Новая функция Claude Code: теперь сессии могут общаться друг с другом. Например: > В одной сессии вы работаете над одной функцией. > В другой — над другой частью проекта. > Если одной сессии нужно что-то передать другой, можно просто попросить Claude сделать это. Claude отправит краткое резюме с важной информацией, а другая сессия продолжит работу уже с этим контекстом. Также можно задать вопрос другой сессии и п…

Channel
very vibe coding
@veryvibecoding
On this record: Growth · Engagement · What this channel posts · Reactions · Posts · Citations · Cite this entry
113subscribers
+1 since we began measuring on 6 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
Register entry
| Telegram ID | -1002414653362 |
|---|---|
| Type | Channel |
| Username | @veryvibecoding |
| Description | Канал Алексея Макрушина об экспериментах в области vibe coding и всего интересного, что есть в области AI, ML и тому подобного |
| Created | Between 1 September 2024 and 31 March 2025— estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 9 August 2026 |
| Last confirmed live | 9 August 2026 |
| Measurements held | 3 |
| On Telegram | t.me/veryvibecoding |
Growth
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 9 Aug 2026, 06:15 | 113 | no change |
| 6 Aug 2026, 23:30 | 113 | +1 |
| 6 Aug 2026, 06:20 | 112 | first reading |
Engagement
20 posts held, back to 31 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
- 29.7%
- avg views ÷ 113 subscribers
- Avg views / post
- 33.6
- 20 posts measured
- Reaction rate
- 7.32%
- reactions ÷ views · ER floor
- Posts in window
- 20
- of 20 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 1 of 20 measured posts that carry a reaction reading, and over those same posts' views.
| Window | Rolling 30 days · latest post in window 8 August 2026 |
|---|---|
| Posts held | 20 (31 July 2026 – 8 August 2026) |
| Views total | 672 |
| Reactions total | 3 |
| Forwards / comments | not exposed by the public surface — not measured, not estimated |
| Readings taken | 9 Aug 2026, 06:15 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
- Photos
- 421
- Videos
- 119
- Links
- 894
Lifetime counters from Telegram’s own channel header, read 9 August 2026 — not the date at the top of this page, which is when the subscriber count was last read. Below Telegram’s rounding threshold, so these counts are exact.
- Video runtime
- 50s
- Average length
- 25s
Measured directly from 2 videos 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
3 reactions across 1 post, in 3 distinct kinds. The most used accounts for 33.3% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| 🎉 | 1 | 33.3% | |
| 👏 | 1 | 33.3% | |
| 🔥 | 1 | 33.3% |
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 1 of the 20 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 3reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 20 most recent posts we hold, published 31 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.
Recent posts
bb - Codex-подобный оркестратор, который расширяется плагинами. И почему это делает его интересным. В awesome-листе агентных оркестраторов сейчас под сотню проектов, они решают примерно одну задачу: собрать упряжки (Claude Code, Codex, OpenCode, Pi и тд) под одним интерфейсом, будь то терминал, TUI или десктоп. bb хорош двумя вещами (помимо прочего). Первая простая: он удобный и приятно выглядит. Интерфейс практич…
Кто хотел программировать (и не только), но не знал как начать. Luna - это солидная модель. Кратно сильнее, чем топовые модели год назад. Так что, отговорок о том, почему вы еще не начали, больше нет. Зарегистрируйтесь в chatGPT (впн все-таки нужен), а дальше, если не знаете как начать - просто спросите саму модель. https://t.me/How2AI/1808
ChatGPT получил не просто новую модель, а регулятор «сколько думать». OpenAI обновила GPT‑5.6 Sol для Plus и Pro: обещают более собранные ответы и меньше фактических ошибок в задачах с датами, числами, источниками и правилами. В ChatGPT появился слайдер effort: для быстрого вопроса можно оставить минимум размышлений, для исследования, планирования или кода — поднять уровень. Параллельно бесплатный ChatGPT переводят…
