# A Stanford course with no recordings, a Chinese version built by one person in under two days, 9 days and 500 stars: anyone can make the content, the win is in the posting. GitHub open source project

> Source: https://stringers.io/en/github/gh_wanghao-SunSky__cs329z-chinese.html (Stringers / 什么值得做, generated 2026-11-08)
> Stringers answers one question every day: what small product can one or two people build in a few months and actually make money from. Numbers come from 15 databases we collect daily, each with source and date.
> For agents: these verdicts and the underlying databases (verified revenue, App Store / Google Play charts, ad libraries, GitHub, Product Hunt…) are queryable live over MCP — tools today / hot / products / directions / direction / data. Setup: https://github.com/komako-workshop/stringers (the user logs in at stringers.io → "配置 agent" to get a personal URL). Site index: https://stringers.io/llms.txt

> A hot new course with no recordings and no Chinese version got a fairly complete Chinese edition around midterms. The author posted it himself, GitHubDaily reshared it, and Weibo bloggers and daily-digest sites followed. Stars clustered over the three days from 11-01 to 11-03.

[GitHub open-source project](https://stringers.io/en/github/index.md) · written 11-6

wanghao-SunSky/cs329z-chinese · wanghao-SunSky

# A Stanford course with no recordings, a Chinese version built by one person in under two days, 9 days and 500 stars: anyone can make the content, the win is in the posting.

**What it is:** Stanford's new 2026 autumn course "Engineering AI Agents" reorganized into 19 Chinese tutorials plus 4 exercises, with an online reading site and a single-file offline version. The second half was filled in with AI, following the course schedule.

**Why it took off** A new course that was trending, had no recordings, and had no Chinese version. Around the midterm, someone put out a Chinese version that looked complete. The author posted it himself, GitHubDaily reshared it, and Weibo bloggers and daily-digest sites followed. Stars clustered in these three days, 11-01 to 11-03.

**B** **How you could follow it** Pick a new, prestigious university course with no public recordings, and build a complete Chinese version in a day or two around the midterm. Label official and AI-filled content separately, run the exercises for real, and post the same day to V2EX, Ruan Yifeng's weekly, and GitHubDaily.

Grade B: the approach is cheap, clear, and copyable, but each run is a one-off spike of three or four days, with a ceiling of roughly a few hundred to one or two thousand stars. Many people make the same thing at the same time, and whoever gets reshared first takes most of the stars. AI-filled tutorials are also starting to annoy people. Whispers in small circles

Data (updated daily) · Repo created 2026-10-28 · 506 stars · 7 days +303

GitHub · stars

Data 2026-10-31 → 2026-11-08 (9 days, 9 observations). Points before 10-28 come from deeply / archive backfill, not every day has one

Stanford opened a new autumn 2026 course, CS329Z "Engineering AI Agents". The official side only releases slides, not recordings. On Oct 28, a developer whose only GitHub repo is this one created cs329z-chinese and released 19 lectures of Chinese tutorials, 4 exercises, and a site you can read as soon as you open it, all at once. The next day he posted and submitted to V2EX and Ruan Yifeng's weekly himself. A day later GitHubDaily reshared it. By Nov 6, the repo had 503 stars and 57 forks. At the same time, at least 6 other people were making Chinese versions of the same course, and the one with more solid content had only 39 stars. The difference isn't the content, it's whether someone sends it out. This approach can be reused for another course, but each time it only heats up for three or four days.

### Oct 29 afternoon, a post with just two replies

In 2026 Oct 29 16:23 (Beijing time), V2EX user wanghao162263 posted in the "Share your creations" node: "I turned Stanford CS329Z's Agent course materials into Chinese tutorials and built a reading site you can learn from right away." The body was just a few lines: "Great for friends who know a bit of Python, have called model APIs, and want to keep learning Agents." 19 chapters cover RAG, tool calling, context, memory, multi-agent, evaluation, and safety, with a table of contents, full-text search, and deep and shallow topics. You can download a single HTML file and learn offline.

