日志工作流真是目前最好的 Agents 协同工作方式,尤其借助大纲软件。大纲纵深就是 Subagents 纵深,大纲并列就是多 Agents Runtime 并发,Block 引用日志都可追本溯源、亦可蒸馏回归,无情分发,无情飞轮。真正的建造游戏内核。#mood
👍12❤1
Signed 志筑仁美

Channel
@isaiahsystem
On this record: Growth · Engagement · What this channel posts · Reactions · Posts · Posts edited after publishing · Citations · Cite this entry
13,545subscribers
-30 since we began measuring on 6 August 2026
Risers and fallers across the register · movement among entries of 10,000–31,623.
| Telegram ID | -1001407174982 |
|---|---|
| Type | Channel |
| Username | @isaiahsystem |
| Description | 科技丨社科哲丨泛文化与艺术 Group: @ghosttown666 Contact: @madebyblackstack |
| Created | Between 1 March 2019 and 31 October 2021— estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 6 August 2026 |
| Last confirmed live | 30 August 2026 |
| Measurements held | 20 |
| Confirmed unchanged | 2 times, most recently 30 August 2026 |
| On Telegram | t.me/isaiahsystem |
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 28 Aug 2026, 23:52 | 13,545 | +2 |
| 27 Aug 2026, 20:28 | 13,543 | +4 |
| 26 Aug 2026, 17:26 | 13,539 | -6 |
| 25 Aug 2026, 14:45 | 13,545 | -5 |
| 24 Aug 2026, 11:48 | 13,550 | +2 |
| 22 Aug 2026, 21:35 | 13,548 | -5 |
| 21 Aug 2026, 12:59 | 13,553 | +5 |
| 20 Aug 2026, 12:13 | 13,548 | -1 |
| 19 Aug 2026, 09:03 | 13,549 | -2 |
| 18 Aug 2026, 12:08 | 13,551 | -4 |
| 16 Aug 2026, 07:05 | 13,555 | -4 |
| 14 Aug 2026, 19:33 | 13,559 | -6 |
| 13 Aug 2026, 11:38 | 13,565 | +4 |
| 12 Aug 2026, 14:15 | 13,561 | -1 |
| 11 Aug 2026, 14:03 | 13,562 | -7 |
| 10 Aug 2026, 16:31 | 13,569 | +1 |
| 9 Aug 2026, 19:02 | 13,568 | -1 |
| 8 Aug 2026, 15:44 | 13,569 | -4 |
| 7 Aug 2026, 16:26 | 13,573 | -2 |
| 6 Aug 2026, 17:17 | 13,575 | first reading |
34 posts held, back to 16 May 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 44 pagesof Telegram’s post history, 20 posts per page.
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.
| Window | Rolling 30 days · latest post in window 29 August 2026 |
|---|---|
| Posts held | 34 (16 May 2026 – 29 August 2026) |
| Views total | 25,235 |
| Reactions total | 105 |
| Forwards / comments | not exposed by the public surface — not measured, not estimated |
| Readings taken | 30 Aug 2026, 06:57 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.
Lifetime counters from Telegram’s own channel header, read 30 August 2026 — not the date at the top of this page, which is when the subscriber count was last read. A count marked ≈ was rounded by Telegram before we ever saw it — t.me prints these counters in full below 1,000 and to three significant figures above, so ≈142,000 means somewhere between 141,500 and 142,499.
247 reactions across 32 posts, in 10 distinct kinds. The most used accounts for 35.2% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| ❤ | 87 | 35.2% | |
| 👍 | 55 | 22.3% | |
| 💅 | 36 | 14.6% | |
| 🔥 | 27 | 10.9% | |
| ❤🔥 | 17 | 6.88% | |
| 🙉 | 10 | 4.05% | |
| 🆒 | 8 | 3.24% | |
| 🎉 | 4 | 1.62% | |
| 🗿 | 2 | 0.81% | |
| 👏 | 1 | 0.405% |
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 32 of the 34 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 247reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 34 most recent posts we hold, published 16 May 2026 to 29 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.
