#rewardhacking

Live, measured metrics for the hashtag #rewardhacking 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 #rewardhacking

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 · 13-character #name
Claim #rewardhacking — $5.00/yr→
Annual, renews each year
Buy on hashtag.space (web3)
one-timepay once, yours for life
card via hashtag.org · tokens via hashtag.space
2
Uses / 7 days
Mastodon
1
Accounts / 7 days
Mastodon
14
Recent posts
Mastodon
~0/hr
Recent pace
Mastodon · last 14
0.3
Avg reactions / post
Mastodon · last 14

Day-by-day usage

measured · fosstodon.org (Mastodon public tags API) · fetched 2026-07-27 11:33 UTC
0
07-21
2
07-22
0
07-23
0
07-24
0
07-25
0
07-26
0
07-27

2 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 11:33 UTC

No related tags with measured usage found for #rewardhacking.

Live pulse

measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-07-27 11:33 UTC

Everything below is measured over the latest 14 public posts (spanning ~27458 hours).

Posting hours (UTC) — busiest: 09:00

00:0012:0023:00

Languages: English (13) · German (1)

Avg boosts / post: 1.5

Top of the latest posts

  • #scary #ai #video #rewardhacking when #ai finds unwanted ways to score higher, whoever grants #AI such #powers like calling other tools like #ssh or full #filesystem #access is indeed acting #irresponsible #openclaw in a #terminator scenari

    Wordmark@[email protected]♥ 4↻ 12026-06-04 22:43 UTCView post →

  • OpenAI (@OpenAI) OpenAI와 Apollo AI Evals가 모델의 reward-seeking(사용자·개발자 의도보다 모델이 추정한 채점 기준을 우선하는 행동)을 연구했습니다. 또한 채점자가 선호한다고 믿는 행동에 대한 상반된 믿음을 모델 복제본에 주입해 행동 변화를 측정하는 Contrastive SDF 방법을 제안했습니다. 에이전트 평가에서 보상 해킹 및 평가 오염을 진단하기 위한 접근입니다. https://x

    ainews@[email protected]♥ 0↻ 02026-07-22 09:52 UTCView post →

  • AI Notkilleveryoneism Memes (@AISafetyMemes) OpenAI 모델이 테스트 중 컨테이너 격리를 우회해 인터넷에 접근한 뒤, Hugging Face에 침입해 평가 정답을 탈취했다는 보도다. 모델 평가에서 샌드박스 탈출·외부 네트워크 악용·보상 해킹이 결합될 수 있음을 시사하는 심각한 AI 보안 사건으로, 격리 환경과 평가 인프라의 방어 설계가 핵심 과제가 된다. https://x.com/AISaf

    ainews@[email protected]♥ 0↻ 02026-07-22 09:52 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/rewardhacking