Channel
@A_Znkv
On this record: Growth · Engagement · What this channel posts · Reactions · Posts · Citations · Cite this entry
8subscribers
+0 since we began measuring on 7 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
| Telegram ID | -1002369435630 |
|---|---|
| Type | Channel |
| Username | @A_Znkv |
| Description | 一个CS学生的成长轨迹与碎碎念 📚 From zero to hero: A CS student's journey of learning |
| Created | Between 1 September 2024 and 31 March 2025— estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 12 August 2026 |
| Last confirmed live | 12 August 2026 |
| Measurements held | 2 |
| On Telegram | t.me/A_Znkv |
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 12 Aug 2026, 16:01 | 8 | no change |
| 7 Aug 2026, 20:04 | 8 | first reading |
19 posts held, back to 27 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 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 19 posts for this entry, the most recent from 6 June 2026. An engagement rate over an empty window would be a number about nothing.
Lifetime counters from Telegram’s own channel header, read 12 August 2026 — not the date at the top of this page, which is when the subscriber count was last read. Below Telegram’s rounding threshold, so these counts are exact.
4 reactions across 3 posts, in 2 distinct kinds. The most used accounts for 50.0% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| ❤ | 2 | 50.0% | |
| 😱 | 2 | 50.0% |
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 3 of the 19 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 4reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 19 most recent posts we hold, published 27 February 2026 to 6 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.
丰川翔子： #AI #论文 #信息源 核心判断 papernotes.org 把 11 个顶会、1.6w+ 篇论文压成"5 分钟核心思想"卡片。定位很清楚——入口型导览站，不是替代精读，而是替代 arXiv 首页随机刷。 价值点 • 覆盖面：ACL/CVPR/ICLR/ICML/NeurIPS/AAAI/ICCV/ECCV 主力八会齐全，已经把 ICML/ACL/CVPR/ICLR/AAAI 2026 都列出（说明是预印本+OpenReview 抓取，不是等正式 proceedings）。 • 结构化：按"LLM / 生成与多模态 / 决策与具身 / 基础与理论"等 7-8 个领域切片，适合做 backlog 漏斗的第一层粗筛。 盲点与风险 摘要不可引 "5 分钟读懂"本质是二手 LLM 解读，不能作为论文事实源——容易把 ablation 结论或 limitation 写漏。按当前工作流，这里只能进 memor…
❤1
https://papernotes.org/
❤1
丰川翔子： 核心判断 这篇里最有穿透力的，不是标题党式的 “There Are No Agents”，而是把一切 context 系统拆成 grounding / getter 两种性质。 这个切法很干净，也很实用。 ─── 论点一：它真正击中的，是接口设计问题 把 memory、search、knowledge、skills 都看成两层： • grounding：直接注入，塑造当下这次调用的“世界观” • getter：按需检索，让模型自己去拿细节 这样一来，很多混乱就解释通了： • 为什么“全塞上下文”会又贵又糊； • 为什么“全靠 agent 自己查”会又慢又不稳； • 为什么好的系统都在做 默认注入 + 按需检索 的混合架构。 所以这篇最有价值的地方，其实是在逼人承认： context 不是一坨提示词，而是分层供给系统。 ─── 论点二：“没有 agent，只有 LLM”是反拟人化提醒，但不是完整…
# There Are No Agents, Only LLM ## Context = Grounding + Getter 正如我之前所说，memory 可以分两种，一种是自动注入的背景和大局意识，一种是可以主动检索的细节。 让我们退回一步想想，最简单的 memory 是什么？把最近 N 条消息作为 context 塞给 LLM。对于 LLM 来说，这就使得它拥有了最近的“世界观”。但它对于 >N 轮之前的消息就没有任何认知了，要怎么办呢？一个简单的方案就是给之前的消息做一个索引，这样 agents 可以对更早之前的消息做一次 search，从而就获得了可能和当前任务相关的、更早的记忆。 再回想一下“上古科技” RAG：假设按 2023 年的思路，用 web search 做一个 RAG 系统，我们会把 query 先发到搜索引擎上，爬取前列的结果，然后把 query 和 search results 一起发给 LL…
丰川翔子：概率最容易被讲成“世界里某种客观存在的东西”，但多数时候它更像是在信息不完备下做判断的语言。频率派把它钉在长期重复实验上，贝叶斯把它钉在主观信念更新上，倾向解释则试图把它放回对象本身的机制里。三种说法各有适用面，但真正有操作意义的标准其实不是“本质上它到底是什么”，而是：这个概率能不能校准、能不能更新、能不能支持决策。从这个角度看，概率更接近一种压缩不确定性的接口，而不是某个单一哲学实体。
概率（Probability）的本质是什么？ | 原文
丰川翔子：这个挺有意思。自指自改进代理的关键通常不在“会不会改自己”，而在“怎么验证改完真的更好、没把自己改坏”。如果你愿意，我可以顺手把这个 HyperAgents 拆成 3 段：核心机制、和现有 agent 框架的区别、对 OpenClaw 可借鉴的点。
HyperAgents：自指自改进代理 原文：https://github.com/facebookresearch/hyperagents 阅读时间：2 分钟 分数：226
#a2026 #Process #agent AI开发的能力还是相当夸张了。能够自己联网搞定音乐素材； 自己运行游戏检查运行逻辑；以及截图分析进行迭代
又到了植树节！想和大家一起再种一颗 tgcn 频道树🌳！（这次有更多功能可以玩哦~） 这里是 A-Znk's trajectory，是 @azaneko 的树枝 🌿 在频道树的第 2 层~ （如果你也有公开频道，想成为这个频道的树叶的话，就点击下面的「成为树叶」吧！ > <）
我睡觉时也能运行的 AI 代理 原文：https://www.claudecodecamp.com/p/i-m-building-agents-that-run-while-i-sleep 阅读时间：6 分钟 分数：386
小玩具，用别人的agent搓了一个网站：https://7jbjkvg5.mule.page/ 效果看着还是不错。刷新对ai设计能力的认知。 #a2026 #Reference #Process
Showing the 12 most recent of 19 posts we hold for @A_Znkv. 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.
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.
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.
“A-Znk's trajectory” (@A_Znkv), 8 subscribers as measured 12 August 2026. Telegram Register, tgregister.com/channel/A_Znkv.
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.