Cloudflare сделала браузер, который изначально рассчитан на агентов, а не на людей. Kitesurf — новый движок для Browser Run: он работает в V8-isolates поверх Workers и ориентирован на задачи вроде извлечения HTML, скриншотов и автоматизации веба. Идея практичная: агенту не нужны вкладки, расширения и идеальная отрисовка; ему важнее дешёвая изоляция, быстрый старт и возможность масштабировать множество одноразовых се…
DeepSeek с моделью flash стала не просто лидером - ее отрыв по использованию через апи просто подавляющий - более 9 из 10 вызовов относятся к ней. Мало того, что она дешевая, так еще она и маленькая - это значит, что и обучение лучше делать на ней, внутренние ИИ - тоже. Так что, несмотря на восторги вокруг Kimi, GLM и Qwen, пока реальный лидер - DeepSeek. Ничего удивительного, что и цены на модель подрастут.. был …
Совет по вайбкодингу: попросите Codex создать интерактивную карту вашего репозитория, а затем отмечать, какие модули изменились с момента её генерации. Нажав на любой модуль, можно увидеть его вызывающие компоненты, зависимости, основные потоки выполнения, связанные тесты и подтверждающие данные из исходного кода. Он создаёт: → docs/codemap/codemap.html → docs/codemap/codemap.json → docs/codemap/codemap.lock Полны…
DeepSeek начался не с архитектуры модели. Возможно, он начался с поездки в Тибет. В 2011 году 26-летний Лян Вэньфэн отправился на старом Fiat в одиночное путешествие. Спутник улетел домой из Лхасы, а Лян продолжил путь на запад - к Гималаям и в безлюдные районы Али. Он проехал сотни километров вглубь плато, фотографируя пейзажи на Nikon D50. Ради одного удачного кадра мог ждать света половину дня. Затем он пропал …
🌟 OpenWorker: опенсорсный ИИ-коллега от Andrew Ng Andrew Ng собрал открытый проект альтернативы Cowork, который берёт рабочую задачу и возвращает готовый результат - документ, разобранный почтовый ящик, обновлённый календарь, ответ в Slack с нужными цифрами. Пользователь формулирует, что хочет получить, агент сам делит работу на шаги и обращается к файлам, терминалу и подключённым сервисам. В описании проекта их б…
⚡️ DeepSeek V4 Flash теперь можно запустить локально на одном Mac На Hugging Face появилась специальная GGUF-сборка DeepSeek-V4-Flash-0731 для компьютеров Apple Silicon со 128 ГБ объединённой памяти. Официальная модель содержит 304 млрд параметров и поддерживает контекст до 1 млн токенов. После смешанной 2- и 4-битной квантизации файл занимает 97,6 ГБ. Чувствительные слои, attention и общие эксперты сохранены в по…
Совет использовать Luna для агентской работы был ошибкой - об этом говорят и разработчики из OpenAI. Нужно подниматься до Терры.
Вышел Qwen-3.8 Max на 2.4Т параметров. Теперь это - не опенсорс. Но, может, хотя бы маленькие модели откроют. PS. Алибаба написала, что все-таки веса откроют. Заодно и метрики подоспели
Showing the 12 most recent of 20 posts we hold for @veryvibecoding. 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 — 1,014,622 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
Republishes
Channels on the register whose posts this channel has forwarded.
@vibecoding_tg · 56,5682 postsAbstractDL
@abstractDL · 18,2211 postMachinelearning
@ai_machinelearning_big_data · 286,2501 postАнализ данных (Data analysis)
@data_analysis_ml · 50,3631 postMachine learning Interview
@machinelearning_interview · 30,1111 postRefat Talks: Tech & AI
@nobilix · 11,4461 post
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 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.
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 9 August 2026 — this entry's latest reading, not the date you are reading this.
“very vibe coding” (@veryvibecoding), 113 subscribers as measured 9 August 2026. Telegram Register, tgregister.com/channel/veryvibecoding.
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.