Live data from Hacker News

Twitter's Recommendation Algorithm

blog.twitter.com

731–740 of 1001 posts

Re: Twitter's Recommendation Algorithm

#731

It's disappointing the comments are so obsessed with the political angle to this that there's a total lack of appreciation (or discussion) of opening up the most influential social media platform in the world.

Just read the article and not the comments. Comments here used to be something you learn new stuffs, apparently that is not the case anymore.

Re: Twitter's Recommendation Algorithm

#732

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.

Yeah, but then what do you do after you measure it? Nothing? No, you make decisions differently so as not to offend whoever is part of the criteria. For example, can we agree that we don't want an "author_is_flat_earther" flag? Because who gives a shit if Twitter makes a change to their recommendation engine that negatively affects flag earthers? Just because something is only used for A/B testing doesn't make it com…

flat_earther can be a a proxy for conspiracy theories. They may want to know if there is a swing.

Re: Twitter's Recommendation Algorithm

#734
WTF is AuthorIsEligibleForConnectBoostFeature? I guess this may explain why some people seem to accumulate a lot of followers very quickly while all those trying to grow organically seem to struggle. You can imagine if a lot of people benefit from this Connect Boost feature, it would make it impossible for others to be noticed through the noise created by all of these boosted individuals. That's essentially what Twitter feels like ATM. Recently, I manually unfollowed anyone who I suspect may have received a special boost from the algorithms.

Re: Twitter's Recommendation Algorithm

#735

Earlier quoted context omitted.

Wait, am I missing something here or author name is cleary mentioned as elon here while musk’s twitter id it @elonmusk? Why is everyone assuming this code is about elon?

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.

Re: Twitter's Recommendation Algorithm

#736
post #658

Earlier quoted context omitted.

This shouldn't really be a surprise to anyone. It was reported years ago that Twitter was unable to cut down on hate speech because the automated systems they developed triggered too many [debatably false] positives on Republican politicians and that was bad for the company's reputation. If Twitter wanted to prevent future code changes from impacting that approach, there needed to be something like this in the code o…

[flagged]

I don't know what specific documents you think did that, but "comprehensively" is absolutely an awful way to describe the Twitter Files. They were anything but "comprehensive". In actuality, they were an excellent example of how easy it is to lie using partial truths. For example, highlighting all the times Twitter took moderation recommendations from a Democratic campaign looks a lot worse if you hide any time they took moderation from Republican campaigns. A simple look at the specific journalists that were given access to Twitter documents and the strings attached to that access reveals that the Twitter Files were not about transparency. They were an ideological play and nothing more. If Musk wanted true transparency, he would have given wider access to more documents or just released them all like Jack Dorsey requested.

Re: Twitter's Recommendation Algorithm

#737
post #551

Earlier quoted context omitted.

Do you think the code looked like that prior to Elon's purchase? I suspect that there was another name there before. Separately, which of these groups do you think that they use as a control?

> I suspect that there was another name there before Who ? Musk is unique in being obsessed with being liked and relevant. All of the other social CEOs including Porag and Jake have never really cared that much. And none of them participated in contributing content anything close to what Musk does.

I miss Jake

Re: Twitter's Recommendation Algorithm

#738

Earlier quoted context omitted.

Couple problems: 1. Actively supplying negative feedback is sometimes hidden behind secondary menus, making it much higher friction compared to just...scrolling past. So most users don't spend the effort. Even with a dislike button, it's unclear what the system is learning. It can't know that I don't like this particular video because it's a conspiracy theory, and to stop showing me those. These platforms often don't…

Eh, 1 is sort of why I see implicit negative feedback as more useful here. Namely, tracking the duration a user is probably giving their attention to a given item, weighted in accordance with how long you'd expect someone to give their attention to an item based on how long it is. For example, I might see a some specific word or pattern of words in a tweet and quickly skip to the next one. That's very low friction bu…

You're talking like an ML engineer. :)

Yes, there are signals in human behavior that you can feed to your model. But no, it is never going to learn "on Mondays he works on his comics, so he'd prefer to see webcomic-related content" Don't sprinkle in your explore/exploit experiments. I know what I want, just let me decide based on what I'm in the mood for!

TikTok-style feeds are the absolute worst offender here, where they couldn't care less about what you think. They will serve you content, and you will either say "yes" or "no". So the only option for you as the user is to just wander through their content hyperspace. There's no structured way to jump between topics because everything lives in this formless content soup.

The other problem is that many social media platforms have you subscribe to the content streams of individuals directly. Individuals are high variance. How can you teach these engines that "I only care about this person's posts about pianos, not their terrarium hobby."

Re: Twitter's Recommendation Algorithm

#740
post #564
post #428

Earlier quoted context omitted.

That’s not how it works. See the parent.

They said that they use it for metrics, so clearly there must be an "elon impression" metric.

I imagine it's the largest metric in a mission control style room

it starts dropping, klaxons start blaring, the room drops to red only lighting, engineers on the floor start pulling out their hair knowing the shitstorm that's coming

Post reply on HN