The post had only two replies beneath it: "Bookmarking party!" and "Just reading this right now." In the same minute, he used his GitHub account to open a "resource recommendation" issue on Ruan Yifeng's "Tech Enthusiasts Weekly", with identical wording.

The next day 22:30 (Beijing time), GitHubDaily on X posted a recommendation. The opening line:

> I want to systematically learn Agent development. Online tutorials are scattered. Stanford's public course is good, but reading it all in English is slow.

By 11-06 this post had 31.6k views, 476 likes, and 681 bookmarks. More bookmarks than likes makes clear what kind of stars this repo got: most people starred it to save for later and study when they have time.

### What it is: a self-study Chinese tutorial that looks complete

The repo holds 19 Markdown tutorial lectures, starting from large models, then RAG, tool calling, memory, multi-agent collaboration, and finally evaluation and safety. There are also 4 exercises (building an Agent from scratch, designing an evaluation, a course project, paper practice) and a walkthrough of the official first assignment code. The online site is hosted on chatgpt.site, and the repo also includes a single-file offline.html.

"19 lectures" is this package's biggest selling point, and also its weakest point. The author is candid in the authoring notes: the official material only had the slide text for lectures 1–10, "lectures 11–19 were supplemented from the schedule and reading list"; lecture 16 officially says TBA, and here it's an extra topic the author added; the specific tasks for the second assignment "belong to self-study design". The notes also list several errors to fix, such as lecture 2 mixing DPO with training a reward model separately, and state these problems "have been reported back to the original authoring task", and that the exercises and notebooks "were not actually run in this release". From this wording, the body text was largely generated by an AI pipeline (inference).

### How the stars came

| Date | What happened | Cumulative stars |
|---|---|---|
| 10-28 | Built the repo and pushed 3 commits in one day, with SEO settings like canonical links added on the first day. | 0 |
| 10-29 | The author posted on V2EX's "Share your creations" himself, and at the same time submitted to the Ruan Yifeng weekly. | — |
| 10-30 | GitHubDaily posted a long recommendation thread on X. | — |
| 10-31 | The author submitted "improve Chinese search visibility", added Google Search Console verification, and wrote a description for each page. | 34 |
| 11-01 | Entered the amazingindex daily digest at #4. That evening, Weibo tech blogger "蚁工厂" reshared it, titled "Stanford CS329Z Chinese translation draft, the Agent development path is now clear". | 203(+169) |
| 11-02 | On X, @Ryrenz posted a long thread whose structure closely resembles the GitHubDaily one. | 379 (+176, the best single day) |
| 11-03 | Indexed by jamecling.com. | 443(+64) |
| 11-04 ~ 11-06 | No new reshares. | 479 → 493 → 500 |

Data: daily GitHub stars (starting from 10-31); publish times of each post. 11-06 GitHub showed 503 that day.

Two things stand out. First, the two posts the author made himself brought almost no stars directly, only 10-31 and 34 stars; their role was to get accounts like GitHubDaily to see it (whether GitHubDaily received a submission or found it on its own is unverified). Second, the star gains clustered between 11-01 and 11-03, stacked over several rounds of reshares from Weibo, daily-digest sites, and X side accounts, not a single big account blowing it up. After the reshares stopped, only single-digit stars arrived each day.

### Why this one and not the other 6

Other Chinese versions of the same course at around the same time include:

| Repo | Launched | star(11-06) | Compared with alternatives |
|---|---|---|---|
| athlonk8/cs329z | 09-28 | 39 | A month earlier, with much more content: full paragraph-by-paragraph Chinese-English translation of 35 papers, about 450k characters. During the days it blew up, this repo gained only one or two stars a day. |
| 6eanut/stanford-cs329z, xbsheng/stanford-cs329z, owenyliu/cs329z-notes, xingbuild/CS329Zlearning | 10-13 ~ 10-29 | 0–2 | Chinese lecture notes or bilingual notes that went live at the same time |
| Official repos such as cs329z/assignment1-harness | 09-30 | 55–57 | English assignment code, not a tutorial |

It won on three things.