日志工作流真是目前最好的 Agents 协同工作方式,尤其借助大纲软件。大纲纵深就是 Subagents 纵深,大纲并列就是多 Agents Runtime 并发,Block 引用日志都可追本溯源、亦可蒸馏回归,无情分发,无情飞轮。真正的建造游戏内核。#mood
👍12❤1
Signed 志筑仁美
Grok Bot Guides https://x.ai/bot/guides SpaceXAI 最近整理了一套 Grok Bot 使用指南,展示如何使用 Grok Bot 高效协同工作。Grok Bot 现在价值也很明显,自带云电脑的 Agent 个人助手,原生浏览器的跨应用接力,拥有记忆和完整 Context 的 Agents 协作能力。Grok Bot 还支持启动 Cursor Cloud Agents,云上加云。需要注意,Grok Bot 云电脑会在空闲时时冻结的,不完全是官方宣传的 24h 在线,可以接 Macmini 常驻。 目前也有 local first 的开源版本: OpenMausBot,X Premium+ 以及 Cursor Pro 也能订阅使用。Grok Bot 作为 X 内容抓取、处理和总结也非常友好。进阶的 Agents 互动范式。 #Agents
❤2❤🔥1
Signed 志筑仁美
把 Matt Pocock Skills 拆成两支 Agent 小队 https://github.com/mattpocock/skills Matt Pocock 的 mattpocock-skills 一直是我 All in 的一套 Agent 工程插件。仓库目前接近 24 万 Stars,也被 Claude Code 官方 Marketplace 收录。现在它已经成了我给各类 Agents 和 Multica 扩展工程能力的主要 skills 来源。 我用 Skillshare 跟踪上游并同步到 Agents,Multica 里,我很早就把它们拆成 Matt Engineering Ops 和 Matt Writing Studio 两支小队。工程线分成 Discovery、Planner、Engineer、Reviewer 这类学习爆破组,比如重点 skills grill-with-docs 和 wayfinde…
❤7
Signed 志筑仁美
设计感受 我很开心 [[Nautilus Log]] 插件获得了一些朋友的私信喜欢/ Star,以及 Obsidan 移植复刻。Nautilus 的概念非常好,我认为应该是目前时间管理实践最强的模型。 我设计插件或者 UI 最常用的提示词是:请你使用 Linear 设计风格...如果 Linear 公司遇到这个 issue,它会怎么优化?如何设计?提示词很有效,基本符合预期。这也是我之前提到关键提示词的作用。比如我在设计 Roam UI 时被提醒:Linear 提出,不要抢夺不该获得的注意力(Don’t compete for attention you haven’t earned),所以有了 Roam 侧边栏卡片聚焦阴影和被主界面包裹而非独立。设计 [[Nautilus Log]] 时,提醒:轻量而非简陋(Building at the early stage),所以各种交互元素虽然挺多,但是可以堆叠淡化。以及 Line…
❤3👍1
Signed 志筑仁美
写作的坏结局 我发现 AI 用于写作生产已经走向了坏结局。AI 写作现在仅作为一次性 Hype 诱饵,用于劣质信息和注意力交换,在废墟上建造废墟,几乎没有复用价值。这和我最初设想的 AI 写作完全相悖。 我认为有效的 AI 写作或者知识生成应该重新审视 Zettelkasten/ Discourse Graph, Roam Ontology 这类知识组织和交互概念,这是现在真正需要重视的建造哲学。AI 可以广泛参与到写作中,前提是 AI 的写作 Vibe 和人的思考氛围必须契合,共同参与生产过程,而不是 AI 在写作过程提前作品化、独立化,这让知识生产变得黑箱、低效率,无迹可循。可悲的写作。 相关链接 1. Zettelkasten: https://zettelkasten.de/ 2. Discourse Graph: https://discoursegraphs.com/ 3. Roam Ontology: htt…
❤7🗿2🆒2👍1
Signed 志筑仁美
#memories
🆒6❤1
Signed 志筑仁美
预设提示词面板 最近越来越发现有些提示词口述重复率越来越高,很多关键句子会让 AI 的输出带来质的变化,这也是为啥很多优秀 Skills 有效或者质变部分就是那 1-2 句提示词。 比如我经常复用的口述约束词,使用 Luna Max 模型子代理来并行处理;将可复用的知识和案例写入 Wiki 这些。前者可以内置为系统提示词,但是会显得不够灵活,后者我也尝试过做成 MCP 让它自主调用,但是会让输出过于笨重和缓慢。这些都是一句话的事情,作为可以随时粘贴的 Snippet 刚好合适。 我主要对比了 Keyborard Maestro 和 Raycast,最后用 Raycast 做的本地 Prompt Launcher:快捷键直接打开面板,可以随时直接粘贴、也可以叠加 Modifier 填充文本,挺方便。(也比较推荐输入法预设模板) #Tools #Prompt
🎉4
Signed 志筑仁美
