Telegram RegisterThe public register of Telegram

Channel

Agent Code

@vibecodevd

On this record: Growth · Engagement · What this channel posts · Reactions · Posts · Citations · Cite this entry

30subscribers

-1 since we began measuring on 7 August 2026

Risers and fallers across the register · movement among entries of Under 1,000.

Register entry

Telegram ID-1003802097987
TypeChannel
Username@vibecodevd
CreatedBetween 1 February 2026 and 11 March 2026— estimated from Telegram’s id allocation, not measured. How this range is calculated.
First recorded11 August 2026
Last confirmed live15 August 2026
Measurements held3
Confirmed unchanged1 time, most recently 15 August 2026
On Telegramt.me/vibecodevd

Growth

303130.57 August 2026 — 31 subscribers11 August 2026 — 31 subscribers15 August 2026 — 30 subscribers7 August 202615 August 2026
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 30–31 and does not start at zero.
Measurement log — every subscribers count we have recorded
Measured (UTC)SubscribersChange
15 Aug 2026, 03:2330-1
11 Aug 2026, 03:0131no change
7 Aug 2026, 18:5631first reading

Engagement

20 posts held, back to 11 March 2026the 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.

Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 20 posts for this entry, the most recent from 13 July 2026. An engagement rate over an empty window would be a number about nothing.

What this channel posts

Video runtime
1m 06s
Average length
33s

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

15 reactions across 10 posts, in 4 distinct kinds. The most used accounts for 53.3% of them.

Every reaction kind recorded on the sample, most used first
ReactionCountShareShare, drawn
🔥853.3%
👍533.3%
16.67%
🙏16.67%

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 10 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 15reactions 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 11 March 2026 to 13 July 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

13 Jul 2026, 13:51 UTC37 viewsread 11 August 2026

Что есть и как нужно писать Скиллы. https://agentskills.io/home

Signed Vladimir

19 May 2026, 09:17 UTCviews —

Agent Code pinned «Привет, простыми словами, что происходит внутри LLM модели. Мы не будем лезть в обучение и веса, а разберем только базовую механику: как из токенов и векторов получается логичный ответ. Перед прочтением рекомендую посмотреть, что такое "вектор" и "матрица"…»

19 May 2026, 08:05 UTC166 views3 reactionsread 11 August 2026

Связываем Qwen Agent + Telegram за 10 минут Можем управлять агентом через тelegram. Пример для моей машины: 1. Создавать, удалять файлы. Дать команду написать сайт и т.п. 2. Запускать автотесты и получать отчеты через тг. 3. Выполнять команды агента из чата. Посмотреть расход токенов через "/context". qwen channel start статья на vc.ru

🔥3

Signed Vladimir

16 May 2026, 07:46 UTC152 views1 reactionsread 11 August 2026
Photo

АИ модель 2026 года не использует текущую дату? 1. Изучаем работу дат. В том числе и Claude Code. Исправляем ответы модели о текущей дате. 2. Понимаем, что модель сама по себе stateless. Не хранит состояние и не ходит в интернет как пример статья на vc.ru

👍1

Signed Vladimir

2 May 2026, 18:24 UTC159 views2 reactionsread 11 August 2026
Photo

Агрегатор информации Google NotebookLM. Перенес для удобства доступа на vc.ru

👍1🔥1

Signed Vladimir

2 May 2026, 17:44 UTC131 viewsread 11 August 2026
Video

Еще один вариант визуализации векторного представления

Signed Vladimir

27 Apr 2026, 15:24 UTC141 views1 reactionsread 11 August 2026
Photo

На картинке фиолетовым показаны семантически близкие слова к слову "замок" в векторном пространстве.

🔥1

Signed Vladimir

27 Apr 2026, 14:46 UTC127 views1 reactionsread 11 August 2026

Привет, простыми словами, что происходит внутри LLM модели. Мы не будем лезть в обучение и веса, а разберем только базовую механику: как из токенов и векторов получается логичный ответ. Перед прочтением рекомендую посмотреть, что такое "вектор" и "матрица" из школьного курса математики. Ссылка на vc.ru Ссылка на статью в Linked in

👍1

Signed Vladimir

25 Apr 2026, 17:01 UTCviews —

Agent Code pinned «На что обратить внимание при тестировании АИ-агента? Подсобрал знания за несколько месяцев. Список будет корректироваться. 1. Запуск - терминал, IDE плагин, десктоп оболочка 2. Создание простейшей задачи - например, разработать Калькулятор без требований…»

25 Apr 2026, 16:17 UTC153 viewsread 11 August 2026
Photo

Запускаем модель локально для IDE. Сервер для модели - Ollama IDE - IntelliJ IDEA Расширение для IDE - Continue. 1. Устанавливаем Ollama. 2. Открываем интерфейс. В окне чата в правом нижнем углу список моделей. Указываем какую хотим скачать. На текущий день qwen3.6 показывает хорошие результаты. Альтернативный вариант через консоль: ollama serve ollama pull qwen3.6:27b 3. Для России. Скачиваем плагин Continue. h

Signed Vladimir

25 Apr 2026, 15:35 UTC84 viewsread 11 August 2026

Бесплатные АИ-агенты. Часть 2. И так Qwen Code по умолчанию стал платным. Какие есть варианты: 1. Запускаем модель на локальном сервере (Ollama, LM Studio, vLLM, AnythingLLM). Вызываем ее через терминальный агент или саму IDE (см. пост), также IDE plugin (Continue и прочие). 2. Открываем терминальный агент. Цепляем к нему модель из облака (OpenRouter, NVIDIA и тд), указывая API key.

Signed Vladimir

25 Apr 2026, 13:17 UTC132 views1 reactionsread 11 August 2026

На что обратить внимание при тестировании АИ-агента? Подсобрал знания за несколько месяцев. Список будет корректироваться. 1. Запуск - терминал, IDE плагин, десктоп оболочка 2. Создание простейшей задачи - например, разработать Калькулятор без требований 3. Создание с требованиями (фронт, бэк и тд) - разработать Калькулятор 4. Круд операции с файлами и папками. 5. Промпт - проверка функциональности по документации.

1

Signed Vladimir

Showing the 12 most recent of 20 posts we hold for @vibecodevd. 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.

Mentions

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 15 August 2026 — this entry's latest reading, not the date you are reading this.

“Agent Code” (@vibecodevd), 30 subscribers as measured 15 August 2026. Telegram Register, tgregister.com/channel/vibecodevd.

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.