Study reveals why algorithms misalign: users engage more with misaligned content

msbernst · x · 2026-08-21

A paper finds that while followed posts are value-aligned, "For You" recommendations are often misaligned. Explanation: users are especially likely to reply to value-misaligned content, which the algorithm misinterprets as positive engagement.

Related event: PNAS study finds X's algorithm amplifies content conflicting with users' values(5 posts)→

Original post →

More from Safety

Safety channel →