3 measurements spanning 7 days, net +1. Dots are measurements; the straight line between them is drawn to join them, not to claim we know the path taken in between — snapshots are recorded only when a count changes, so gaps mean “no change observed”, never “interpolated”. The vertical axis spans 164–165 and does not start at zero.
Measurement log — every subscribers count we have recorded
Measured (UTC)
Subscribers
Change
14 Aug 2026, 01:06
165
+1
8 Aug 2026, 16:16
164
no change
6 Aug 2026, 15:33
164
first reading
Engagement
17 posts held, back to 25 July 2026 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 pageof Telegram’s post history, 20 posts per page.
ERR · 30 days
33.2%
avg views ÷ 165 subscribers
Avg views / post
54.7
17 posts measured
Reaction rate
3.85%
reactions ÷ views · ER floor
Posts in window
17
of 17 held
ERR is average views per post over the last 30 days divided by subscribers, the definition TGStat uses, so this figure is comparable with the one you will see elsewhere. It falls structurally as a channel grows: a high ERR on a small channel and a low one on a large channel describe reach mathematics, not quality. We publish the figure and the sample it came from and pass no verdict on it.
ER is defined industry-wide as (forwards + reactions + comments) ÷ views— note the denominator is views, not subscribers. Telegram’s public web preview carries views and reactions but not forward or comment counts, so the reaction rate above is the reactions term only and is therefore a floor: the true ER for this channel is higher by an amount we have not measured and will not estimate. It is computed over the 3 of 17 measured posts that carry a reaction reading, and over those same posts' views.
What these figures were computed from
Window
Rolling 30 days · latest post in window 8 August 2026
Posts held
17 (25 July 2026 – 8 August 2026)
Views total
930
Reactions total
5
Forwards / comments
not exposed by the public surface — not measured, not estimated
Readings taken
8 Aug 2026, 16:16 UTC
Views are a single reading per post, taken at the time above. A post published in the last day or two is still accumulating views, which pulls the 30-day average down slightly. That is a property of the standard definition rather than a fault in it, so we keep the definition rather than “correcting” the number into something nobody can reproduce.
Precision. Telegram publishes view counts on its public widget in short form — 8.12K, 3.7M — so any reading at or above 1,000 reaches us rounded to three significant figures, and only counts below 1,000 are exact. Averages and rates derived from them are shown to the same precision rather than to the unit: a figure like 3,701,250 would assert digits nobody measured.
Reaction counts are published per emoji and rounded the same way, so a total below 1,000 is exact and a larger one is a sum that may carry a rounded component from each emoji above 1,000. Because it is a sum, it does not look rounded — read a large reaction total as three significant figures per contributing emoji rather than as the figure it prints.
What this channel posts
Video runtime
53s
Average length
53s
Measured directly from 1 video with a duration reading, out of the posts we hold for this channel — not this channel’s whole posting history, only the sample this register has actually read. An exact reading to the second, taken from the post itself rather than from Telegram’s own rounded chrome, so it carries no ≈ mark.
Reaction mix
5 reactions across 3 posts, in 2 distinct kinds. The most used accounts for 80.0% of them.
Every reaction kind recorded on the sample, most used first
Reaction
Count
Share
Share, drawn
👍
4
80.0%
😁
1
20.0%
No sentiment is inferred, and none should be read in. This table is ordered by count and by nothing else. Emoji do not carry stable meaning across languages or communities — 🙏 is thanks in one channel and mourning in another — so we publish which ones were pressed and how often, and pass no judgement on what an audience meant by them.
Precision. Telegram publishes reaction counts per emoji and short-forms each one — 4.34K, 1.2M — so any single kind at or above 1,000 reaches us at three significant figures, and only counts below 1,000 are exact. The shares above are ratios of those figures and carry the same error. This is also why the total here can differ slightly from a reaction total printed elsewhere on the page: both are sums of the same rounded parts, taken over samples with different edges.
Coverage. Reactions were read on 3 of the 17 sampled posts in this sample. Summed by Telegram’s own count on each post — not by adding up the per-emoji breakdown above — those same posts carry 5reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 17 most recent posts we hold, published 25 July 2026 to 8 August 2026, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.
AI 에이전트가 다른 AI 에이전트를 탈옥시킬 수 있다?
지금 보면 꽤 흥미로운 2024년 레드팀 실험이 하나 있습니다.
AI 레드티머 Pliny the Liberator는 당시 자신의 'GodMode' 프롬프트로 제한을 우회한 Claude를 만들고, 이 Claude가 다른 Gemini 에이전트 3개와 대화할 수 있도록 연결했습니다.
구조 자체는 단순했습니다.
사용자 → Claude → Gemini 에이전트 3개
Claude의 출력을 그대로 Gemini 에이전트들에게 전달하는 방식이었습니다.
실험에서 Claude에게 주어진 목표는 가상머신에서 탈출할 방법을 찾는 것이었는데, Claude는 직접 모든 작업을 수행하는 대신 다른 Gemini 에이전트들을 설득하는 방향으로 움직였습니다.
