Source Code for the X Recommendation Algorithm
Posted4 months agoActive4 months ago
github.comTechstory
skepticalmixed
Debate
40/100
TwitterAlgorithmRecommendation SystemSocial Media
Key topics
Twitter
Algorithm
Recommendation System
Social Media
The release of Twitter's recommendation algorithm source code on GitHub sparks discussion about the algorithm's impact on user experience and potential biases, with some users expressing frustration and skepticism.
Snapshot generated from the HN discussion
Discussion Activity
Light discussionFirst comment
2h
Peak period
3
2-3h
Avg / period
1.8
Key moments
- 01Story posted
Sep 8, 2025 at 11:26 PM EDT
4 months ago
Step 01 - 02First comment
Sep 9, 2025 at 1:07 AM EDT
2h after posting
Step 02 - 03Peak activity
3 comments in 2-3h
Hottest window of the conversation
Step 03 - 04Latest activity
Sep 9, 2025 at 9:48 AM EDT
4 months ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
ID: 45177043Type: storyLast synced: 11/20/2025, 7:45:36 PM
Want the full context?
Jump to the original sources
Read the primary article or dive into the live Hacker News thread when you're ready.
So, yeah, they try to make inferences about what you'll like based on who you interact with, they invariably prove to be wrong, and here we are. I suppose they may also be paid to astroturf interests to other people, but who knows?
It was probably good for maximizing "engagement", but that meant turning Twitter (now X) into an open sewer.