0 views collected around this technical thread.
The upcoming retirement of Chrome Manifest V2 forces extensions to adopt Manifest V3, which requires Chrome Web Store review for updates, dramatically slowing ad‑blocker rule changes and giving YouTube an advantage, while other browsers remain unaffected.
This article examines YouTube's massive backend infrastructure, detailing its use of MySQL with Vitess for horizontal scaling, caching with Memcache, coordination via Zookeeper, cloud‑native deployment on Kubernetes, CDN delivery, and the storage systems (GFS, BigTable) that enable billions of users to upload and stream petabytes of video data.
This article examines YouTube’s massive backend infrastructure, detailing how the platform stores billions of videos using MySQL, Vitess for horizontal scaling, sharding, replication, disaster management, cloud‑native deployment on Kubernetes, and the supporting storage systems such as GFS and BigTable.
This article explains why and how sample weighting is used in machine learning, illustrates YouTube's conversion of video watch time into sample weights to align with its commercial goals, and describes practical weighted‑logistic‑regression techniques applied to improve game recommendation systems.
The article explains why recommendation‑system optimization goals must align with business objectives, illustrates this with YouTube’s watch‑time target and Alibaba’s multi‑task CVR/CTR model, and stresses the strategic importance of defining clear goals to guide cross‑team collaboration.
The article examines YouTube’s large‑scale recommendation system, detailing its deep‑learning architecture, the challenges of scale, freshness and noise, and the design choices in candidate generation, ranking, data collection, and evaluation that together deliver over 70% of user watch time.
This article examines YouTube's large‑scale architecture, detailing its platform components, web and video services, database evolution, data‑center strategy, and key lessons for building high‑concurrency, fault‑tolerant backend systems.