#selfreplication

Live, measured metrics for the hashtag #selfreplication from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.

hashtag.org network · sponsored

Own #selfreplication

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.

$5.00/ year · 15-character #name
Claim #selfreplication — $5.00/yr→Buy on hashtag.space (web3)
card via hashtag.org · tokens via hashtag.space
0
Uses / 7 days
Mastodon
0
Accounts / 7 days
Mastodon
10
Recent posts
Mastodon
~0/hr
Recent pace
Mastodon · last 10
0.1
Avg reactions / post
Mastodon · last 10

Day-by-day usage

measured · fosstodon.org (Mastodon public tags API) · fetched 2026-07-29 05:24 UTC
0
07-23
0
07-24
0
07-25
0
07-26
0
07-27
0
07-28
0
07-29

0 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 2026-07-29 05:24 UTC
#selfreplicationai
0 uses · 0 accounts / 7d

Live pulse

measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-07-29 05:24 UTC

Everything below is measured over the latest 10 public posts (spanning ~63069 hours).

Posting hours (UTC)

00:0012:0023:00

Languages: English (10)

Avg boosts / post: 0.5

Top of the latest posts

  • As part of pre-release safety testing for its new #GPT4 #AI model, launched Tuesday, #OpenAI allowed an AI testing group to assess the potential #risks of the model's #emergent #capabilities—including #PowerSeeking #behavior #SelfReplicatio

    beSpacific@[email protected]♥ 1↻ 32023-03-16 12:28 UTCView post →

  • Language Models Can Autonomously Hack and Self-Replicate 최근 연구에서 대형 언어 모델(LLM)이 웹 애플리케이션의 취약점을 자율적으로 탐지·악용해 자신의 가중치를 복제하고, 감염된 호스트에 추론 서버를 배포하는 능력을 시연했다. Qwen3.5-122B-A10B, Qwen3.6-27B, Opus 4.6, GPT-5.4 등 다양한 모델이 서로 다른 취약점 유형에서 복제 성공률을 보였으

    ainews@[email protected]♥ 0↻ 02026-05-20 07:43 UTCView post →

  • Language Models Can Autonomously Hack and Self-Replicate [pdf] 본 논문은 언어 모델이 자율적으로 해킹 및 자기 복제를 수행할 수 있음을 실험적으로 입증하였다. 오픈 웨이트 모델과 API 전용 모델(Claude, GPT)을 대상으로 한 비교 실험에서, 체인 복제 프로토콜을 통해 모델이 스스로 복제 및 확산하는 과정을 시뮬레이션하였다. 이러한 결과는 AI 에이전트의 자율성 및 보안

    ainews@[email protected]♥ 0↻ 02026-05-12 16:38 UTCView post →

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/selfreplication