EMBEDDINGS
2 items
2 posts
Blog
EmbeddingGemma 2 Guide: Local Multimodal Embeddings for CodeEmbeddingGemma 2 is a 740M open model that embeds code, images, video and audio in one space. Specs, Matryoshka storage math, and where it breaks.
Blog
Ternlight: A 7 MB Embedding Model That Runs Entirely in the BrowserTernlight ships a ternary-quantized sentence encoder at 7 MB that runs semantic search at 5ms per embedding - entirely client-side via WASM, no API calls required. Here is how it works, what HN thinks, and where browser-side embeddings make sense.
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever