791–800 of 1001 posts
Earlier quoted context omitted.
So now engineers working on the algo can ensure their launches won't lower Elon's tweet visibility. Looks like those remaining at Twitter have a knack for corporate survival.
When your visa is on the line, you’ll do anything
Earlier quoted context omitted.
Are you serious? What other Elon do you think it refers to?
I mean yeah it must be elon we know but what I was mostly curious about was if it’s actually meant for him only, why didn’t they use his twitter handle? And just elon? I am not a developer I must mention it looks like. And I was genuinely curious.
Earlier quoted context omitted.
> We literally went through reporting a few months back where he was clearly instructing the team to make sure his tweets always come up, for everyone. Feel free to give me a source for that, but I'm pretty sure that's not true.
looks like evolve2k is himself the source. maybe he was a twitter employee ?
Earlier quoted context omitted.
So many unnecessarily cynical takes here. Let's say you were in charge of a large legacy system that some segment of customers complain about it not working for them as well as other segments. How would you know whether their complaints are valid unless you measured it? You have to know first. So measure it.
Elon has said he wanted more reach and experimented with getting it. He also loves attention and tweets a ton. There’s benefit of the doubt then there’s just… whatever the polar opposite of that is.
Earlier quoted context omitted.
Why measure something if you don’t intend to change it?
You might want to ask that of, say, astronomers, paleontologists, or even simply journalists. Observing and measuring leads to understanding. As others here have noted, sometimes you want to measure to ensure that you're not inadvertently affecting an outcome or phenomenon.
You compare scientists with businesses. One of them's job and passion is to collect knowledge for the sake of knowledge. For the other one it would be cost without gain and eliminated if they didn't do anything with it!
No idea what journalists are doing in that list, what do they measure? If they want something measured they'd ask or look at other's services. Unless you mean the business that the journalists work for, but hen it's just that, a business.
It's reassuring to know that billion dollar tech companies write CI exactly like I do: https://github.com/twitter/the-algorithm/blob/main/ci/ci.sh Permalink: https://github.com/twitter/the-algorithm/blob/7f90d0ca342b92...
Context: I teach at Princeton and study social media and recommendation systems. From a very quick skim of the repositories, this appears to be quite limited transparency. The documentation gives a decent high-level overview of how Tweet recommendation works—no surprises—and the code tracks that roadmap. Those are meaningful positive steps. But the underlying policies and models are almost entirely missing (there are…
So why did they opensource it?
Earlier quoted context omitted.
> We literally went through reporting a few months back where he was clearly instructing the team to make sure his tweets always come up, for everyone. Feel free to give me a source for that, but I'm pretty sure that's not true.
It was widely reported in the days following the Super Bowl that he personally ordered his Tweets be boosted after a Tweet by Biden got more engagement than his similar Tweet [0]. As far as I can tell, he did not instruct Twitter employees to make his Tweets appear to all users, but he did want them to make his posts appear in timelines significantly more often. This lead to reports of users suddenly getting their ti…
After some digging in the code base it turned out that there was a de-boosting factor based on the absolute numbers of blocks your account had, which affected popular and controversial accounts (like Elon’s) unfairly.
This investigation was initiated by Musk but it resulted in a great improvement in the algorithm with no special treatment for his account.
Context: I teach at Princeton and study social media and recommendation systems. From a very quick skim of the repositories, this appears to be quite limited transparency. The documentation gives a decent high-level overview of how Tweet recommendation works—no surprises—and the code tracks that roadmap. Those are meaningful positive steps. But the underlying policies and models are almost entirely missing (there are…
I am assuming that open sourcing the code aims to increase transparency about the business logic of the ranking decisions. At the same time you don't want spammers to be able to easily run experiments against a cloned version of your system.