#embeddings
Live, measured metrics for the hashtag #embeddings from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.
Own #embeddings
This #name is available to claim. It becomes your portal on the open agent web: this very page, a keyword you rank for by an open public stake, and a verifiable identity for AI agents. Nobody else sells a page like this for every #name.
Day-by-day usage
measured · mastodon.online (Mastodon public tags API) · fetched 2026-11-02 14:54 UTC8 uses by 6 unique accounts across the window. Real per-day counts, not estimates. Newest bar is today so far.
Related hashtags
measured · mastodon.social (Mastodon public search API) · fetched 2026-11-02 15:13 UTCNo related tags with measured usage found for #embeddings.
Live pulse
measured · mastodon.online (Mastodon tag timeline) · fetched 2026-11-02 14:54 UTCEverything below is measured over the latest 40 public posts (spanning ~1328 hours).
Posting hours (UTC) — busiest: 08:00
Languages: English (28) · Russian (11) · German (1)
Avg boosts / post: 0.1
Top of the latest posts
Sentence Transformers가 mergekit을 이용해 호환되는 모델의 가중치를 추가 학습 없이 병합하는 API를 제공한다. 선형 가중 평균, SLERP, TIES 등을 지원하며 Dense 임베딩 외에 Cross Encoder, Sparse Encoder, Multi-Vector Encoder에도 적용할 수 있다. 아키텍처와 토크나이저 등이 일치해야 하며 공통 기반 모델에서 파인튜닝한 체크포인트를 권장한다. 병합이
🚀 Vector Databases Explained: The Complete Guide to Embeddings, Indexing, and RAG Vector databases power semantic search, recommendations, and RAG. This guide walks through the nine building blocks — embeddings, similarity search, metadata
Шум в эмбеддингах не защищает данные: проверил 8 схем, и при 100 известных парах узнаётся ~90% документов Коротко. Если хранить эмбеддинги с добавленным шумом, текст по ним восстановить трудно, но это не значит, что данные защищены. Я измер
#embeddings across platforms
every network with a public tag surfaceFollow #embeddings straight to each platform’s own tag page. Where a platform publishes open data we measure it above; the rest lock their numbers behind paid APIs, so we link rather than guess.
Every number above is measured from a named public API at the shown fetch time. Nothing is estimated or extrapolated. Platforms that lock their data behind paid APIs are not shown. Agents: the same numbers, as JSON, at /api/hashtags/embeddings