Challenges with BYOA and social networks
AI summary of the linked articleDiscussion of bring-your-own-algorithm (BYOA) for social networks raises several challenges, according to the article. It notes that world-class consumer apps in 2024 use machine learning based feeds, which consumers prefer by time spent, and that building a good ML feed requires significant resources. A feed marketplace would likely need a backend where developers upload models that clients run, raising privacy concerns. A developer building a Farcaster client, Kartik, reported that feed performance was much harder than expected and that running the backend cost about $2k per month for a few hundred active users. |
Recommended by 3 curators |
1 comment 0xluo.ethSubmitter Yes, building recommendation algorithms presents numerous challenges. That's why many are eager for Warpcast, with its vast user base and strong development capabilities, to excel in this area. These algos can also combat spam and bots while uncovering hidden high-quality users, making everyone's feed more engaging. |
More from dwr.email on Kiwi News |
