Channel
@maestro_de_prompts
On this record: Topic · Growth · Engagement · Reactions · Posts · Polls · Citations · Cite this entry
7,151subscribers
+363 since we began measuring on 7 August 2026
Risers and fallers across the register · movement among entries of 3,162–10,000.
| Telegram ID | -1001839391783 |
|---|---|
| Type | Channel |
| Username | @maestro_de_prompts |
| Created | Between 1 October 2022 and 30 September 2023 — estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 7 August 2026 |
| Last confirmed live | 18 September 2026 |
| Measurements held | 15 |
| Confirmed unchanged | 1 time, most recently 18 September 2026 |
| On Telegram | t.me/maestro_de_prompts |
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 12 September 2026 and assigned it the closest of 31 fixed categories, at 86% 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.
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 18 Sept 2026, 20:14 | 7,151 | +49 |
| 14 Sept 2026, 11:38 | 7,102 | +41 |
| 11 Sept 2026, 01:17 | 7,061 | +44 |
| 6 Sept 2026, 05:38 | 7,017 | +19 |
| 2 Sept 2026, 05:44 | 6,998 | +17 |
| 29 Aug 2026, 18:59 | 6,981 | +24 |
| 27 Aug 2026, 04:37 | 6,957 | +24 |
| 24 Aug 2026, 11:44 | 6,933 | +32 |
| 20 Aug 2026, 15:48 | 6,901 | +39 |
| 17 Aug 2026, 16:35 | 6,862 | +29 |
| 14 Aug 2026, 00:46 | 6,833 | +18 |
| 11 Aug 2026, 01:56 | 6,815 | +20 |
| 8 Aug 2026, 12:34 | 6,795 | +7 |
| 7 Aug 2026, 18:31 | 6,788 | no change |
| 7 Aug 2026, 18:25 | 6,788 | first reading |
23 posts held, back to 1 February 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 10 pages 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 23 posts for this entry, the most recent from 18 August 2026. An engagement rate over an empty window would be a number about nothing.
822 reactions across 22 posts, in 20 distinct kinds. The most used accounts for 47.9% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| ❤ | 394 | 47.9% | |
| 👍 | 210 | 25.5% | |
| 🔥 | 100 | 12.2% | |
| 👏 | 60 | 7.30% | |
| 👌 | 10 | 1.22% | |
| 🤔 | 9 | 1.09% | |
| ✍ | 8 | 0.973% | |
| 👨💻 | 4 | 0.487% | |
| 🥰 | 4 | 0.487% | |
| ⚡ | 3 | 0.365% | |
| 👀 | 3 | 0.365% | |
| 💯 | 3 | 0.365% | |
| 🤝 | 3 | 0.365% | |
| 😱 | 2 | 0.243% | |
| 🙏 | 2 | 0.243% | |
| 🤨 | 2 | 0.243% | |
| 🤯 | 2 | 0.243% | |
| 🏆 | 1 | 0.122% | |
| 😁 | 1 | 0.122% | |
| 😢 | 1 | 0.122% |
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 22 of the 23 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 822 reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 23 most recent posts we hold, published 1 February 2026 to 18 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.
El ChatGPT gratis ya no tiene límite de mensajes de texto. Y pronto verás anuncios. Dos cambios que conviene entender. Desde esta semana, los planes gratis y Go chatean por texto sin tope (el límite sigue para subir archivos e imágenes), y el modelo nuevo, Luna, pasa a ser el de por defecto con un botón "Think" para cuando quieras que razone más. A cambio, OpenAI va a probar publicidad en los planes gratis y Go: pr…
👍12❤4👏1🤔1
ChatGPT ahora te hace exámenes y te corrige al momento. El 14 de agosto añadieron los quizzes interactivos. Le dices el tema, te pregunta, tú respondes en el propio chat y te dice qué está bien y qué no. Sin apps, sin pagar nada extra, con el ChatGPT que ya tienes. Pruébalo con algo real, no con un ejemplo. Pega esto: Estoy preparando [tu tema]. Hazme un quiz de 5 preguntas, una a una. Cuando responda, dime si es…
❤5👏4👍3
Desde el 2 de agosto, formar en IA es obligación legal en Europa. Entró en vigor el artículo 4 del AI Act, el reglamento europeo de inteligencia artificial. En cristiano: si en tu empresa o tu trabajo se usa ChatGPT, Copilot o cualquier herramienta con IA, la empresa tiene que poder demostrar que la gente que la usa entiende qué hace y cuándo no fiarse. No hace falta un curso caro ni un certificado. Basta con dejar…
👍9❤3👏1🤔1
🔗 Que ChatGPT te lea el correo cada mañana y te avise — sin instalar nada más. La semana pasada montaste tu primer empleado de IA y viste que ChatGPT ya trabaja solo durante horas. Hoy le damos algo suyo de verdad: acceso a tu bandeja. Todo dentro de la app del móvil. Nada que comprar, nada que instalar. La receta (5 min, una sola vez): 1️⃣ En ChatGPT: Ajustes → Conectores → Gmail, y conéctalo con tu cuenta de Goo…
