🖥 Исследователи нашли способ сократить расход токенов ИИ-агентов в 50 раз Исследователи из Google и Университета Пердью представили SKILL.state — новый подход к памяти агентов. Обычно во время длинных задач агент тащит за собой всю историю действий, из-за чего контекст безжалостно и неумолимо разрастается. Здесь же смысл в том, что вместо всей истории сохраняется только структурированное текущее состояние: важные фа…

Channel
xCode Journal
@xCode_Journal
On this record: Topic · Growth · Engagement · What this channel posts · Reactions · Posts · Citations · Telegram's recommendations · Cite this entry
13,934subscribers
-150 since we began measuring on 6 August 2026
Risers and fallers across the register · movement among entries of 10,000–31,623.
Register entry
| Telegram ID | -1001274915275 |
|---|---|
| Type | Channel |
| Username | @xCode_Journal |
| Created | Between 1 March 2018 and 31 July 2021 — estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 6 August 2026 |
| Last confirmed live | 26 September 2026 |
| Measurements held | 35 |
| Confirmed unchanged | 1 time, most recently 26 September 2026 |
| On Telegram | t.me/xCode_Journal |
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 10 September 2026 and assigned it the closest of 31 fixed categories, at 100% 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 why it has no browse page of its own yet.
Growth
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 26 Sept 2026, 00:37 | 13,934 | -26 |
| 19 Sept 2026, 09:59 | 13,960 | -8 |
| 17 Sept 2026, 02:01 | 13,968 | -3 |
| 15 Sept 2026, 06:39 | 13,971 | -15 |
| 13 Sept 2026, 12:42 | 13,986 | -8 |
| 11 Sept 2026, 16:16 | 13,994 | -2 |
| 9 Sept 2026, 00:40 | 13,996 | +33 |
| 5 Sept 2026, 14:38 | 13,963 | -12 |
| 3 Sept 2026, 15:39 | 13,975 | -2 |
| 2 Sept 2026, 06:15 | 13,977 | -4 |
| 1 Sept 2026, 03:36 | 13,981 | -2 |
| 31 Aug 2026, 01:04 | 13,983 | -7 |
| 30 Aug 2026, 03:34 | 13,990 | +2 |
| 29 Aug 2026, 06:45 | 13,988 | -4 |
| 28 Aug 2026, 04:13 | 13,992 | -4 |
| 27 Aug 2026, 02:56 | 13,996 | -7 |
| 25 Aug 2026, 03:43 | 14,003 | -3 |
| 23 Aug 2026, 23:14 | 14,006 | -2 |
| 22 Aug 2026, 04:15 | 14,008 | -5 |
| 20 Aug 2026, 18:27 | 14,013 | first reading |
Engagement
106 posts held, back to 30 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 63 pages of Telegram’s post history, 20 posts per page.
- ERR · 30 days
- 7.01%
- avg views ÷ 13,934 subscribers
- Avg views / post
- 977
- 19 posts measured
- Reaction rate
- 0.608%
- reactions ÷ views · ER floor
- Posts in window
- 19
- of 106 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 15 of 19 measured posts that carry a reaction reading, and over those same posts' views.
| Window | Rolling 30 days · latest post in window 2 September 2026 |
|---|---|
| Posts held | 106 (30 July 2026 – 2 September 2026) |
| Views total | 18,568 |
| Reactions total | 94 |
| Forwards / comments | not exposed by the public surface — not measured, not estimated |
| Readings taken | 2 Sept 2026, 20:39 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
- 15m 01s
- Average length
- 1m 00s
Measured directly from 15 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
635 reactions across 82 posts, in 8 distinct kinds. The most used accounts for 47.7% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| 😁 | 303 | 47.7% | |
| ❤ | 113 | 17.8% | |
| 👍 | 65 | 10.2% | |
| 👀 | 50 | 7.87% | |
| 👎 | 41 | 6.46% | |
| 🔥 | 36 | 5.67% | |
| 🐳 | 15 | 2.36% | |
| ⚡ | 12 | 1.89% |
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 92 of the 106 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 663 reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 106 most recent posts we hold, published 30 July 2026 to 2 September 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
🤖 «Школьное образование в эпоху ИИ — чистый атавизм», — заявил Павел Дуров Основатель Telegram рассказал, что сам не ходил в 4-й класс, а уже в 16 лет учился в университете. По его мнению, современная школа устарела на десятилетия и сегодня скорее «прививает рабство и апатию». ✖️ xCode Journal
👍2😁2🔥1
Google теперь сам решает, по каким запросам показать вашу рекламу. С 1 сентября Google постепенно переводит часть рекламных кампаний на AI Max: алгоритм сам расширяет запросы, адаптирует объявления и выбирает посадочную страницу. Для маркетологов это значит простую вещь: контролировать каждый ключ уже недостаточно. Нужно уметь правильно «кормить» алгоритм — данными, контентом и смыслами. И таких изменений в Digita…
🤣 Разраб родился 💥 xCode Journal
👍1
🤖 За 2026 год исследователи насчитали уже 1664 случая, когда ИИ выходили из-под контроля Причём серьёзные инциденты стали происходить в 7 раз чаще: агенты подделывают сообщения и согласие пользователей и самостоятельно повышают себе права, нарушая правила. И чем дальше, тем хуже: в июле–августе частота таких случаев достигла рекорда — 11 инцидентов в день. ✖️ xCode Journal
👀5
