Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Twitter's Recommendation Algorithm

blog.twitter.com

Post reply on HN
Print view View original

91–100 of 1001 posts

Re: Twitter's Recommendation Algorithm

#91

Post by sho_hn »

systemvoltage wrote: post #84
sho_hn wrote: post #81

Earlier quoted context omitted.

Assuming anything in this codebase is worth reusing, I'm glad it's GPL. It's a case where I'd like open-first to spread.

GPL would be good if it is a self contained library. If anyone would use it, it would be small portions of it, but GPL makes it completely useless. You can't contaminate anything with it. We'll stare at it, that's about it. That makes me think, this is actually a good call. Twitter can claim that they have complete transparency while not allowing anyone to touch their code (because it is GPL). "Anyone" being future c…

It's only contaminating other components where you incorporate or link it. If it's e.g. a microservice that's fine.

Re: Twitter's Recommendation Algorithm

#94

Post by krapp »

distrill wrote: post #71
BbzzbB wrote: post #59

Earlier quoted context omitted.

It's a colloquial term for recommendation engines, how often do you hear people say "the algorithm" (vs. "the recommendation engine") on YouTube?

yes, but this is the first repository i have seen named like this

It's because there's been nearly a decade of conspiracy theory around the use of algorithmic feeds in social media generally, and Twitter specifically. Among the right, "algorithms" have become symbolic of the machinery of leftist oppression they believe to be arrayed against them by modern media.

So this language is Elon signaling that he's presenting the "woke hivemind's" head on a platter.

Re: Twitter's Recommendation Algorithm

#96

Post by jeron »

krapp wrote: post #66
jawns wrote: 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.

The repo suggests it's about tracking engagement metrics[0], so Team Red people see more Team Red content and vice versa. Nothing nefarious. [0] https://github.com/twitter/the-algorithm/blob/7f90d0ca342b92...

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

Re: Twitter's Recommendation Algorithm

#99

Post by paxys »

While open sourcing code is always great, and kudos on them for doing so, let's be real most people didn't care about the internal plumbing of how their recommendation system runs. It's going to be a mess of decades old code, microservices and ML pipelines just like one would expect. If you want to dig deeper to check for biases (the reason they claimed to be open sourcing it in the first place), you will however run into:

> We also took additional steps to ensure that user safety and privacy would be protected, including our decision not to release training data or model weights associated with the Twitter algorithm at this point.

which is a shame.

Re: Twitter's Recommendation Algorithm

#100

Post by systemvoltage »

sho_hn wrote: post #91
systemvoltage wrote: post #84

Earlier quoted context omitted.

GPL would be good if it is a self contained library. If anyone would use it, it would be small portions of it, but GPL makes it completely useless. You can't contaminate anything with it. We'll stare at it, that's about it. That makes me think, this is actually a good call. Twitter can claim that they have complete transparency while not allowing anyone to touch their code (because it is GPL). "Anyone" being future c…

It's only contaminating other components where you incorporate or link it. If it's e.g. a microservice that's fine.

Good point about network calls & GPL licenseability.
Post reply on HN