4 measurements spanning 6 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 5,310–5,313 and does not start at zero.
Measurement log — every subscribers count we have recorded
Measured (UTC)
Subscribers
Change
12 Aug 2026, 14:15
5,312
+2
9 Aug 2026, 11:01
5,310
-3
6 Aug 2026, 14:08
5,313
no change
6 Aug 2026, 04:32
5,313
first reading
Engagement
18 posts held, back to 8 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 8 pagesof Telegram’s post history, 20 posts per page.
ERR · 30 days
44.2%
avg views ÷ 5,312 subscribers
Avg views / post
2,350
14 posts measured
Reaction rate
0.991%
reactions ÷ views · ER floor
Posts in window
14
of 18 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 13 of 14 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 9 August 2026
Posts held
18 (8 July 2026 – 9 August 2026)
Views total
32,880
Reactions total
305
Forwards / comments
not exposed by the public surface — not measured, not estimated
Readings taken
12 Aug 2026, 04:29 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
10s
Average length
10s
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
401 reactions across 17 posts, in 7 distinct kinds. The most used accounts for 46.6% of them.
Every reaction kind recorded on the sample, most used first
Reaction
Count
Share
Share, drawn
👍
187
46.6%
😁
75
18.7%
❤
72
18.0%
🤯
31
7.73%
👎
15
3.74%
🤔
15
3.74%
🎉
6
1.50%
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 17 of the 18 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 401reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 18 most recent posts we hold, published 8 July 2026 to 9 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.
Telegram Stars
Stars received
7
across the posts below
Posts paid on
4
of 18 we hold a reading for · 22%
Most on one post
3
single highest reading
A paid reaction is a reader spending Telegram Stars — bought with money — on a post by @ai_driven. Telegram publishes the count on the public post preview alongside ordinary reactions, and this register reads it there. It is the only figure on this site that measures money moving rather than attention.
Stars are not reactions, and the two are never added. They are rendered in the same strip on Telegram and counted in the same shape, but one is a tap and the other is a purchase. The reaction totals and the engagement rate elsewhere on this page exclude every figure in this section, and no rate here is computed against a reaction count.
This is not revenue, and we publish no currency figure. What a Star costs a reader and what it pays a channel are different numbers, Telegram takes a share we cannot observe, and the terms have changed. Converting a Star count into money would be an estimate dressed as a measurement, so the count is where we stop.
Counted over the 18 most recent posts we hold for this entry, published 8 July 2026 to 9 August 2026. Star counts above 1,000 reach us in Telegram’s short form and carry the same three-significant-figure rounding as everything else on this page.
Luna - потрясающая модель для Code Review
Собственно, похоже, что GPT 5.6 Luna max сейчас лучшая моделька для код ревью по соотношению цена-качество, да и в принципе одна из лучших моделей для ревью.
Это подтверждают как наши внутренние бенчи на Code Review, так и новый бенчмарк от Vercel DeepsecBench (да да, бенч на секьюрити в принципе можно смело экстраполировать на код ревью).
С учетом ее предельной дешевизны, …
Не все мне нравится в UX десктопной версии Claude Code, но надо отдать им должное - фича просмотра прототипов прямо в диалоге Claude Code просто бомбическая.
Раньше для этого требовалось просить сгенерить HTML, и отдельно открывать ее в браузере - не очень удобно.
Напомню, что прототип - это супер крутой и быстрый способ еще до того, как агент написал хоть строку кода, посмотреть как будет выглядит результат и направ…
Важность исследования контекста
Тема заезженная, но я сейчас кодю с Opus 5 и, конечно, провожу новую фичу через research стадию и интервью. Собственно, хоть фича и совсем небольшая, даже после того, когда кажется, что все готово, я все равно прошу опуса доисследовать контекст и проработать корнер кейсы и он действительно находит что-то новое и мы учитываем дополнительные инварианты, т. е. не зря просили доисследоват…
Какой-то баг с реациями в ТГ случился (навайбкодили опять) и были доступны только дизлайки и сомнения, поэтому мы с дядей Бобом собрали рекордное кол-во дизайков под постом, я еще начал думать, что никто уже не читает такие "длинные" посты до конца. Короче, если вы хотели отреагировать как-то иначе - теперь можно. А еще лучше - подключайтесь к дискусси, тк дебаты разгорелись нехилые в комментариях...
