Channel
@kravcov_ai
On this record: Growth · Engagement · Reactions · Posts · Citations · Cite this entry
194subscribers
+13 since we began measuring on 6 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
| Telegram ID | -1003402336602 |
|---|---|
| Type | Channel |
| Username | @kravcov_ai |
| Created | Between 1 November 2025 and 31 March 2026 — estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 7 August 2026 |
| Last confirmed live | 19 September 2026 |
| Measurements held | 6 |
| Confirmed unchanged | 1 time, most recently 19 September 2026 |
| On Telegram | t.me/kravcov_ai |
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 19 Sept 2026, 05:37 | 194 | +3 |
| 10 Sept 2026, 16:15 | 191 | +2 |
| 2 Sept 2026, 13:48 | 189 | +4 |
| 19 Aug 2026, 18:13 | 185 | +4 |
| 7 Aug 2026, 08:17 | 181 | no change |
| 6 Aug 2026, 04:18 | 181 | first reading |
18 posts held, back to 21 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 page of Telegram’s post history, 20 posts per page.
Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 18 posts for this entry, the most recent from 4 August 2026. An engagement rate over an empty window would be a number about nothing.
22 reactions across 11 posts, in 8 distinct kinds. The most used accounts for 31.8% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| 😁 | 7 | 31.8% | |
| 👍 | 5 | 22.7% | |
| ❤ | 3 | 13.6% | |
| 👏 | 2 | 9.09% | |
| 😱 | 2 | 9.09% | |
| 👀 | 1 | 4.55% | |
| 🔥 | 1 | 4.55% | |
| 🤡 | 1 | 4.55% |
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 11 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 22 reactions 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 21 July 2026 to 4 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.
Обновил 🛠 sdd-power до версии v3 Скилл для Claude Code, который ведет долгую разработку по документации: план, ворклог, таймлайн и уроки живут в docs/sdd-power/ и обновляются синхронно с кодом. Что нового: ⚙️ Один скрипт вместо прозы Раньше скилл описывал инфраструктуру словами - и агент «выполнял» шаг, рассказывая о нем в ответе. Теперь sdd.sh init разворачивает все сам, а первый ответ сессии обязан содержать выв…
👍1
Сделал небольшую надстройку над AI чатами, суть в том, что если вы случайно закрыли/дропнули страницу с чатом, введенный текст будет сохранен как черновик в следующей сессии. Будет полезно?
❤2
Первый ответ AI полезно рассматривать как рабочую версию, а не как окончательную истину. Поэтому после его получения стоит выполнить отдельную проверку. Причина не в том, что искусственный интеллект «не видит своих ошибок», а в особенностях работы больших языковых моделей. Они последовательно генерируют текст, прогнозируя наиболее вероятный следующий токен на основе контекста и данных, на которых были обучены. При эт…
👍1
С 1 сентября 2027 года ИИ-модель без записи в реестре может остановить систему в ГИС или на объекте КИИ. Это норма из разбора РБК Компании по законопроекту «Об основах государственного регулирования сфер применения технологий искусственного интеллекта в РФ». По этой версии, реестр доверенных моделей станет обязательным пропуском для ИИ в государственных информационных системах и на объектах критической информационно…
❤1👀1
Боль!
😐 JetBrains продолжают развеивать мифы о популярных скиллах для coding-агентов Сначала они разобрали Caveman: обещанные 65% экономии токенов превратились в 8.5%, но без экономии $ и изменений в качестве кода. Потом под удар попал rtk, который сжимает вывод команд вроде git status и pytest. Вместо обещанных 60–90% экономии он не сэкономил ничего: на low reasoning задачи стали на 7.6% дороже, на high разница исчезла.…
👍1
В CLAUDE DESIGN шаблонов подвезли
👍1
Пост - знакомство 🤝 Привет! Меня зовут Кравцов Виталий. Больше 18 лет в IT, начинал с SEO. Был совладельцем агентства интернет-маркетинга: клиенты федерального уровня, команда до 70 человек. Часть собственных проектов запустил и успешно продал. Год, плотно в AI - свои продукты и консалтинг: от «с чего начать» до интеграций и разработки. Сейчас на стыке AI, SEO и Product: маркетплейсы и агрегаторы в TravelTech и F…
👏2🔥1
Страшные истории на ночь!
😱2
Пользуюсь сам, делюсь с вами! Сделал Skill SDD Power: Скилл для Claude Code: дисциплина длительной разработки по существующей проектной документации - с персистентным трекингом состояния и критической проверкой самой документации. Он нужен там, где работа не укладывается в одну сессию: агент возвращается к проекту через неделю с пустым контекстом и должен за минуту понять, что сделано, что осталось и почему когда-т…
Photo, posted without a caption
😁3
Учимся искать AI артефакты на сгенерированных картинках @Kravcov_AI
😁4🤡1
Showing the 12 most recent of 18 posts we hold for @kravcov_ai. 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.
Republished by
Channels on the register that have forwarded this channel's posts into their own feed.
Republishes
Channels on the register whose posts this channel has forwarded.
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.
Named by 1 registered channel — 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.
Names
Channels on the register whose handles appear in this channel's posts.
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.
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 19 September 2026 — this entry's latest reading, not the date you are reading this.
“Kravcov AI - ИИ в работе, бизнесе и жизни” (@kravcov_ai), 194 subscribers as measured 19 September 2026. Telegram Register, tgregister.com/channel/kravcov_ai.
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.