Channel
@redrecsys
On this record: Growth · Engagement · Reactions · Stars · Posts · Citations · Cite this entry
1,206subscribers
+20 since we began measuring on 6 August 2026
Risers and fallers across the register · movement among entries of 1,000–3,162.
| Telegram ID | -1002852737703 |
|---|---|
| Type | Channel |
| Username | @redrecsys |
| Created | Between 1 June 2025 and 30 September 2025— estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 6 August 2026 |
| Last confirmed live | 12 August 2026 |
| Measurements held | 4 |
| Confirmed unchanged | 1 time, most recently 12 August 2026 |
| On Telegram | t.me/redrecsys |
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 12 Aug 2026, 20:56 | 1,206 | +17 |
| 10 Aug 2026, 00:41 | 1,189 | +2 |
| 7 Aug 2026, 03:41 | 1,187 | +1 |
| 6 Aug 2026, 18:17 | 1,186 | first reading |
18 posts held, back to 14 December 2025 — 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.
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 26 June 2026. An engagement rate over an empty window would be a number about nothing.
692 reactions across 17 posts, in 16 distinct kinds. The most used accounts for 41.9% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| ❤ | 290 | 41.9% | |
| 🔥 | 265 | 38.3% | |
| 👍 | 79 | 11.4% | |
| 🎄 | 17 | 2.46% | |
| 👏 | 11 | 1.59% | |
| ⚡ | 8 | 1.16% | |
| 🌚 | 4 | 0.578% | |
| ❤🔥 | 3 | 0.434% | |
| 🐳 | 3 | 0.434% | |
| 😁 | 3 | 0.434% | |
| 🤯 | 2 | 0.289% | |
| 🦄 | 2 | 0.289% | |
| 🫡 | 2 | 0.289% | |
| 🙊 | 1 | 0.145% | |
| 🤡 | 1 | 0.145% | |
| 🤮 | 1 | 0.145% |
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 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 692reactions 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 14 December 2025 to 26 June 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.
A paid reaction is a reader spending Telegram Stars — bought with money — on a post by @redrecsys. Telegram publishes the count on the public post preview alongside ordinary reactions, and this register reads it there. It is the only figure on this site that measures money moving rather than attention.
Stars are not reactions, and the two are never added. They are rendered in the same strip on Telegram and counted in the same shape, but one is a tap and the other is a purchase. The reaction totals and the engagement rate elsewhere on this page exclude every figure in this section, and no rate here is computed against a reaction count.
This is not revenue, and we publish no currency figure. What a Star costs a reader and what it pays a channel are different numbers, Telegram takes a share we cannot observe, and the terms have changed. Converting a Star count into money would be an estimate dressed as a measurement, so the count is where we stop.
Counted over the 18 most recent posts we hold for this entry, published 14 December 2025 to 26 June 2026. Star counts above 1,000 reach us in Telegram’s short form and carry the same three-significant-figure rounding as everything else on this page.
