I think the author didn't actually go to this burrito restaurant, but rather just wrote an article as if he was going to go to the burrito restaurant. From the intro:
> We’ve written about the decline of Google Search, and how to rigorously measure it through human evaluation. But why stop at Google? We’re starting a new blog series of real-world ML evaluations, where we investigate search and recommendation systems – whether YouTube, Meta, TikTok, or Amazon. In this post: an evaluation of Facebook Search!
For some businesses Facebook is great, bars that have events, getting a better feel for an apartment complex, a couple other things like that. I won't use it as a maps but to find a place hosting a trivia night it is really useful.
Maybe Facebook doesn't really care if it's bad at that category of search, since nobody in their right mind would use Facebook to figure out where to get burritos.
> We’ve written about the decline of Google Search, and how to rigorously measure it through human evaluation. But why stop at Google? We’re starting a new blog series of real-world ML evaluations, where we investigate search and recommendation systems – whether YouTube, Meta, TikTok, or Amazon. In this post: an evaluation of Facebook Search!