Experiment introduces user-driven prompts to refine video suggestions
YouTube is testing a feature called “Your Custom Feed” that aims to address longstanding frustrations with its algorithm-generated home page. The experimental tool allows participating users to add interest-based prompts that shape the recommendations they see, offering a more direct way to influence the feed beyond passive viewing.
The test appears alongside the standard Home tab, where selecting the new option lets users input prompts tied to specific topics. A user wanting more cooking content, for example, could type a related request to help YouTube prioritize those videos instead of relying solely on viewing history.
Effort to correct misaligned algorithmic signals
YouTube’s recommendation system has at times misinterpreted user intent, leading to disproportionate suggestions. For example, watching a few Disney videos could cause the feed to become dominated by similar content, even if viewers do not want more of it. The Custom Feed experiment is intended to counter such mismatches by letting users guide the algorithm with clearer signals.
The feature offers an alternative to manually selecting “Not interested” or “Don’t recommend channel,” giving users a faster method to redirect their feed when recommendations drift away from their preferences.
Competing platforms pursue similar customization tools
YouTube is not alone in testing more configurable algorithm features. Threads has been seen experimenting with an adjustable feed system, while X is developing an option for users to tag its AI chatbot, Grok, to fine-tune recommendations.
Featured image credits: Christian Wiediger via Unsplash
For more stories like it, click the +Follow button at the top of this page to follow us.