#sber
Live, measured metrics for the hashtag #sber from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.
Own #sber
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 · fosstodon.org (Mastodon public tags API) · fetched 2026-07-27 08:06 UTC0 uses by 0 unique accounts across the window. Real per-day counts, not estimates. Newest bar is today so far.
Related hashtags
measured · fosstodon.org (Mastodon public search API) · fetched 2026-07-27 08:06 UTCLive pulse
measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-07-27 08:06 UTCEverything below is measured over the latest 34 public posts (spanning ~46358 hours).
Posting hours (UTC) — busiest: 11:00
Languages: Russian (19) · English (13) · Norwegian (1)
Avg boosts / post: 0.2
Top of the latest posts
Title: P2: P2: Conference of largest IT gov-corporation. [2025-12-11 Thu] For video models pre-train: - PyTorch FSDP - Sequence parellelism - Activation checkpoing - Flash Attention 3 - NABLE Major LLM flaws as I see: - not ability to say I
Title: P1: P2: Conference of largest IT gov-corporation. [2025-12-11 Thu] tree, large modules is hard to form during trainingh. Two standard way of using Mixture of Experts (MoE) is switching whole LLMs OR by replacing most dense FFN block
Title: P0: P2: Conference of largest IT gov-corporation. [2025-12-11 Thu] AI agent build as one major model and small fast models for tools calling and stop thinking. Good readings: - https://www.anthropic.com/engineering/claude-think-tool
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/sber