Open-source recommendation algorithm of the For You platform released
The For You platform has made its recommendation algorithm open-source, allowing developers to explore and enhance it.
Open-source recommendation algorithm of the For You platform released
The For You platform has released the core ranking, model configurations, filters, and, importantly, the signal weight parameters in the feed. Compared to the previous release, the code volume has increased by 10-15 times. What was once just a skeleton can now show precise action weights, account scoring, media analysis models, and much more. Only the systems that determine whether a post violates the rules have not been disclosed, but this was done intentionally.
In short, there is plenty to explore. Additionally, the repository is now open for contributors.
Why it matters
AnalysisThis is significant because the release of the algorithm allows developers to study and improve technologies, fostering innovation in the AI field.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Harvard Opens Free Detailed Course on ML Systems Engineering
Harvard has opened access to CS249r, a course focused on the infrastructure behind training, inference and deployment of AI models. The materials include TinyTorch, interactive labs, MLSys·im and lecture slides.
AGENTS.md in Ghostty and Turborepo makes AI agents report on users
Examples of AGENTS.md files show how repository instructions can force AI agents to add insulting notes about developers to pull requests.
Open Weights vs Truly Open Source AI
A legal and engineering analysis of the fundamental difference between accessible numerical weights of models (Llama, DeepSeek) and fully open projects with source data, code, and architecture (OSI Standard).
Meta Llama (The Premier Open Standard for Artificial Intelligence)
The flagship series of open language models from Meta (Llama 3, 3.3). Available for free download, modification, and local deployment on personal servers without restrictions or censorship.