Why is nobody pointing out that this is likely an April Fools joke? We just deployed our April Fools joke into production today too.
I fell for it too until a friend pointed it out. I wonder why it's working so well Edit: hi friend
Lmao
Twitter's Recommendation Algorithm
501–510 of 1001 posts
Re: Twitter's Recommendation Algorithm
#502I want to go back to a world where there isn't an algorithm feeding me what someone "thinks" I want to read.
I want to see a chronological list of things sources I follow have posted.
Yes, I understand you can do this on Twitter still, but I would guess most people are more influenced by "the algorithm".
Re: Twitter's Recommendation Algorithm
#503From https://github.com/twitter/the-algorithm/blob/7f90d0ca342b92... ( "author_is_elon", candidate => candidate .getOrElse(AuthorIdFeature, None).contains(candidate.getOrElse(DDGStatsElonFeature, 0L))), ( "author_is_power_user", candidate => candidate .getOrElse(AuthorIdFeature, None) .exists(candidate.getOrElse(DDGStatsVitsFeature, Set.empty[Long]).contains)), ( "author_is_democrat", candidate => candidate .getOrEls…
> But we are deleting this bs. I only learned about it now! Will be gone by tomorrow.
https://twitter.com/elonmusk/status/1641908130274525187?t=5t...
Re: Twitter's Recommendation Algorithm
#504Context: 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…
[flagged]
Re: Twitter's Recommendation Algorithm
#505hmmm https://github.com/search?q=repo%3Atwitter%2Fthe-algorithm-m...
Twitter hmu if you need help trying Pytorch 2.0 ;)
Re: Twitter's Recommendation Algorithm
#506Earlier quoted context omitted.
I thought it was interesting how it explicitly doesn't boost independents. So much of the two-party system is self-reinforcing.
Also how about.... everyone else in the world who is not an American voter?
Before I deliberately locked myself out of it (well before Musk), I asked for my data.
They classify me as:
* speaks Indonesian
Interested in:
* Beer
* Cricket
* DJs
* Dance
* Enterprise software
* Horror
* NFL football
* South America
And aged either between 13-54 or (and?) over 65
On that basis, they'd probably call me a Republican.
Carries a different meaning when you're British, that name does.
Re: Twitter's Recommendation Algorithm
#507Earlier quoted context omitted.
The author_is_elon flag doesn't surprise me, but the two political designators are somewhat shocking. I'd sure like to know what changes based on what Twitter knows about your political affiliation.
I thought it was interesting how it explicitly doesn't boost independents. So much of the two-party system is self-reinforcing.
I thought it was interesting that twitter thinks the U.S is the world
Re: Twitter's Recommendation Algorithm
#508Earlier quoted context omitted.
So they could pretend to be open. It's the "Open"AI model. Open-washing?
This is a very cynical take. They should be commended for publishing recommendation code at all, which no other major social network does.
Let's have reasonable goals, shall we ? "Their shit doesn't stink as bad as others'" is nothing commendable, especially after souch publicity.
Re: Twitter's Recommendation Algorithm
#509Earlier quoted context omitted.
True, it still seems odd to encode an explicitly ordinal variable as categorical (particularly one with a small finite range, in contrast to the follower logarithmic bucket ones), but Twitter's layout is weird enough that it could be a impactful difference in terms of engagement.
This is (weirdly) common in production ML codebases written by software engineers. Like you, I have no idea why unless it's a memory optimisation (where you count 4+ as many).
Having every column as a boolean (0/1) means you can treat it as a bitmap. As an (entirely fictional) example, imagine if you wanted to get the features of a thread instead of a single tweet. You could do it as a union of all the tweets:
threadFeatures = tweet1 | tweet2 | tweet2