@Xuegaogx: I probably understand the new algorithm. Now the new algorithm should recommend your tweets more to people who might interact with you. I feel that although my tweet traffic has decreased recently, the interaction rate has increased a lot. I probably understand the new algorithm. Now the …
Summary
The user observed that the new algorithm on X platform recommends tweets more to people who may interact, resulting in lower traffic but higher interaction rate.
View Cached Full Text
Cached at: 05/17/26, 06:21 PM
I roughly understand the new algorithm now.
The new algorithm should now recommend your tweets more to people who are likely to interact with you.
I feel that although my tweet traffic has dropped recently,
the interaction rate has increased significantly.
Am I right? @elonmusk
Ice Cream Warrior🍦 (@Xuegaogx): Already feeling the power of X’s new algorithm.
Based on my past experience, both of these tweets could have hit 50k–100k.
🤔
Similar Articles
@FinanceYF5: The latest 𝕏 algorithm has been uploaded to GitHub. Someone then used Grok Build to analyze it. The biggest conclusion: X is no longer a simple like/reply system. It has become a recommendation engine driven by Grok. 10 things creators need to know:
The latest 𝕏 algorithm has been released on GitHub. After analyzing it with Grok Build, it was pointed out that X has transformed from a simple like/reply system into a recommendation engine powered by Grok, and listed 10 things creators need to know.
@FinanceYF5: What you scroll through on X every day — the algorithm behind it has now been released on GitHub by Musk. This For You system simultaneously grabs content from people you follow and candidate posts from across the network, then uses a Grok-based transformer to predict the posts you're most likely to interact with. The black box of the information feed is being pried open…
Musk has open-sourced X's (formerly Twitter) For You recommendation algorithm on GitHub. The algorithm uses a Grok-based transformer to predict user interaction preferences.
@DeRonin_: BREAKING: X dropped the new ranking algo today. What's dead and what wins for bangers: [ what just died ]: - spam posti…
X released a new ranking algorithm that penalizes spam, reply farming, text-only posts, recycled viral templates, generic AI tool roundups, engagement bait, motivational fluff, and engagement pods; it rewards original takes from small accounts, threads with clear narrative arcs, text+media combos, contrarian takes with proof, long-form posts, responding to replies quickly, and consistent posting cadence.
@vista8: Last night I casually tested Knowly developed by the @Ethan_Yang_AI team. Tried interpreting YouTube videos and arXiv papers – the results were stunning. Except for a rather limited free quota and slightly slow vector processing. In terms of both product interaction and interpretation quality, it's no less impressive than NotebookLM. With a Chrome extension that has only a few users but has already been selected by Google as a featured pick, its strength is evident. Official site in comments https://t.co/62NkT3pO4G
Introduces Knowly AI tool, capable of interpreting YouTube videos and arXiv papers with impressive results. Interaction and interpretation quality rival NotebookLM. Comes with a Chrome extension already featured by Google. Drawbacks: limited free quota and slightly slow vector processing.
@Honcia13: Never worry about missing hot topics scrolling through dozens of apps again! This 50k-star open-source tool TrendRadar directly aggregates hot topics from across the web, uses AI to filter precisely based on your interests, pushing only relevant content to your phone! Supports keywords + natural language descriptions like “what I want to see”, AI auto-translation + briefing generation, one-click push to…
TrendRadar is an open-source hot-topic aggregator that uses AI to filter content based on interests and generate briefings, supporting Docker deployment and multi-platform notifications.