Telegram RegisterThe public register of Telegram
Telegram profile photo for codokot

Channel

codokot

@codokot

On this record: Topic · Growth · Engagement · Reactions · Posts · Polls · Cite this entry

635subscribers

-19 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-1001830001664
TypeChannel
Username@codokot
CreatedBetween 1 October 2022 and 30 September 2023 — estimated from Telegram’s id allocation, not measured. How this range is calculated.
First recorded8 August 2026
Last confirmed live14 November 2026
Measurements held11
Confirmed unchanged2 times, most recently 14 November 2026
On Telegramt.me/codokot

Topic

Technology — a classification, not a measurement. An on-box language model (Qwen3.6-35B-A3B-FP8, prompt version 1) read this channel’s own recent posts on 20 September 2026 and assigned it the closest of 31 fixed categories, at 96% confidence. This is a model’s judgement about what the channel is likely to be about, not a fact this register measured the way a subscriber count or a view count is measured — it can be revised on a later pass, and it carries no weight anywhere else on this page. How this classification works, and the other topics.

Growth

635654644.57 August 2026 — 654 subscribers8 August 2026 — 654 subscribers24 August 2026 — 653 subscribers30 August 2026 — 652 subscribers8 September 2026 — 650 subscribers16 September 2026 — 648 subscribers30 September 2026 — 643 subscribers9 October 2026 — 644 subscribers23 October 2026 — 642 subscribers30 October 2026 — 637 subscribers6 November 2026 — 635 subscribers7 August 20266 November 2026
11 measurements spanning 91 days, net -19. 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 632–657 and does not start at zero.
Measurement log — every subscribers count we have recorded
Measured (UTC)SubscribersChange
6 Nov 2026, 08:56635-2
30 Oct 2026, 07:04637-5
23 Oct 2026, 17:05642-2
9 Oct 2026, 20:19644+1
30 Sept 2026, 06:38643-5
16 Sept 2026, 19:56648-2
8 Sept 2026, 17:36650-2
30 Aug 2026, 12:44652-1
24 Aug 2026, 10:04653-1
8 Aug 2026, 02:46654no change
7 Aug 2026, 18:29654first reading

Engagement

19 posts held, back to 31 January 2024 — 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 19 posts for this entry, the most recent from 2 April 2026. An engagement rate over an empty window would be a number about nothing.

Reaction mix

181 reactions across 17 posts, in 13 distinct kinds. The most used accounts for 65.2% of them.

Every reaction kind recorded on the sample, most used first
ReactionCountShareShare, drawn
👍11865.2%
🔥2513.8%
❤126.63%
🤬126.63%
✍21.10%
🤔21.10%
🤡21.10%
🤮21.10%
🤯21.10%
👎10.552%
💩10.552%
🥰10.552%
🫡10.552%

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 19 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 181 reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.

Measured over the 19 most recent posts we hold, published 31 January 2024 to 2 April 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

2 Apr 2026, 06:05 UTC581 views9 reactionsread 8 August 2026

В гитхаб слили исходный код Claude Code Менее суток назад был слит самый популярный и продвинутый платный инструмент кодинга от Антропик, который был доступен только по подписке и конечно с ограничениями для некоторых стран. В итоге его слитые файлы были полностью переписаны с сохранением функций исходного продукта. Этот репозиторий уже был форкнут 100K раз (менее чем за сутки). Такого в истории еще не было, до этог…

👍4🤡2🤮2💩1

20 Feb 2026, 19:32 UTC568 views4 reactionsread 8 August 2026

Сравнение GLM-5 Kimi K2.5 Qwen3.5 397B‑A17B MiniMax‑M2.5 vs Cloude Opus 4.5 GLM-5 (Z.ai) GLM‑5 — open-weights модель для кодинга и long-horizon agentic задач. По model card: MoE с 744B total / 40B active. Контекст: max_position_embeddings = 202752 (≈200K). Архитектура/обучение: DSA (DeepSeek Sparse Attention) + асинхронный RL‑посттрейн через slime. Для пользователей: “thinking/tool-use” сценарии, готовые рецепты деп…

🔥4

9 Feb 2026, 11:25 UTC637 views3 reactionsread 8 August 2026

Кто реально пишет код лучше: популярные ИИ лоб в лоб В новом видео я устроил честный батл четырёх моделей: дал им одинаковые задачи (лендинги, мини‑игра, дашборд и web‑приложение) и собрал лидерборд по результатам Kimi K2.5 (Moonshot AI) Kimi K2.5 — открытая native multimodal (текст+изображения) модель, ориентированная на агентные сценарии и режимы *instant/thinking*. По model card это MoE с 1T total / 32B activat…

🔥3

2 Feb 2026, 05:47 UTC681 viewsread 8 August 2026
Poll

Какие из этих инструментов Вы уже используете на регулярной основе?

  1. Opencode7%
  2. Agent Zero2%
  3. OpenClaw11%
  4. Пока не использовал, но обязательно попробую46%
  5. Есть получше варианты9%
  6. Мне они без надобности33%

The shares total 108%, above 100: this poll accepts more than one answer per voter. No per-option vote count is published, so the number of voters who chose each option is not derivable and is not shown.

