#memorization
Live, measured metrics for the hashtag #memorization from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.
Own #memorization
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 20:41 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 20:41 UTCLive pulse
measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-07-27 20:41 UTCEverything below is measured over the latest 39 public posts (spanning ~35066 hours).
Posting hours (UTC) — busiest: 06:00
Languages: English (35) · German (1) · Portuguese (1) · Polish (1)
Avg boosts / post: 0.7
Top of the latest posts
In our own work, we researched memorization in language models for code and ways to let them regurgitate training data: > From the training data that was identified to be potentially extractable we were able to extract 47% from a CodeGen-Mo
I don’t have a good memory for names, facesr, and details. I’ve built up a system of note taking and #memorization to work around my limits, and now I’ve written about it. https://www.daviddaly.me/2023/12/the-nerdiest-thing-i-do.html This w
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
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/memorization