Technology

Twitter algorithm open-sourced… Is Elon playing 5D chess?


It is April 3rd 2023 and you’re watching the code report less than six months ago Elon Musk paid 44 billion dollars for Twitter and people have been dunking on him ever since he fired half the company gave blue check marks to The Peasants and freed a bunch of people from Twitter

Jail do not come do not come I’m Gonna Come in some ways it looks like Twitter is collapsing it’s now only worth 20 billion dollars many users have moved to Mastodon the New York Times just lost its blue check and even LeBron James won’t pay the five so did Elon buy

Twitter just to be the king and watch it burn or is he actually playing a game of 5D chess against the mainstream news media like the Fox News and CNN channels that your grandparents watch he’s playing the long game to take their advertisers by making Twitter the future

Platform for all journalism and if he plays his moves right I predict he will become the richest man in the world even richer than Elon Musk himself yesterday he made a crazy move by open sourcing the code to Twitter’s recommendation algorithm and it’s some of the most interesting code you’ll ever see in

Today’s video we’ll dissect the code and explain why they want to make Twitter like the Linux of social media companies well kind of although it is real production code at Twitter it’s not 100 of the code so it’s really only useful for research and transparency the code

Base is mostly written in Scala a jvm language that’s kind of like Java but concise and just way better Twitter was originally written with Ruby on Rails but they moved away from it over a decade ago everybody already kind of knows how these algorithms work but it’s extremely interesting to see the real

Deal implemented in code like this method in the early bird tensorflow based similarity engine.scalifile we have a bunch of ranking parameters each with a default value retweets provide a 20x boost while likes provide a 30X boost and images and videos also provide a small boost and not surprisingly you

Also get a boost for being a pain Twitter blue member like I said the New York Times just lost its blue check mark and now it’s not verified so it could just be a cap behind a screen on the flip side a tweak can get a debuff if

The account has a lot of mutes blocks or spam reports also spelling errors and made up words will give you a debuff and there’s also a long list of topics that won’t be Amplified like anything that’s been flagged as misinformation harassment putting bounties on people’s heads and many other no-nos the platform

Also keeps close track of Elections and there’s actually Tools in place like this government requested class that allows president Camacho to keep you safe from Bad content but taking a step back we can break the total algorithm into three parts first it finds a pool of 1500 tweets that you might be

Interested in use using a technique called candidate sourcing it includes accounts you follow but also out of network sources by clustering similar accounts together allowing it to find relevant tweets from accounts that you don’t follow yet from there it ranks that pool of tweets with a 48 million parameter neural network and then

Finally it filters out content by Static rules like accounts that you’ve blocked or muted there’s also a second repo called the algorithm ml that contains the machine learning models used at Twitter the project uses Pi torch and they actually created their own in-house embeddings that contain over a billion

Nodes and hundreds of billions of edges on the home feed it uses something called the heavy ranker but some people have criticized this for amplifying misinformation the most controversial block of code though was this one here that keeps track of whether or not an author is a democrat or republican or

Whether it’s Elon or a power user but apparently this code is only used for collecting metrics but has already been removed one thing that’s not found in the source code though is its apparent juicing of VIP accounts like AOC on the left and Cat turd on the right which was

Reported by platformer the code is highly interesting and I recommend you clone it and check it out yourself but why would Elon do this why would he release his trade secrets to the public it kind of makes Twitter like the Linux of social media the public can identify

Things that are unfair in the algorithm and address them in public it’s mostly a marketing move to build trust it no longer feels like it’s run by a mysterious cabal that can Shadow ban and de-boost content without some degree of transparency and there’s a huge opportunity here because the trust in

Mainstream media has fallen so low many people already use Twitter to consume the news and although Twitter is currently losing money they’ve talked about compensating content creators just like YouTube and other platforms too when that happens journalists could potentially make a living on Twitter and put their best content there Elon knows

Twitter blue is never going to make Twitter any money but rather it’s designed to uplift independent creators while embarrassing The Establishment the blue checks are now irrelevant and by open sourcing the code Twitter is laying the groundwork to become the fair and balanced most trusted name in news and

This may Force other social media platforms to become more transparent putting elon’s balls in Zuckerberg’s Court this has been the code report thanks for watching and I will see you in the next one

#Twitter #algorithm #opensourced #Elon #playing #chess
For More Interesting Article Visit : https://mycyberbase.com/

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *