Channel

Parallel Experiments 🌠

@LinghaoCh

On this record: Growth · Engagement · Reactions · Posts · Citations · Cite this entry

1,763subscribers

+4 since we began measuring on 6 August 2026

Risers and fallers across the register · movement among entries of 1,000–3,162.

Register entry

Telegram ID	-1001381813778
Type	Channel
Username	@LinghaoCh
Created	22 September 2018 — measured — cross-checked against a third-party dataset (TGDataset)
First recorded	6 August 2026
Last confirmed live	9 September 2026
Measurements held	11
Confirmed unchanged	1 time, most recently 9 September 2026
On Telegram	t.me/LinghaoCh

Growth

11 measurements spanning 34 days, net +4. 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 1,758–1,771 and does not start at zero.

Measurement log — every subscribers count we have recorded
Measured (UTC)	Subscribers	Change
9 Sept 2026, 11:58	1,763	-6
4 Sept 2026, 12:20	1,769	+4
29 Aug 2026, 02:26	1,765	-1
26 Aug 2026, 06:33	1,766	-1
23 Aug 2026, 16:56	1,767	+1
20 Aug 2026, 01:32	1,766	+3
17 Aug 2026, 11:24	1,763	-1
13 Aug 2026, 13:38	1,764	+1
10 Aug 2026, 09:54	1,763	+4
7 Aug 2026, 07:58	1,759	no change
6 Aug 2026, 13:16	1,759	first reading

Engagement

20 posts held, back to 9 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 2 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 20 posts for this entry, the most recent from 25 July 2026. An engagement rate over an empty window would be a number about nothing.

Reaction mix

78 reactions across 12 posts, in 9 distinct kinds. The most used accounts for 47.4% of them.

Every reaction kind recorded on the sample, most used first
Reaction	Count	Share
❤	37	47.4%
👍	19	24.4%
🤔	8	10.3%
🔥	6	7.69%
👏	3	3.85%
🎉	2	2.56%
🏆	1	1.28%
🐳	1	1.28%
👀	1	1.28%

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 16 of the 20 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 78 reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.

Measured over the 20 most recent posts we hold, published 9 February 2026 to 25 July 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.

Recent posts

25 Jul 2026, 19:39 UTC364 views1 reactionsread 7 August 2026

https://alexzhang13.github.io/blog/2026/harness/ > A good harness is a harness that reduces unfamiliar problems to familiar ones and reduces complex problems to simple ones. In other words, even if the state s is out-of-distribution (OOD) to what any individual language model call was trained for, a good harness produces observations o that are locally in-distribution (LID), which we define as every individual LM ca…

👀1

Signed Linghao Zhang

6 Jul 2026, 08:24 UTC736 views0 reactionsread 7 August 2026

https://linghao.io/posts/taxonomy-differences-matter 以前觉得 taxonomy 只是无聊的分类学，开始做 LLM quality 以后几乎每天都在思考和跟同事争论 loss taxonomy 的细枝末节。这几天放假闲下来仔细想想，taxonomy 无处不在，至关重要。

Signed Linghao Zhang

28 Jun 2026, 05:39 UTC≈1,660 views4 reactionsread 7 August 2026

关于层出不穷的各式 AI memory system 的一些思考：我们应该把更多的精力放在设计更好的 eval 上，从而让最强的 memory system 进化出来 https://linghao.io/posts/memory-systems-should-be-evolved

🤔4

Signed Linghao Zhang

17 May 2026, 21:54 UTC≈1,110 views0 reactionsread 7 August 2026

https://arxiv.org/abs/2503.02113 The core idea: Deep learning does not work because neural nets somehow escape generalization theory. It works because very flexible models can still generalize when they have soft inductive biases — preferences for simple, compressible, structured solutions. Key points: - 🧠 Overparameterization is not automatically a problem. Having more parameters than data points does not nece…

Signed Linghao Zhang

18 Apr 2026, 02:14 UTC991 views13 reactionsread 7 August 2026

Forwarded from @foreseaz_collectionPhoto

一月底最后一个周六有了一个灵感，想做个解放双手，优化了 AirPods 录音，边散步边和自己对话的 App。打开 Cursor coding 了一天，第二天就出门去 SoHo 散步就用上了，然后就完全离不开了，一天不落用到今天，录了300多条录音，200多个不同地点，近100小时和自己的对话。这两个半月工作之余的 side project 时间全放在了这个 App 的打磨上，和自己和它的关系也有忽近忽远的变化，有意思的是也用它自己记录了下来。最近在读荣格，说自性化的目标是走向完整，走向完整指的是充分体验所有情感，如何充分体验所有情感？我给的答案是记录。放下手机，出门散步，踏出的每一步，对自己说出每个字，周围记录下来的环境音，路上随手拍的照片，都是值得记录下来的此时此刻。随手录音，AI转录，适配了各种麦克风，privacy first，取名叫 Yuho，Logo是个伦敦的大肥鸽，昨天刚刚上线了，欢迎试玩，有机会一起散步🚶 如果…

