renew his attack:
“When are you going to write about seed oils?”
“Did you know that seed oils are why there’s so much {obesity, heart disease, diabetes, inflammation, cancer, dementia}?”
“Why did you write about {meth, the death penalty, consciousness, nukes, ethylene, abortion, AI, aliens, colonoscopies, Tunnel Man, Bourdieu, Assange} when you could have written about seed oils?”
“Isn’t it time to quit your silly navel-gazing and use your weird obsessive personality to make a dent in the world—by writing about seed oils?”
He’d often send screenshots of people reminding each other that Corn Oil is Murder and that it’s critical that we overturn our lives...
Strong upvoted. I learned a lot. Seriously interested in what you think is relatively safe and not extremely expensive or difficult to acquire. Some candidates I thought of but im not exactly well informed:
-- Grass fed beef
-- oysters/muscles
-- some whole grains? which?
-- fruit
-- vegetables you somehow know arent contaminated by anti-pest chemicals?
I really need some guidance here.
Post for a somewhat more general audience than the modal LessWrong reader, but gets at my actual thoughts on the topic.
In 2018 OpenAI defeated the world champions of Dota 2, a major esports game. This was hot on the heels of DeepMind’s AlphaGo performance against Lee Sedol in 2016, achieving superhuman Go performance way before anyone thought that might happen. AI benchmarks were being cleared at a pace which felt breathtaking at the time, papers were proudly published, and ML tools like Tensorflow (released in 2015) were coming online. To people already interested in AI, it was an exciting era. To everyone else, the world was unchanged.
Now Saturday Night Live sketches use sober discussions of AI risk as the backdrop for their actual jokes, there are hundreds...
Fair enough, thank you! Regardless, it does seem like a good reason to be concerned about alignment. If you have no idea how intelligence works, how in the world would you know what goals your created intelligence is going to have? At that point, it is like alchemy - performing an incantation and hoping not just that you got it right, but that it does the thing you want.
Summary. In this post, we present the formal framework we adopt during the sequence, and the simplest form of the type of aspiration-based algorithms we study. We do this for a simple form of aspiration-type goals: making the expectation of some variable equal to some given target value. The algorithm is based on the idea of propagating aspirations along time, and we prove that the algorithm gives a performance guarantee if the goal is feasible. Later posts discuss safety criteria, other types of goals, and variants of the basic algorithm.
In line with the working hypotheses stated in the previous post, we assume more specifically the following in this post:
Exactly! Thanks for providing this concise summary in your words.
In the next post we generalize the target from a single point to an interval to get even more freedom that we can use for increasing safety further.
In our current ongoing work, we generalize that further to the case of multiple evaluation metrics, in order to get closer to plausible real-world goals, see our teaser post.
Thanks to Leo Gao, Nicholas Dupuis, Paul Colognese, Janus, and Andrei Alexandru for their thoughts.
This post was mostly written in 2022, and pulled out of my drafts after recent conversations on the topic. My main update from then is the framing. Rather that suggesting searching for substeps of search as an approach I'm excited about, I now see it only as a way to potentially reduce inherent difficulties. The main takeaway of this post should be that searching for search seems conceptually fraught to the point that it may not be worth pursuing.
Searching for Search is the research direction that looks into how neural networks implement search algorithms to determine an action. The hope is that if we can find the search process, we can then determine...
Aren't LLMs already capable of two very different kinds of search? Firstly, their whole deal is predicting the next token - which is a kind of search. They're evaluation all the tokens at every step, and in the end choose the most probable seeming one. Secondly, across-token search when prompted accordingly. Say "Please come up with 10 options for X, then rate them all according to Y, and select the best option" is something that current LLMs can perform very reliably - whether or not "within token search" exists as well. But then again, one might of cours...
This is a response to the post We Write Numbers Backward, in which lsusr argues that little-endian numerical notation is better than big-endian.[1] I believe this is wrong, and big-endian has a significant advantage not considered by lsusr.
Lsusr describes reading the number "123" in little-endian, using the following algorithm:
He compares it with two algorithms for reading a big-endian number. One...
What if you are not a person, but a computer, converting a string into an integer? In that case, having a simpler and faster algorithm is important, having to start with only the beginning of a string (what the user has typed so far) is plausible, and knowing the number's approximate value is useless. So in this case the little-endian algorithm is much better than the big-endian one.
For the most part this is irrelevant. If you are a computer with only partial input, recieving the rest of the input is so much slower than parsing it that it literally does...
Epistemic Status: Musing and speculation, but I think there's a real thing here.
When I was a kid, a friend of mine had a tree fort. If you've never seen such a fort, imagine a series of wooden boards secured to a tree, creating a platform about fifteen feet off the ground where you can sit or stand and walk around the tree. This one had a rope ladder we used to get up and down, a length of knotted rope that was tied to the tree at the top and dangled over the edge so that it reached the ground.
Once you were up in the fort, you could pull the ladder up behind you. It was much, much harder to get into the fort without the ladder....
Attendee: knock knock Hey, is the organizer in there?
Me: Yeah, what's up?
Attendee: The fire department is here, and we think an attendee just left in an ambulance but we're not sure who or why.
Me: . . . I'll be right out.
And that's the most stressful thing that's ever happened to me as an event organizer.