The tool looks interesting, but man it is sooo hard to read the LLM generated blog post as a human. Not because the text is bad (it kind of is), but because it doesn't feel like anyone has put any energy and real work into it. So it feels like a waste of my time to read something, that could have been three short sentences and a benchmark table without loosing much information.
I thought the blog was pretty reasonable until I came across "One caveat keeps the speed numbers honest" which was the one obvious tell for me. Otherwise I thought it was pretty straightforward to read.
Curious, what were the tells. I'm mostly familiar with Claude family of models' writing so I wonder is this Astra or similar which is why I didnt find it odd.
To play devils advocate: Isn't it that the management had to choose between two potential problematic decisions? What if the management declined the hindu request and then the hindus made a big fuss about it? Wouldn't people scream "how could they think that discriminating the hindu religion would be a good decision?!?".
The work of Zuse is way out of the danger zone, isn't it? Mobile phones with LCDs are in the danger zone, or the phone booth, but not the first working computers ever build.
In german typography the name for widow is "Hurenkind" wich translates to "child of a whore". I was pretty surprised to hear that word on a regular basis while working in text for print.
https://de.wikipedia.org/wiki/Hurenkind_und_Schusterjunge
Yes, there are quite a few signs of LLM usage in the post, which I also found annoying. But I also had the feeling that someone really cared about the quality of the text and I found only one strange/useless sentence in the post, which today has to be taken as a win, I guess.
The US is so big, that 50 ms is physically not possible for everyone.
This is something that not everybody is aware of. When I as a German build something for germans, everyone who needs to wait longer than 100 ms for a request, is rightfully mad. But when I want to serve the same stuff to americans at the same speed, I have to build something completely different and much more complex.
Yeah, but you would need to run an API server in each of those to reach that latency, and even then you're well into eventually-consistent distributed system headache if you accept the POST without synchronising with all the others first.
You terminate SSL (err, TLS) at the pop so the clients TCP connection gets setup faster, and then you use a hot TCP connection from the pop to a centralized API server. That gets you not having to deal with the headache of running a distributed system but a better experience for the client.
If you want 50ms then you're gonna have to do the distributed systems headache that rcxdude was trying to avoid. For everything smaller than Google, that's too expensive, but it can be done.
While I also enjoyed it very much, some thing are strangely ordered and not how I would expect someone with such knowledge of all the moving parts in a request, would build such a site. So for me it feels like an LLM has build it and the human with the prompt saw it and said "eh, good enough".
Agreed. This reeks LLM writing with no human oversight, or at least a human with no writing experience. The text underneath “The Click” is an immediate giveaway:
> Five milliseconds of hardware and browser bookkeeping before a single byte leaves the laptop.
I don’t even know how to describe it, but the “[…] before X” sentence style stands out to me.
reply