111–120 of 1001 posts
Context: 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…
Context: 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…
So why did they opensource it?
Context: 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…
So why did they opensource it?
I wonder what the "author_is_elon", "author_is_power_user", "author_is_democrat", and "author_is_republican" labels are for [1]. [1]: https://github.com/twitter/the-algorithm/blob/main/home-mixe...
\*
\* These author ID lists are used purely for metrics collection. We track how often we are
\* serving Tweets from these authors and how often their tweets are being impressed by users.
\* This helps us validate in our A/B experimentation platform that we do not ship changes
\* that negatively impacts one group over others.
\*
Typically, we expect to be able to run "open source" software ourselves. If you open-source your C compiler, I can compile a C program with it. In a few recent high-profile cases though, companies have "open sourced" ML systems without releasing the model weights. This practice is just like your releasing the builds scripts for your C compiler, but not the compiler itself. While more transparency from social media wi…
Running this code would require a lot more than just the exported models. There are a large number of code and system dependencies missing.
Say what you will about Elon, but this wouldn't have happened without him. Thanks! And thank you to everyone at Twitter who helped organize this release. Open sourcing something like this is no small effort.