Live data from Hacker News

Twitter's Recommendation Algorithm

blog.twitter.com

461–470 of 1001 posts

Re: Twitter's Recommendation Algorithm

#461
post #433

Earlier quoted context omitted.

Seems dumb of them. Cost is trivial and their competition that isn’t so politically motivated will have a much further reach. The smart move would be silent on the policy change, pay, and support rival platforms as they can. Instead they will eventually pay and look like they lost.

For the NYT to verify their official accounts plus those of their reporters (using the Twitter Blue Affiliations feature) would be $1m annually. This, for a budget line item that has heretofore been $0. In this economy, that's a reach. I don't think the NYT is worried about "reach."

> I don't think the NYT is worried about "reach."

LOL they are desperate for reach. Incredibly so; have you not listen to any podcast by them? They are begging people to go to their site. They get a fraction of the organic traffic they used to and nearly everything is driven from other site like Twitter, Google News, Facebook, etc. The internet age has not been kind to classic news orgs.

Re: Twitter's Recommendation Algorithm

#462

Earlier quoted context omitted.

Engineers who work at twitter can easily find another job in the US.

even considering all the layoffs other companies are doing?

What do you think is the percentage of companies who did layoffs or have hiring freezes vs companies who are hiring high caliber engineers?

Re: Twitter's Recommendation Algorithm

#463
post #31

Earlier 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.

Exactly. I don't see NPA (no party affiliation) anywhere.

Did you not get the memo? "If you're not with us, you're against us".

It's probably more of a conservative/liberal identifier based on US political party ideals... And they likely would filter any metrics from this by the users country

Re: Twitter's Recommendation Algorithm

#464
post #11

From 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…

Coded as if the only two political parties on the planet were the Rs and the Ds. Shameful.

Re: Twitter's Recommendation Algorithm

#465
post #180

Squashing the commit history before releasing it was an interesting (and completely predictable) decision.

> Squashing the commit history before releasing it was an interesting (and completely predictable) decision.

This is standard practice when it comes to open-sourcing such repos that were closed-source for years.

Re: Twitter's Recommendation Algorithm

#466
post #109
post #96

Earlier quoted context omitted.

You say it’s not nefarious but isn’t that how echo chambers are created?

I don't believe echo chambers are nefarious - there's no hidden agenda involved with them. That's just how recommendation algorithms work, and it's what most people want. But if someone finds some code that suppresses recommendations from a specific political ideology across the board, that would be nefarious, IMO.

[flagged]

Re: Twitter's Recommendation Algorithm

#467
post #327
post #105

The twitter algorithm sucks balls and heavily overweights who's paid for a checkmark. The default feed view has grown increasingly useless over the past ~6 months.

I don't think any changes to bias towards bluechecks have been made yet.

A significant portion of my 'for you' is low quality tweets from paid bluechecks.

The people who are willing to pay to be heard more seem to be willing because everyone is already tired of listening to them.

Re: Twitter's Recommendation Algorithm

#468

Earlier quoted context omitted.

Engineers who work at twitter can easily find another job in the US.

H1-Bs are harder to get approved these days and a lot of companies don't want to go through the effort/cost to do so

According to this one link [0], H1B "tranfers" are not subject to visa caps. Plus you can search for new jobs and start the process while still employed.

0: https://usvisagroup.com/changing-jobs-h-1b-visa

Re: Twitter's Recommendation Algorithm

#470
post #90

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...

Maybe it's weird, but for all the work I have ever done, I have never used CI/CD in the way that it was meant to be used, or never really leveraged it. Maybe all of my past jobs were unprofessional, but like, I see a lot of jobs using "CI/CD experience required" and I think... huh I wonder if they actually do it

I wouldn't say it's necessarily weird, and I'd never call it unprofessional, but I have also been using CI of some shape or form since I entered the industry in the '00s. From home brewed scripts that were cobbled together internally, to CI servers on-prem, to CI servers in the cloud, and now back to on-prem. At work, I am literally in the middle of a massive migration of my teams multiple CI servers. We have dozens, sometimes hundreds of jobs kicked off on a daily basis + at least 2 dozen nightlies. Without CI, our team would be dead in the water.
Post reply on HN