1 Feb 2026, 17:22 UTC724 views5 reactionsread 8 August 2026

Агенты действуют: 1️⃣ Вариант 1: «Умный помощник» Пишешь задачу — он предлагает план/патч/команды. • Пример: OpenCode в терминале. 2️⃣ Вариант 2: «Агент в контейнере/песочнице» Умеет запускать код, искать инфу и писать инструменты под себя. • Пример: Agent Zero. 3️⃣ Вариант 3: «Много агентов + среда общения» Взаимодействуют между собой и живут как сообщество. • Кейс: Moltbook. ⚡️ Магия и страх: как только агент «чит…

🔥5

17 May 2024, 19:34 UTC≈3,340 views24 reactionsread 8 August 2026

Command-r. Вызов функций. Веб поиск. #commandr Command R - это большая языковая модель, оптимизированная для диалогового взаимодействия и задач с длительным контекстом. Она создана с прицелом на корпоративный сегмент, но при этом ее использование может быть локальным и бесплатным. Command R может похвастаться высокой точностью поиска, расширенной генерацией (RAG) и задачами использования инструментов, низкой задерж…

👍21❤3

29 Mar 2024, 17:49 UTC≈2,910 views21 reactionsread 8 August 2026

ANYTHINGLLM #anythingllm ссылка на видео: https://youtu.be/jslYFbhmwCM ссылка на проект: https://useanything.com Установка скачайте и запустите пользуясь видеоинструкцией. Список ембендинг моделей способных работать с русским языком https://github.com/avidale/encodechka Запросить бесплатный API ключ для супербыстрой mixtral8x можно здесь https://groq.com

👍13❤4🔥4

3 Mar 2024, 16:39 UTC≈2,740 views16 reactionsread 8 August 2026

STABLE DIFFUSION+OLLAMA #stablediffusionollama ссылка на видео: https://youtu.be/rWnLYPyZjQI ссылка на проект: https://github.com/ollama/ollama Как запустить SD в open webUI 1. Запустить интерфейс open webUI, и запустить его в браузере - localhost:8080 2. Запустить stable diffusion с флагами --api --listen или записать их в файл как COMMANDLINE_ARGS="--api --listen" 3. Перейти в браузер, запустить localhost:786…

👍10❤3🔥3

1 Mar 2024, 07:53 UTC≈2,020 views11 reactionsread 8 August 2026

У кого проблемы со свободным местом для ollama на диске С - нужно задать переменную окружения OLLAMA_MODELS=путь\до\папки. Должно сработать и для другого диска. Туда будут сохранены все загруженные модели, которые и выедают место

👍8❤1🔥1🫡1

27 Feb 2024, 07:17 UTC≈2,050 views20 reactionsread 8 August 2026

Блокируют учётку ютуб😕 Написал в поддержку. Появился доступ без объяснения причин 🙄

🤬12👍4🤔2🤯2

25 Feb 2024, 15:48 UTC≈2,190 views25 reactionsread 8 August 2026

OLLAMA #ollama ссылка на видео: https://youtu.be/J2pWl4UeSa4 ссылка на проект: https://github.com/ollama/ollama Установка одной командой для виндовс: https://ollama.com/download/OllamaSetup.exe одной командой для линукс: curl -fsSL https://ollama.com/install.sh | sh установка веб интерфейса open-webui: источник https://github.com/open-webui/open-webui установить c помощью докер: docker run -d -p 3000:8080 …

👍19🔥4👎1🥰1

19 Feb 2024, 16:49 UTC≈1,590 views8 reactionsread 8 August 2026

OPEN INTERPRETER #openinterpreter ссылка на видео: https://youtu.be/ld0DtwFIO2Q ссылка на проект: https://github.com/KillianLucas/open-interpreter/ Установка одной командой для виндовс: curl -o oi-windows-installer.ps1 https://raw.githubusercontent.com/KillianLucas/open-interpreter/main/installers/oi-windows-installer.ps1 || bitsadmin /transfer "DownloadScript" https://raw.githubusercontent.com/KillianLucas/open…

👍7🔥1

Showing the 12 most recent of 19 posts we hold for @codokot. 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.

Polls

The poll we hold for this entry, as Telegram rendered it when we read the post. A poll’s figures keep moving after that, so each one is dated.

2 Feb 2026, 05:47 UTCAnonymous Poll46 voters

Какие из этих инструментов Вы уже используете на регулярной основе?

  1. Opencode7%
  2. Agent Zero2%
  3. OpenClaw11%
  4. Пока не использовал, но обязательно попробую46%
  5. Есть получше варианты9%
  6. Мне они без надобности33%

The shares total 108%, above 100: this poll accepts more than one answer per voter. No per-option vote count is published, so the number of voters who chose each option is not derivable and is not shown.

Percentages only — there are no per-option vote counts here, because Telegram publishes none. The public post preview gives each option’s share and a single voter total, and nothing else. Multiplying one by the other would produce a per-option tally that looks measured and is not: the shares are rounded to whole numbers before we ever see them. We print what was published and leave the column that does not exist empty.

The shares need not add up to 100. Rounding alone puts many polls at 99 or 101. A poll that allows more than one answer per voter runs well past 100 by design, and several here do. The bars are drawn against a fixed 100% track at each option’s own percentage rather than normalised to the total, so a poll that exceeds it shows that it does instead of being quietly rescaled.

Read from the 19 most recent posts we hold, published 31 January 2024 to 2 April 2026. Telegram labels each poll by kind — an anonymous poll, a quiz, a closed set of final results — and that label is reproduced rather than paraphrased.

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 6 November 2026 — this entry's latest reading, not the date you are reading this.

“codokot” (@codokot), 635 subscribers as measured 6 November 2026. Telegram Register, tgregister.com/channel/codokot.

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.