❤13🔥10👍3😱2
🛠 Dentro de tu ChatGPT hay un programador. Y casi nadie lo usa. Ayer os conté que OpenAI mató Sora y movió todo su peso a código y empresas. Hoy os digo por qué eso te interesa a ti, aunque no hayas programado en tu vida. Se llama Codex y no es un chat. ChatGPT te explica cómo hacer algo. Codex lo hace: escribe el código, lo ejecuta, prueba si funciona y corrige sus propios errores. Es la diferencia entre un prompt…
❤30👍14👏8🔥2
🎬 ¿Ibas a pagar ChatGPT para hacer vídeos? Espera. Me lo preguntó un suscriptor por privado: «voy a pagar una IA para imágenes y vídeos, ¿cuál me recomiendas?». Lo contesto aquí porque seguro que no es el único — y porque la respuesta cambió hace poco y mucha gente no se ha enterado. Sora, el generador de vídeo de OpenAI, cerró en abril. ChatGPT ya no hace vídeo. Si pagas la suscripción esperando vídeo, tiras el di…
👍15❤7🔥5⚡1👏1💯1
Un momento para mirar quién se ha juntado aquí. En este canal hay de todo: gente con un empleo que quiere quitarse tareas de encima, freelancers y dueños de negocio buscando ingresos, algún que otro profe, gente que estudia y unos cuantos que ya trastean con código. Perfiles muy distintos. Pero cuando rascas un poco, casi todos venís por lo mismo: que la IA haga el trabajo por vosotros. Que automatice lo aburrido y…
👍18🔥6👀3❤1
📋 Ayúdame a que este canal sea justo lo que TÚ necesitas (2 min). Volví con un foco nuevo: IA práctica, agentes y automatización. Para acertar contigo, necesito saber quién eres y qué buscas. Son 6 preguntas, 2 minutos, anónimo 👇 https://docs.google.com/forms/d/e/1FAIpQLScKToMPfUjccLvTDqKKjTbi4DKI71_ht0BBx7ooZ6TZcQMM7w/viewform Gracias — leo todas las respuestas. 🙌 @maestro_de_prompts
❤11👍7👨💻4
⚙️ Monta tu primer "empleado de IA" en 5 minutos (sin programar). Automatizar no es solo para grandes empresas. Aquí tienes algo que puedes montar HOY: un resumen de tu día que te llega solo cada mañana, sin que hagas nada. Con las Tareas programadas de ChatGPT (plan Plus): Abre ChatGPT → crea una Tarea a las 7:30. Pega esto como instrucción: Cada mañana a las 7:30, prepárame el día en 30 segundos: – El tiempo de…
👍21🔥6👏3🤝2❤1🏆1
⚡️ Ayer ChatGPT dio su mayor salto en meses: ahora no responde… TRABAJA. Tres cosas cambiaron de golpe (8-9 julio). Lo importante y cómo aprovecharlo: 1️⃣ ChatGPT Work: un agente que hace el trabajo entero, solo. Esto es lo grande. Le das un objetivo («prepárame un informe de la competencia», «móntame esta hoja de cálculo», «hazme una web sencilla») y trabaja durante horas por su cuenta: investiga, usa tus apps con…
🔥19👍9❤7
🤖 Un prompt te da una respuesta. Un agente hace el trabajo por ti. Construyamos uno. La diferencia que lo cambia todo: – Prompt: preguntas, responde, se acabó. Mañana lo repites desde cero. – Agente: le das un objetivo y unas reglas UNA vez, y se queda montado trabajando. Crea tu primer agente en ChatGPT (la función «GPTs» — crearlo es gratis): ChatGPT → «Explorar GPTs» → Crear. En «Configurar», pega esto y rellen…
❤21👍6👏3🤝1
Lo que está pasando en la IA esta semana (y por qué te importa) 1️⃣ A Anthropic le «prohibieron» su mejor modelo… y volvió más fuerte. En junio EE.UU. bloqueó Claude Fable 5 por seguridad. El 1 de julio levantaron la restricción y ya está de vuelta, con un nuevo filtro de ciberseguridad. Los mejores modelos ya son casi «asunto de Estado». 2️⃣ Mañana, 9 de julio, OpenAI presenta GPT-5.6 — y empieza a llegar a los us…
👍20❤10👏6🤔1
Showing the 12 most recent of 23 posts we hold for @maestro_de_prompts. 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.
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.
¿Qué te interesa aprender en Maestro? Elige TODO lo que te interesa (puedes votar varias opciones):
The shares total 271%, 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 23 most recent posts we hold, published 1 February 2026 to 18 August 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.
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.
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 18 September 2026 — this entry's latest reading, not the date you are reading this.
“Maestro de Prompts · IA, ChatGPT y Agentes” (@maestro_de_prompts), 7,151 subscribers as measured 18 September 2026. Telegram Register, tgregister.com/channel/maestro_de_prompts.
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.