Telegram RegisterThe public register of Telegram
Telegram profile photo for AI大模型•系统提示词•AI应用体验馆

Channel

AI大模型•系统提示词•AI应用体验馆

@AGICameBy

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

955subscribers

+70 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-1002048074342
TypeChannel
Username@AGICameBy
CreatedBetween 1 November 2023 and 31 May 2024 — estimated from Telegram’s id allocation, not measured. How this range is calculated.
First recorded8 August 2026
Last confirmed live20 October 2026
Measurements held10
Confirmed unchanged1 time, most recently 20 October 2026
On Telegramt.me/AGICameBy

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 19 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

8859559207 August 2026 — 885 subscribers8 August 2026 — 885 subscribers8 August 2026 — 887 subscribers22 August 2026 — 894 subscribers29 August 2026 — 910 subscribers5 September 2026 — 913 subscribers13 September 2026 — 923 subscribers1 October 2026 — 934 subscribers12 October 2026 — 943 subscribers20 October 2026 — 955 subscribers7 August 202620 October 2026
10 measurements spanning 74 days, net +70. 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 875–966 and does not start at zero.
Measurement log — every subscribers count we have recorded
Measured (UTC)SubscribersChange
20 Oct 2026, 11:34955+12
12 Oct 2026, 16:20943+9
1 Oct 2026, 13:01934+11
13 Sept 2026, 00:17923+10
5 Sept 2026, 10:20913+3
29 Aug 2026, 11:48910+16
22 Aug 2026, 11:04894+7
8 Aug 2026, 11:51887+2
8 Aug 2026, 01:05885no change
7 Aug 2026, 18:20885first reading

Engagement

20 posts held, back to 4 August 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 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 20 posts for this entry, the most recent from 8 August 2026. An engagement rate over an empty window would be a number about nothing.

What this channel posts

Video runtime
55s
Average length
55s

Measured directly from 1 video 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.

Recent posts

8 Aug 2026, 00:05 UTC2 viewsread 8 August 2026

这篇文章教你如何用 Claude 实现全方位生活自动化(内含完整系统):

7 Aug 2026, 23:04 UTC3 viewsread 8 August 2026

Fable 5 的发布是 AI 行业的正式转折点。 此后发布的每一个模型都将受到严格监管。 记住我今天说的话。

7 Aug 2026, 19:03 UTC3 viewsread 8 August 2026

Claude 是一个极其强大的金融工具。 用对方法,你的个人资产将大幅增长。 我刚刚泄露了最强大的 Claude 个人理财提示词(prompts)。 8 个 Claude 财富积累提示词:

7 Aug 2026, 17:04 UTC3 viewsread 8 August 2026
Photo

我觉得大家还没意识到 Codex 作为一款产品有多么优秀。 不到 2 周的时间,用户量从 600 万增长到 1000 万。太疯狂了。 原推链接

7 Aug 2026, 17:04 UTC3 viewsread 8 August 2026
Photo

Loop engineering 已死。我们正在进入 graph engineering 时代。 在这篇文章中:解析 graph engineering、真实案例,以及如何立即部署。 比你想象的要简单得多: 原推链接

7 Aug 2026, 04:02 UTC19 viewsread 8 August 2026

取消你今晚的计划。 你需要: • 测试 Prime 的 AI agent • 部署 Luna Max (subagent) • 测试 Kimi K3 • 设置 Hermes agent • 学习 graph engineering • 学习 loop engineering • 使用 Fable 5 运行 loops • 创建至少 3 个 Claude skills • 测试 Gemini Spark 要做的事情太多了。

7 Aug 2026, 00:07 UTC24 viewsread 8 August 2026
Photo

只需将此提示词发送给 Claude Code,它将引导你完成部署首个图表的精确步骤。 比 loop engineering 好 10 倍。 你会想要把这个提示词保存在某个地方: 原推链接

6 Aug 2026, 22:06 UTC19 viewsread 8 August 2026
Photo

强烈推荐大家花约5分钟时间完整阅读 Hermes agents 的官方文档。 包含大量免费的 alpha 信息。 涵盖技能、技巧、实用指南等内容。 你甚至可以让你的 agent 抓取整个网页,并根据你的工作模式进行实用的落地应用。 → 原推链接

6 Aug 2026, 15:07 UTC22 viewsread 8 August 2026
Photo

Prime Intellect 的新 AI Agent 在 ARC AGI 测试中得分**超过**人类水平。 95.3 分,远高于人类平均水平。 AGI 时代已至? 原推链接

6 Aug 2026, 10:08 UTC21 viewsread 8 August 2026
Photo

到底什么是 Graph,今天该如何部署一个? 这篇文章教你掌握关于图工程(graph engineering)所需的一切知识(像五岁小孩一样解释): 原推链接

6 Aug 2026, 03:08 UTC18 viewsread 8 August 2026
Photo

GPT-5.6 Luna Max 是目前市场上性价比最高的模型。 目前最佳操作方案是使用 GPT-5.6 Sol 作为协调器,并利用 Luna Max 启动子代理(subagents)。 以下 Prompt 正是为此设计,可降低 50% 或以上的 token 成本: 原推链接

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

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 20 October 2026 — this entry's latest reading, not the date you are reading this.

“AI大模型•系统提示词•AI应用体验馆” (@AGICameBy), 955 subscribers as measured 20 October 2026. Telegram Register, tgregister.com/channel/AGICameBy.

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.