If you don’t feel great about the numbers, why are there so many of them on the website? The presentation seems much more focused on the scores than a collection of information.
I think the numbers are much better than nothing and much better than any substitute that currently exists, and I’m not aware of a better design or a great way to deemphasize them while preserving their value.
Edit: like, they convey a lot of real info, and more conservative alternatives would fail to do so.
Off-topic: thanks for commenting in the same thread so I can see your names side-by-side. Until now, I thought you were the same person.
Now that I know Zach does not work at Anthropic, it suddenly makes more sense that he runs a website comparing AI labs and crossposts model announcements from various companies to LW
A quick take from me (I did some of the design on the site, though Ray did most of it): I think the numbers are helpful for organizing the content into meaningful categories, and helps people figure out where the interesting content is. Otherwise you would be dealing with a huge amount of prose. I currently think the numbers/table is a pretty decent way to get a sense of what the content is, and where it makes sense to pay attention to (usually the places where there is the most variance in numbers across a category, or where scores are particularly low or high).
I definitely find the presentation useful. In particular, the ability to drill down on each block is great (though it took me a moment to figure out how that worked).
If you don’t feel great about the numbers, why are there so many of them on the website? The presentation seems much more focused on the scores than a collection of information.
I think the numbers are much better than nothing and much better than any substitute that currently exists, and I’m not aware of a better design or a great way to deemphasize them while preserving their value.
Edit: like, they convey a lot of real info, and more conservative alternatives would fail to do so.
Off-topic: thanks for commenting in the same thread so I can see your names side-by-side. Until now, I thought you were the same person.
Now that I know Zach does not work at Anthropic, it suddenly makes more sense that he runs a website comparing AI labs and crossposts model announcements from various companies to LW
A quick take from me (I did some of the design on the site, though Ray did most of it): I think the numbers are helpful for organizing the content into meaningful categories, and helps people figure out where the interesting content is. Otherwise you would be dealing with a huge amount of prose. I currently think the numbers/table is a pretty decent way to get a sense of what the content is, and where it makes sense to pay attention to (usually the places where there is the most variance in numbers across a category, or where scores are particularly low or high).
I definitely find the presentation useful. In particular, the ability to drill down on each block is great (though it took me a moment to figure out how that worked).
If you have any thoughts on what would be more intuitive while accomplishing the goal, let me know.