DHDylan Hoggininfocruncher.hashnode.dev·Sep 25 · 8 min readStatic embeddings: a practical guide to model2vecSentence-transformer embeddings work well, but they are slow on a CPU. For a few thousand texts, the speed doesn't matter. When you embed millions of texts, or need embeddings within a tight latency b00
DHDylan Hoggininfocruncher.hashnode.dev·Sep 23 · 33 min readOpen alternatives to JevThe open System One models you can run yourself Jev is a week old and has been hard to avoid since launch. TypeSafe's "System One" model is built to be called by software. You post one state plus a ma00
DHDylan Hoggininfocruncher.hashnode.dev·Sep 23 · 11 min readLecture summary: Trends in AI by Jeff DeanJeff Dean, Chief Scientist for Google Research and Google DeepMind presents his talk "Important Trends in AI: How Did We Get Here, What Can We Do Now, and Where are We Headed?" as part of the Princeto00
DHDylan Hoggininfocruncher.hashnode.dev·Sep 23 · 14 min readEmbedding model dimensions for image search: what the published evidence showsPublicly published results suggest that embedding vectors often add cost without meaningfully improving image-search quality, so smaller dimensions are worth evaluating. 1. Two common assumptions abou00