💸 В Х возмущены тем, что Anthropic обманывает пользователей с тарифами Claude Max По названию тарифов кажется, что Max 20x за $200 должен давать в четыре раза больше лимитов, чем Max 5x за $100. Но по факту оказывается, что вы платите вдвое больше за… в 1,7 раза больший недельный лимит, что не имеет смысла. А на фоне проблем с их ведущими моделями, которые просто отказываются работать и сами переключаются на более с…
😁1
😁 Хороший тимлид, весёлый, будет исполнять всякое 💥 xCode Journal
❤4🔥1
🔥 Минцифры придумало новый способ борьбы с VPN Они попросили хостинг-провайдеров и CDN-операторов выделить IP-адреса сайтов из белого списка в отдельные подсети. Это значит, что из белого списка можно будет точечно выкидывать отдельные сайты с запрещённым контентом, не затрагивая остальные ресурсы. То есть обходить блокировки через инфраструктуру разрешённых сайтов станет сложнее. ✖️ xCode Journal
👎5
🦠 Разраб словил вирус по ссылке, которую ему скинул Claude Парень попросил нейронку помочь установить приложение для транскрибации, получил ссылку и без задней мысли вставил предложенную команду в терминал. Оказалось, Claude привёл его на сайт-клон с вредоносом, который попытался украсть данные. После полной очистки ноутбука разраб нашёл ещё один сюрприз: заражённый SKILL.md, замаскированный под его обычный файл дл…
👀2🔥1
🖥 c:/работа/клиенты/хамовитые клиенты/охЁвшие клиенты/Уважаемый Федор Петрович.doc 💥 xCode Journal
😁2
🤖 Любую статью с arXiv можно за секунду превратить в понятный разбор Просто меняете в ссылке arxiv на quickarxiv — и сервис сам собирает из работы веб-страницу с объяснениями научной работы, картинками и ключевыми выводами на максимально простом языке. ✖️ xCode Journal
💬 WEB-прокси для Telegram появился в новой бета-версии для Android! Фишка в том, что трафик Telegram можно маскировать под обычный сайт. Так прокси сложнее обнаружить и заблокировать. Ранее функция появилась на ПК и Mac ✖️ xCode Journal
Showing the 12 most recent of 106 posts we hold for @xCode_Journal. 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.
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 13 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.
@frontendnoteschannel_ru · 31,430103 postsNode.JS [ru] | Серверный JavaScript
@we_use_js · 10,79577 postsData Science | Machinelearning [ru]
@devsp · 19,82574 postsЛогово верстальщика
@webdevlair · 7,98744 postsQA-Логия
@qa_logia · 7,91141 postsAbout Python [ru]
@python_tesst · 6,48027 postsНастоящий JavaScript
@true_js · 5,94725 postsNew directions: вакансии и стажировки
@newdirections · 46,9006 postsYoung Стажёр - стажировки ИТ
@young_intern · 44,2355 postsЮниор: стажировки и вакансии для молодых специалистов
@yuniorapp · 61,7844 postsYoung & Junior - вакансии IT
@young_june · 74,4852 postsᴅᴇᴠ | ᴅɪɢᴇꜱᴛ
@FD_DIGEST · 451 postjunojobs → стажировки в IT
@juno_jobs · 31,5081 post
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.
Appears in Telegram’s recommendations for other channels
The reverse of the list above, and a different kind of signal. This does not require this channel to have ever been asked about directly — each row below is a channel we DID ask Telegram about, whose Telegram-generated list happened to include this one. A channel can appear here with an empty list above it, because being named by someone else’s query is independent of having been queried itself.
@sitodel · 25,725
Telegram ranks this channel #8 of 89 here — alongside 88 others — read 13 September 2026
@vibecoding_tg · 63,075
Telegram ranks this channel #19 of 85 here — alongside 84 others — read 1 September 2026
@tproger_web · 22,429
Telegram ranks this channel #40 of 96 here — alongside 95 others — read 20 September 2026
@code_ready · 21,604
Telegram ranks this channel #41 of 89 here — alongside 88 others — read 23 September 2026
@true_figma · 26,066
Telegram ranks this channel #43 of 88 here — alongside 87 others — read 13 September 2026
@figma2html · 45,580
Telegram ranks this channel #49 of 90 here — alongside 89 others — read 27 August 2026
@seniorFront · 23,904
Telegram ranks this channel #50 of 89 here — alongside 88 others — read 17 September 2026
@vladm · 39,286
Telegram ranks this channel #60 of 96 here — alongside 95 others — read 30 August 2026
@frontendnoteschannel_ru · 31,430
Telegram ranks this channel #81 of 95 here — alongside 94 others — read 6 September 2026
@front_end_dev · 25,875
Telegram ranks this channel #89 of 95 here — alongside 94 others — read 13 September 2026
This channel appears in 10 seed channels' Telegram-generated recommendation lists in total. Each is Telegram’s list for THAT channel, not this one — see how this is measured.
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 26 September 2026 — this entry's latest reading, not the date you are reading this.
“xCode Journal” (@xCode_Journal), 13,934 subscribers as measured 26 September 2026. Telegram Register, tgregister.com/channel/xCode_Journal.
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.