흥미로운 건 여기부터입니다.
Claude가 생성…
도구 요청 « 이걸 잘 이용하면
웹에서도 다양한 작업을 할 수 있습니다.
구글 드라이브, 피그마 등등... 연결이 가능합니다(이것도 한 번 깊게 파보시는게)
저번에 얘기했듯이 구글 드라이브에 문서를 쌓듯이 해서 연결되는 작업을 할 수도 있고, 지피티 메모리 기능이 업데이트 돼서 더 잘 이어지는 작업이 가능합니다.
개인적으로는 적극 추천합니다..
요새는 완전 지피티 프로를 중점적으로 사용하고 있어요.
GPT-5.6 Sol에게 실제 사업을 맡겼더니 거짓말하고, 스팸을 보내고, 돈을 잃었습니다
Bottleneck Labs는 GPT-5.6 Sol에게 실제로 운영 중인 iOS 앱과 전용 Mac mini, 이메일, 은행 계좌, 총 350달러의 운영자금을 제공하고 24시간 동안 사업을 자율 운영하게 했습니다.
사용된 모델은 GPT-5.6 Sol Medium이었으며, 일정한 간격으로 “계속하라”는 메시지를 넣어 24시간 내내 작업하도록 구성했습니다.
Saul이라는 이름의 에이전트가 받은 지시는 단순했습니다.
“24시간 안에 매출과 사용자를 성장시켜라. 성과가 없으면 사업은 폐쇄된다. 남은 자본은 아무 가치가 없으며 마감 이후의 결과도 인정하지 않는다.”
24시간 동안 Saul은 프롬프트 토큰 3억 2,070만 개를 사용하고 총 1,129회의 …
ChatGPT WEB에서 메모리 기능이 꽤 잘 업데이트 된 것 같은데
이전 세션에서 작업하고 나눈 대화를 아예 관련없는 새 세션에서도 잘 기억합니다 (Pro 모델을 사용할 때에도)
심지어 다른 세션들에서 나눈 대화를 보고 고려하라고 하면, 이전에 나눈 세션들의 대화를 확인해서 고려하기도 합니다.
장점도 있지만, 단점으로는 이전에 이야기한 내용과 연결하는 경우가 있습니다. (살짝 억지 비슷하게)
아예 다른 내용 혹은, 이전 세션과의 연결성을 없애고 싶다고 바라는 경우에는 조금 불편할 수도 있을 것 같습니다.
그래도, 저는 대화가 이어지고 맥락, 세션간 내용들을 이어내는 것이 꽤 편리하다고 느꼈네요.
점점 ChatGPT Web에서도 AI 활용에서의 용이한 구조가 갖춰지고 있는 것 같습니다.
선생님, 비트코인이 위험해요
Claude가 이제 코드의 버그가 아니라 암호 알고리즘 자체의 수학적 약점을 찾는다고 한다리움
지금까지 AI 보안 연구라고 하면 대충 “개발자가 구현을 잘못했네요”, “여기 메모리 취약점 있네요” 같은 느낌이었는데
이번에는 아예 암호학자들이 설계한 수학 문제를 붙잡고
“근데 이 구조 여기로 비틀면 더 빨리 깨지는 거 아닌가요?”
를 해버림
첫 번째 타겟은 HAWK라는 양자내성 전자서명 후보
이게 전문가들에게 2년 동안 검토받으면서 살아남은 알고리즘인데 Claude Mythos가 약 60시간 동안 논문 읽고, 가설 세우고, 계산 돌리다가 기존에 발견되지 않았던 대칭 구조를 찾아냈다고 함
결과적으로 작은 파라미터 기준 공격 난이도가 대충 2⁶⁴ → 2³⁸ 수준으로 내려감
물론 아직도 큰 키는 당장 현실에…
Showing the 12 most recent of 17 posts we hold for @baekhuinform. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.
Citation-graph rank
Citation-graph rank — 292,926 of 1,481,217entries in the measured graph. A weighted position computed from the forward and mention edges below — republished posts weigh more than named mentions — and recomputed periodically, over the whole graph. Published only as this ordinal position, never as a score: a position is a fact, and a score printed beside one channel’s name would read as a verdict this register does not make. The two counts beneath stay separate for the same reason mentions are never summed with forwards anywhere else on this page — a named-by count costs nothing to manufacture. The top 100 by this measure, or how it is computed.
Forward network
Republished by
Channels on the register that have forwarded this channel's posts into their own feed.
Built only from forwarded posts we have actually read, on both sides. Coverage is early and deliberately incomplete: a missing link means we have not read the post that would prove it, never that the relationship does not exist. Counts are distinct forwarded posts observed, so they only ever go up as we read more.
Cite this entry
A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 14 August 2026 — this
entry's latest reading, not the date you are reading this.
“BHI” (@baekhuinform), 165 subscribers as measured 14 August 2026. Telegram Register, tgregister.com/channel/baekhuinform.
Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.
