Core Viewpoint - GitHub has made Elon Musk's open-source recommendation algorithm system fully visible, which is primarily driven by AI models, marking a significant step towards transparency in social media algorithms [1][2][4]. Group 1: Algorithm Transparency and Design - The open-source file indicates that the algorithm is almost entirely AI-driven, having removed most human-designed features and heuristic rules [2][3]. - The community has reacted positively, praising the transparency that no other platform has achieved [4]. - Musk acknowledged the algorithm's shortcomings, stating it is "dumb" and requires significant improvements, but emphasized the importance of transparency in the development process [5][6]. Group 2: Algorithm Functionality - The recommendation system is based on a Transformer architecture similar to Grok-1, which learns from users' historical interactions to recommend content [10]. - The system constructs a "real-time user profile" by collecting raw user behavior data without pre-set assumptions, allowing the model to learn directly from this data [14][15]. - The algorithm filters content through various modules, including a retrieval module that gathers potentially interesting tweets from both followed and unfollowed accounts [18][20]. Group 3: Key Features of the System - The system operates on five key principles: 1. Purely data-driven, rejecting manual rules [28]. 2. Candidate isolation mechanism for independent scoring [29]. 3. Hash embedding for efficient retrieval [30]. 4. Predicting multiple user behaviors rather than a single score [31]. 5. Modular pipeline design for rapid iteration [32]. Group 4: Criticism and Future Plans - Despite the praise for transparency, the algorithm has been criticized for lacking a time decay mechanism for historical blocking, which could unfairly impact account recommendations [33][35]. - Musk has committed to ongoing transparency, stating that updates will continue to be released every four weeks [39].