任务飞轮 这是最近 3 天的工作日志(图 1),这 3 天我都将计划全部从容完成,我的身体、学习和工作。还是那句话,所有都是可塑、可设计的,只需要一个意念或者模型。 基本很少想到休息,也足够轻松。这都是写给 Agents 的日志和内容,我发现前期将所有 Plan 规划写好,让 Agents 调用 Subagents 和不同模型来决策、执行,效率极高,效果也好。给 Agents 的 /goal 不重要,前期的规划、细节和约束推进方式才是重点。我使用 Keyboard Maestro 一键发给终端,纯跳转处理。 这个日志也让我在多任务线程里游刃有余,只要目前任务派发完并且已在运行,我继续分配下个任务。所以基本没有闲暇等输出时间。建立任务要足够细和具体、这是 Nautilus Log 时间任务管理的核心,好处是几个同类具体任务可以直接派发给主 Agents 然后分子代理去处理。所以效率是倍增的。当你启动了多个任务,真正就是享受飞…
👍3❤1❤🔥1
Signed 志筑仁美
Orca丨把项目拉起来的 Agents IDE https://www.onorca.dev/ Orca 是款以项目为主的 Agent IDE,它把 Codex/ Claude Code/ OpenCode 等 CLI Agent 放进独立的 Worktree,同时能拉起终端、编辑器、Diff、Git 状态和浏览器,UI 也非常成熟,已有移动端。 我比较喜欢的还是它与 Linear 联动。Linear Issues 可以直接建立并绑定 Worktree,Agent 也能直接读写任务,图片和评论可以进入 Agent 上下文。我前面想把任务管理 All in Linear,但现在已经由 Roam [[Nautilus Log]] 分担了重要部分。Linear 主要追踪项目、特定线程和面板,或者说 Linear 会是我的 Agents 任务派发面板,连接像 Orca/ Multica 这些 Agents 自动化任务领取。 总得来…
👍1
Signed 志筑仁美
https://x.com/naval/status/2091369804795916779 The people who want to censor (code, speech, money) are the bad guys. #quotes
💅5
Signed 志筑仁美
Datawhale https://github.com/datawhalechina 一个国内的开源 AI 学习社区,里面有从机器学习基础到 LLM、Agent 的大量教程和项目。 最近 Paul Graham 也说,如果自己 17 岁,会从零开始学习构建 LLM 训练顶级模型,而非创业。 相关链接 1. Paul Graham refs #Learning #Agents
❤4
Signed 志筑仁美
[[Nautilus Log]] 的魔法在于当你做事越多越快,你会发现空余时间也越来越多。时间消耗越多,消耗越少。认知负荷和执行力的博弈,完美的时间幻觉机器。 对金钱、时间以及 Token 的计量消费和把握拥有最大的耗费快感。 #time
❤4
Signed 志筑仁美
Showing the 12 most recent of 34 posts we hold for @isaiahsystem. 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.
@isaiahsystem edited 3 posts after it first published — the same permalink now carries different wording than the one this register originally read, caught because our own crawl held a copy of the earlier text.
An edit is not deception. Typo fixes, price updates and corrections look exactly like this too — this register can tell you the wording changed and when, not why. How this is measured.
Citation-graph rank — 87,761 of 1,626,884entries 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.
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 9 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.
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 28 August 2026 — this entry's latest reading, not the date you are reading this.
“404 KIDS SEE GHOSTS (生产力之王版” (@isaiahsystem), 13,545 subscribers as measured 28 August 2026. Telegram Register, tgregister.com/channel/isaiahsystem.
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.