Cosine is a social platform where discovery is driven by semantic similarity instead of follower graphs. Instead of relying on popularity, hashtags, or communities, Cosine connects people and discussions based on meaning and shared interests. You can: • Discover people using prompts • Find posts through semantic search • Explore related ideas and discussions • Control your feed with advanced vector controls — adjust weights, freeze interests, reset or explore new dimensions

Figr AI: UX Agent for Product Teams — Learns your product. Thinks through UX

Learns your product. Thinks through UX

Hey Product Hunt 👋 I built Cosine after noticing something strange about how most social platforms work. Discovery on today’s platforms is mostly driven by **followers, popularity, or fixed communities**. That means a lot of interesting ideas never reach the people who would actually care about them. Cosine experiments with a different model: **semantic social discovery**. Instead of follower graphs deciding what you see, posts and people are connected through **meaning and shared interests**. Some things you can do on Cosine: • Discover people using natural prompts • Search discussions by meaning instead of keywords • Explore related ideas and conversations • Control how your feed evolves with vector-based feed controls (freeze, reset, adjust interests) The goal isn’t to replace existing platforms overnight. It’s to explore a different way social discovery could work: **relevance over popularity**. I’d really love to hear your thoughts: • Does semantic discovery make sense for social platforms? • Would you prefer feeds you can control instead of opaque algorithms? All feedback — positive or critical — is welcome. Thanks for checking it out!

Figr AI: UX Agent for Product Teams — Learns your product. Thinks through UX

Learns your product. Thinks through UX

Cosine

Social network powered by semantic discovery, not followers

Social network powered by semantic discovery, not followers