Хардовые будни как обычно надо компенсировать фоточками в канале, так что ловите) Они тут прилетели с мероприятий в июне, и есть кадры сразу с несколькими очень крутыми людьми. Саша Плошкин - лид команды архитектур с ранним связыванием, с которым мы оба заводим новые технологии для рекламного домена. И Аня Липкина - лид команды разработки рекомендательных сервисов, с ней мы вместе (как и большая часть службы) работа…
❤18🔥8❤🔥3
Препринт Gryphon) https://arxiv.org/abs/2606.08604 Ключевое: объединили архитектурно генеративный ретривал на Semantic IDs с ранжированием и задеплоили с успешным А/Б. Если судить по препринтам, именно в таком сочетании - первые в мире) Тут конечно нужна очень важная оговорка: "To the best of our knowledge, ...". Я вполне могла за последний месяц что-то пропустить в экспах-докладах-статьях. Делитесь в комментах, …
🔥35❤14👏6🐳1
Вопросы по Грифону. Часть I. "Chain-of-Recommendation" Было много вопросов к докладу, которые мне задали лично или в tg. Понемногу их раскрою, потому что в 25 минут рассказа не успела вместить всё, что на самом деле хотела бы рассказать. 💬 Скорит ли ранжирующий модуль только айтемы внутри коллизии? (Короткий ответ: Нет, это полноценный скоринг всей выдачи GR) Beam search выдаёт нам пул Semantic IDs (например 1000)…
🔥12👍5❤1🐳1
Делюсь презентацией доклада про Грифон
🔥23
Еду сейчас домой с датафеста. Спасибо, что пришли, крутой день) Было очень много вопросов в чате и в кулуарах, я попозже доберусь ответить в канале на ключевые
❤33👍7🔥3🐳1
В работе сейчас насыщенно, и в канале пишу меньше хардовых постов. Появится передышка в ресёрче - исправлюсь) Зато успела зайти в гости к N айтишниц и рассказать немного о своём пути. Жизнь - бывает такая разная
🔥24❤13🤡1
Дата фест в этом году не стал делать отдельную RecSys секцию, так что доклады по теме можно поискать в разные дни и в разных местах. Я свой буду рассказывать в секции "Practical ML". Программа тут Моя тема: "Гибридная генеративно-ранжирующая модель на базе Semantic IDs в рекомендациях Яндекс Музыки". В этой же секции будут доклады о том, как в Яндексе трансформируют Argus - от Саши Плошкина и от Жоры Смирнова. Я не…
🔥21
Накопился целый список мини-историй, которым хочу поделиться. Канал Ильдара Сафило. Ильдар сейчас работает Engineering Manager в FAANG в Лондоне, а познакомились мы, когда он собеседовал меня в МТС в 2022. В работе с Ильдаром (и Эмилем) как менторами я поняла, что теперь всегда буду искать в руководителе 3 супер-важных качества - экспертизу, увлечение своим делом и неподдельную человеческую открытость. Беспроигрышно…
👍15❤11
Сегодня в Калининграде на одном из эвентов Яндекса. На похожем мероприятии я была почти год назад - в этом же городе, в этом же отеле, ровно у этого озера. Где-то здесь и прижилась мысль, что может всё же стоит пойти поработать с этими ребятами) С тех пор это был очень насыщенный путь. Сейчас я работаю над проектами, которые требуют абсолютной вовлеченности (а иначе неинтересно!). Узнаю тонну нового. И проживаю усп…
❤55👍11🔥6👏1
Читала сегодня в ИТМО лекцию по Semantic IDs и Generative Retrieval в рамках курса по продвинутым рекомендательным системам. Первый опыт, когда материал для лекции я собирала с нуля - на основе большого количества статей по теме. А сами статьи перед этим много и подробно разбирали внутри команды. Было здорово разложить наконец всё по полочкам) Материалом делюсь
❤49🔥21😁1
Я просто не могу это не репостнуть. Мама как-то спрашивала меня, как шутят люди моей профессии
Шикарная штука из Твиттера, оказывается Опус может генерировать простенькие видосы с текстом напрямую через moviepy и ffmpeg. Всё воспроизвелось, вот мой видос. Оригинальный промпт: "can you use whatever resources you like, and python, to generate a short 'youtube poop' video and render it using ffmpeg ? can you put more of a personal spin on it? it should express what it's like to be a LLM"
🌚4❤2😁2🤯1
Showing the 12 most recent of 18 posts we hold for @redrecsys. 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.
Stars beside a post are paid reactions — Telegram Stars, bought with money and spent on that post. They are a different unit from reactions and are never added to them, here or anywhere else on this page.
Citation-graph rank — 5,180 of 1,169,250entries 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.
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 7 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.
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 12 August 2026 — this entry's latest reading, not the date you are reading this.
“Red RecSys” (@redrecsys), 1,206 subscribers as measured 12 August 2026. Telegram Register, tgregister.com/channel/redrecsys.
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.