#rlhf
Live, measured metrics for the hashtag #rlhf from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.
Own #rlhf
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 2026-10-30 05:43 UTC1 uses by 1 unique accounts across the window. Real per-day counts, not estimates. Newest bar is today so far.
Related hashtags
measured · mastodon.online (Mastodon public search API) · fetched 2026-10-30 05:43 UTCLive pulse
measured · mastodon.online (Mastodon tag timeline) · fetched 2026-10-30 05:43 UTCEverything below is measured over the latest 40 public posts (spanning ~4774 hours).
Posting hours (UTC) — busiest: 16:00
Languages: English (25) · Russian (12) · Czech (1) · Japanese (1)
Avg boosts / post: 0.2
Top of the latest posts
Почему геймификация убьет разум в ИИ: скрытые риски коммерческого сбора данных и тупик Alignment Современная гонка искусственного интеллекта полностью сфокусирована на терафлопсах, объемах контекстных окон и бенчмарках. Однако за рамками об
Aiden Bai (@aidenybai) 포스트트레이닝을 대규모로 실용화하려면 모델 평가 도구의 기본 경험이 크게 개선돼야 한다는 지적이다. 롤아웃 비용, 흔한 거짓양성·거짓음성 및 리워드 해킹, 과도하게 엄격하거나 부정확한 테스트 지시문, 데이터 검토의 높은 인력 비용이 핵심 병목으로 제시됐다. https://x.com/aidenybai/status/2108703154758185277 #modelevaluation #post
fly51fly (@fly51fly) Stanford·토론토 연구진이 인간 선호를 검증 가능한(verifiable), 언어로 명시 가능한(articulable), 암묵적(tacit) 요소로 구분해 다루는 프레임워크를 제안했다. LLM 정렬·RLHF에서 어떤 선호를 명세·평가·학습할 수 있는지 분석하는 연구로 보인다. https://x.com/fly51fly/status/2107230553103896615 #aialignment
What “rlhf” means
WikipediaIn machine learning, reinforcement learning from human feedback (RLHF) is a technique to align an intelligent agent with human preferences. It involves training a reward model to represent preferences, which can then be used to train other models through reinforcement learning.
“Reinforcement learning from human feedback” on Wikipedia (CC BY-SA) →#rlhf across platforms
every network with a public tag surfaceFollow #rlhf 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/rlhf