their app has some very strange flow to it, i cant tell if it feels designed by committee or if there are just so many strange use cases that its somehow the least bad given some arbitrary constraints i cant begin to understand.
even selecting my restaurant is a constant battle. the closest restaurant to my house as the bird flies is not the closest restaurant. even the closest by miles driven involves much more complication than the one i always want to pick. it constantly battles me that i have selected a suboptimal choice. maybe learn that when i am at home, i want to default to my preferred choice, every time, unless i say otherwise.
I'm only 50/50 but I swear they have only one app for the entire globe.
Can you imagine how complex that must be vs just making like 100 different apps in each country.
But eCoNoMiEs oF sCaLe
If you're balking at makin 100 different apps, then for reference, I am pretty sure my local mcdonalds - just the one restaurant turns over >10 mill a year, so you get a sense of how much they'd want to invest in, idk, the ordering front-end of every maccas in Australia
At least in Japan on iOS, they have their own app, and it’s great.
You can find a seat first, then order directly from your seat, for delivery to your seat (helpful since some McDonald’s in Japan are really busy, and have very vertical, so you might need to climb up some two/three floors to find a seat!).
You can even order McDelivery and they’ll deliver McDonald’s to your house on McDonald’s branded mopeds.
It’s also been pretty fast, even on a slow internet connection.
The only two problems I’ve had with it are:
- Although the menu and the rest of the app is translated to English, sometimes coupons are only in Japanese, and not translated to English (I’m guessing these might be store-specific) (although it’s easy enough to translate that using your phone’s translator)
- I’ve had Apple Pay occasionally be down and fail to work, which forced me to redo my whole order, then realize that Apple Pay is still down, then do my entire order again with a different payment method. Although it’s only happened twice a few months ago, so it could be something that they’ve already fixed (or I’m quite unlucky).
I tried to log into it just now to see which McDonald's it would select for me at home and whether it would be callous about changes.
But when I touched the icon to open the app, a big M appeared on a bright red screen and then it died and returned to the home screen less than half a second later.
In theory I would expect them to be able to ingest the corpus of the new yorker and turn it into a template with sub-templates, and then be able to rehydrate those templates.
The harder part seems to be synthesizing new connection from two adjacent ideas. They like to take x and y and create x+y instead of x+y+z.
Most of the good major models are already very capable of changing their writing style.
Just give them the right writing prompt. "You are a writer for the Economist, you need to write in the house style, following the house style rules, writing for print, with no emoji .." etc etc.
The large models have already ingested plenty of New Yorker, NYT, The Times, FT, The Economist etc articles, you just need to get them away from their system prompt quirks.
I think that should be true, but doesn't hold up in practice.
I work with a good editor from a respected political outlet. I've tried hard to get current models to match his style: filling the context with previous stories, classic style guides and endless references to Strunk & White. The LLM always ends up writing something filtered through tropes, so I inevitably have to edit quite heavily, before my editor takes another pass.
It feels like LLMs have a layperson's view of writing and editing. They believe it's about tweaking sentence structure or switching in a synonym, rather than thinking hard about what you want to say, and what is worth saying.
I also don't think LLMs' writing capabilities have improved much over the last year or so, whereas coding has come on leaps and bounds. Given that good writing is a matter of taste which is beyond the direct expertise of most AI researchers (unlike coding), I doubt they'll improve much in the near future.
To the point that defense spending prevents us from publishing an accurate financial statement for soon to be 30 years running.
The Government Accountability Office (GAO) issued a disclaimer of opinion on the U.S. government’s FY 2025 financial statements — the 29th consecutive year it has been unable to determine whether the statements are fairly presented. This is primarily due to serious, ongoing financial management problems at the Department of Defense and weaknesses in accounting for interagency transactions.
Watching Mark testify before the senate it honestly appears like it may have never occurred to him that it is an option to have not offered a feature. He treats the product as if it is some kind of inevitable outcome that was destined to exist.
I guess I’d rather have something approaching bittorrent, edonkey/kad, ipfs, blockchain, webarchives.
You have named networks that are federated together, and people can publish to the networks they are invited to or sign up for. The networks survive even with individual servers go down. Data is cached all over at the edges.
Your version is just way too susceptible to rot, unless you see that as a feature. I see it as most of the good content falling into the ether sooner rather than later.
The problem with distributed storage is they place too high of a requirement on edge nodes, which people have to host, and they synchronize too slowly for real time messenging. If I upload a 1GB video to my server's chat, that storage load should not be replicated on many other nodes. Who pays for that disk space? The federated model is a lot more robust in this regard.
As far as archiving is concerned, many archiving orgs will pop up if their discussion servers and public facing websites can't be traced or easily shutdown. The protocol itself can't archive things, but it protects the people doing the archiving work and gives a place for websites like Annas Archive to live without relying on IP and DNS. The idea is to amass enough uncensorable social power so that such efforts can't be banned or shutdown, then you can use existing protocols like BitTorrent all you want.
reply