❤12🤔1

Signed Linghao Zhang

23 Mar 2026, 23:25 UTC≈1,240 views1 reactionsread 7 August 2026

装 nanoclaw 的时候，发现启用新功能比如对接 telegram 不再是通过在配置里打开一个选项，而是让 agent 直接修改本地代码来实现功能。这一点很有意思，几乎就是 config as code 的彻底反面 — code as config。联想到一些生物学的类比，写了这篇文章。以前软件的"基因"是固定的，所有人跑的是同一份 binary。但当 AI agent 开始直接改源代码本身，每个人跑的软件就开始各自突变、各自演化 — 这是软件的物种分化。由此引出三个有意思的推论：只在你这台机器上出现、别人永远无法复现的 bug；版本号失去意义，取而代之的是追踪每个实例的演化谱系；以及代码最终可能优化到只有 agent 看得懂、人类再也无法理解的程度。最后提了三个对 2027 年的预测：Verification-as-a-Service、Frozen Core 架构、Reverse-SaaS。 https://…

🎉1

Signed Linghao Zhang

15 Mar 2026, 07:39 UTC≈2,100 views16 reactionsread 7 August 2026

Photo

周末无聊 vibe coding 了个玩具，模拟 EVA 里 MAGI 系统的三方表决。你输入一个提案，MELCHIOR、BALTHASAR、CASPAR 三个子系统会从各自人格出发思考然后投票，推理过程接了 Gemini 3.1 Flash Lite 实时流式输出，看起来挺有那味儿的。 https://github.com/dnc1994/magi

👍9❤5🎉1🐳1

Signed Linghao Zhang

14 Mar 2026, 04:43 UTC≈1,090 viewsread 7 August 2026

https://github.com/dnc1994/jarvis 我最近也做了相关的实践，目前 scope 比上面这位要小得多，只负责管理三类 todo：ad hoc、recurring、project based。一个需求是它会基于 obsidian，因为我本来就是重度用户。配合 *claw，现在不管走到哪，在 telegram 里就可以按照符合自己设想的信息架构的方式去管理 todo 我甚至感觉开源也没什么意义，agents 的厉害之处就在于每个人都可以高度定制自己用的方案。

Signed Linghao Zhang

14 Mar 2026, 04:36 UTC≈1,610 views6 reactionsread 7 August 2026

其实纯个人使用的话 memory 系统不需要很复杂。非常认同这篇文章的大道至简：https://x.com/koylanai/status/2025286163641118915 每次跟 AI 开新对话都要重新介绍自己、粘贴风格指南、解释目标，作者烦了，于是造了个"Personal Brain OS"。系统本质是一个 Git 仓库，80+ 个 Markdown/YAML/JSONL 文件，不用数据库也不用 API Key。在任何地方只要把仓库拉下来，直接用 Cursor 或 Claude Code 打开就能跑。架构上分成 11 个隔离模块，用三级渐进加载：第一级是路由文件，决定该加载哪个模块；第二级是模块指令；第三级才是具体数据。这样做是为了避免无关内容占用上下文窗口，模型注意力是有限的，塞太多反而变差。文件格式也是刻意设计的。JSONL 存日志，因为它只能追加不能覆写，防止 agent 一不小心把历史数据全干掉（…

❤6

Signed Linghao Zhang

10 Mar 2026, 07:08 UTC915 viewsread 7 August 2026

https://store.steampowered.com/app/3509230/Gambonanza/ 小丑牌火了以后 Balatro-like 层出不穷，但鲜有做得这么出色的。国际象棋玩法容易上手，机制和boss设计可圈可点。

Signed Linghao Zhang

4 Mar 2026, 07:22 UTC≈1,050 views0 reactionsread 7 August 2026

https://youtu.be/fsLh-NYhOoU Mind blown 🤯

Signed Linghao Zhang

1 Mar 2026, 21:49 UTC≈1,420 views0 reactionsread 7 August 2026

https://github.com/petergpt/bullshit-benchmark 这个 Bullshit Benchmark 挺好玩的，测试模型是否能够意识到人类提供的问题是无稽之谈。Claude 又屠榜了 🔥

Signed Linghao Zhang

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

Forward network

Republished by

Channels on the register that have forwarded this channel's posts into their own feed.

Hyperbola
@HyperbolaPodcast · 222 posts Vintage NLP for Work
@nlpfw · 1,0921 post 101010
@OB101010 · 851 post Winnowing Words
@winnowingword · 2171 post

Republishes

Channels on the register whose posts this channel has forwarded.

C’s Random Collection
@foreseaz_collection · 3342 posts

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.

Mentions

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.

HTTP 301
@instante_thoughts · 21 post

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.

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 9 September 2026 — this entry's latest reading, not the date you are reading this.

“Parallel Experiments 🌠” (@LinghaoCh), 1,763 subscribers as measured 9 September 2026. Telegram Register, tgregister.com/channel/LinghaoCh.

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.