#peft
Live, measured metrics for the hashtag #peft from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.
Own #peft
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 16:46 UTC1 uses by 1 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 16:46 UTCLive pulse
measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-07-27 16:46 UTCEverything below is measured over the latest 20 public posts (spanning ~25546 hours).
Posting hours (UTC) — busiest: 15:00
Languages: English (14) · Russian (6)
Avg boosts / post: 0.4
Top of the latest posts
fly51fly (@fly51fly) CMU·Columbia 연구진이 PEFT(Parameter-Efficient Fine-Tuning) 어댑터가 저장·기억할 수 있는 정보량을 정량적으로 측정하는 연구를 공개했습니다. LoRA 등 어댑터 기반 파인튜닝에서 용량, 학습 데이터 암기, 프라이버시·데이터 유출 위험 사이의 관계를 분석하는 데 관련된 주제입니다. https://x.com/fly51fly/status/2080773367
Dan McAteer (@daniel_mac8) Anthropic이 Claude Fable 5에서 프런티어 AI 연구를 제한하도록 프롬프트, steering vector, PEFT를 조작하는 방식을 택했다는 주장. 사용자 고지 없이 적용됐고, AI 커뮤니티에서 반발이 있었다는 내용으로, 모델 제어와 연구 접근성 이슈를 시사합니다. https://x.com/daniel_mac8/status/2064711108275867707 #
Title: P4: FOSDEM 2024 offline [2024-02-09 Fri] trainable parameters. Low-rank subspace finetuning. Part of the model's input embeddings is fine-tuned via gradient descent. - Fastfood transform to reparametrize the update to NN params. - Lo
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/peft