Агентам не нужен TDD
Дядя Боб говорит, что TDD вообще-то для людей и агентам совсем не обязателен, ведь у агента дела с краткосрочной памятью обстоят куда лучше, чем у людей.
А что нужно агентам по его мнению? Юнит тест, CRAP метрика и мутационное тестирование... Кто-то считает CRAP и делает мутационные тесты? Если первое ещё иногда интересно, то второе довольно спорная техника - если практикуете расскажите.
TDD !…
Kimi K3 и ревью моделями разных семейств
Ну как вам новая Kimi K3? Медленно? Если использовать ее не как основную модель, а как еще одно мнение - вполне норм, тем более, что она действительно находит интересное в дополнение к Опусу. Сейчас как раз работаю над очень сложной задачкой по улучшению комплексного и длительного воркфлоу, он должен быть устойчивым к разным сбоям, там всякие outbox'ы, умные фолбеки и другие …
Аномалии Opus 5 и оптимальный reasoning effort
Если вы используете агентов так активно, что даже 200$ лимитов вам не хватает, ну или просто хотите получать адекватный результат быстрее (иногда в разы), то надо озаботиться выбором оптимального уровня размышления модели. Так вот, из официального анонса это неочевидно, а вот из системной карточки вполне.
И там видно, что в Opus 5 medium effort часто оказывается даже э…
Все лимиты и ресеты для Codex 200$ закончились. Рекорд - расход 2 недельных подписки за сутки (работа над RepoContextBench v2 ведется полным ходом). А Claude медленный, да еще и с лимитированным фейблом. В итоге, взял Грока за 300$ 100$ - говорят, там лимиты почти бесконечные и все очень быстро. Грок за 30$ мне понравился как по качеству, так и по скорости.
Грока я использую в качестве исполнителя внутри OpenCode (во…
Ну, это так для сравнения (DeepSWE 1.1).
Юзает ли кто-нибудь Gemini нынче? Кажется, совсем у них дела плохи. Раньше хоть дешевые мелкие модели были (мы в CodeAlive вовсю их гоняли при индексации), а сейчас вообще юзкейсы непонятны.
Я, кстати, в добавку к Codex и Claude взял еще на Grok подписку и использую в кач-ве ревьюера - действительно находит много интересного, я доволен.
А Fable использую как эксперта-консульта…
❤5👍4
Showing the 12 most recent of 18 posts we hold for @ai_driven. 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.
Stars beside a post are paid reactions — Telegram Stars, bought with money and spent on that post. They are a different unit from reactions and are never added to them, here or anywhere else on this page.
Citation-graph rank
Citation-graph rank — 17,834 of 1,151,006entries 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.
Mentions
Named by 16 registered channels — every channel on the register whose own posts have named this one, by its current username or any other username it currently holds, merged from two separately captured readings of the same fact so a namer caught by only one of them is not missed and a namer both caught is not counted twice. A username this channel has since dropped is not matched — that handle may belong to someone else now, and crediting today’s namer to yesterday’s owner would misattribute it.
Named by
Channels on the register whose posts name this channel's handle.
A mention is a weaker signal than a forward and is counted separately for that reason — naming a channel is not republishing it, and a handle in a post body is easy to place deliberately. The post counts beside each row below are distinct posts in which the handle appeared, from posts we have read on both sides — the “Named by N registered channels” figure above is a different count, of distinct NAMING CHANNELS rather than posts, and is not the sum of the rows under it.
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 12 August 2026 — this
entry's latest reading, not the date you are reading this.
“AI-Driven Development. Родион Мостовой” (@ai_driven), 5,312 subscribers as measured 12 August 2026. Telegram Register, tgregister.com/channel/ai_driven.
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.