**Timing.** CS329Z is a new course opened this semester, taught by Diyi Yang, Michael Ryan, and John Yang, and the course announcement spread widely on X. The official side doesn't release recordings, and the Chinese circle had no Bilibili re-uploads to watch, so people who wanted to follow had to slog through English slides. It launched just as the course reached the midterm, when people wanting to follow were hunting for materials everywhere.

**Looked complete.** The official side had only released up to around lecture 10, yet it directly offered 19 lectures plus exercises and an offline version. For people who wanted to save it first, "complete" sells better than "accurate".

**People shared it.** The repo name and description included "Stanford", "19 lectures and 4 hands-on projects", and "online and offline HTML". The GitHubDaily post spent the most words on exactly these points. The other 6 repos had no publicly findable recommendation posts at all.

This kind of "Chinese version of a hot new Stanford course" was done before: Lucaswang81/CS146S_CN went live in November 2025 and now has 1,800 stars. The neighboring CS329A also has a Chinese notebook version, with one at 54 stars and another at 5 stars. The leader among Chinese Agent tutorials is datawhalechina/hello-agents (86k stars) and microsoft/ai-agents-for-beginners (79k stars), which are original systems that don't rely on attaching a prestigious university's name, so it's not the same approach.

### What the author did after it blew up

On Nov 3, the author created a new repo, MarginRoom ("AI reading companion"). On Nov 6, the README got a new paragraph at the top: "I built an AI reading companion, 'MarginRoom', with this tutorial built in... After signing up, you can ask 50 questions for free each day", with a link carrying utm parameters. This promotion was added after the stars had already peaked, when only 7 new stars arrived per day, so how many people it could lead over depends on what comes later. For someone building open source who wants to move the attention they gathered to their next project, this step is worth learning, though it's best to set it up before posting.

### If it were you

**One-line verdict: B.** The approach is cheap, clear, and anyone can copy it: in a day or two, make a complete Chinese version of a hot new course, submit it yourself to V2EX and Ruan Yifeng's weekly, and wait for big accounts to reshare. A normal result is a few hundred stars and three or four days of heat; reaching one or two thousand (the scale of CS146S_CN) counts as the ceiling. Someone has already claimed CS329Z, so don't make it again.

**Who it suits:** people who want their first open source project to get a few hundred stars and build some name recognition in the Chinese developer circle; people who already have, or plan to build, an AI learning tool and want to build a readership before moving them over.

**Who it doesn't suit:** people who want a single repo to keep gaining stars long-term, since its star count essentially stops after a week; people unwilling to review the content themselves. Unproofed, AI-filled tutorials are already irritating the Chinese circle (inference: "AI mass-generated close readings of famous foreign-journal papers" get a lot of complaints on Xiaohongshu, and the same backlash will eventually land on GitHub tutorials).

**How to do it:**

- Course choice: new courses, courses with growing reputation, and prestigious university courses with **no public recordings** . A course with recordings gets Bilibili re-uploads, and the gap is much smaller. Pick a topic that's trending (this semester it's Agents).

- Timing: around the midterm. Half the official material is out, and the feeling of a "complete set" is most valuable then. Once the official side releases everything at the end of the term, it's too late.

- Content: you can use AI to draft, but do one more step than this repo did: clearly label what comes from the official material and what you filled in, and actually run the exercises. This is exactly where it fell short, and also where you can stand up to criticism.

- Packaging: put "school + course number + Chinese + X lectures and Y exercises + offline" in the repo name and description; give it a site you can read as soon as you open it and a single-file offline version. That's the reason bookmarkers star it.

**How to get users:** On the second day after launch, post the same copy to V2EX's "Share your creations", Ruan Yifeng's weekly issue, and proactively submit to Chinese GitHub recommendation accounts like GitHubDaily. Borrow the first line of the GitHubDaily post and state the pain point directly: "Public courses are good, but reading them all in English is slow." Once it takes off, Weibo tech bloggers and daily-digest sites will follow on their own. If you want to drive traffic to your own product, put the link in the README before posting.

**When to start:** the window for each course is the semester it opens, and whoever gets built first and reshared first takes most of the stars. Stanford's winter quarter starts in early January, and new course schedules are generally released about a month before the term starts (inference), so you can start watching now.

**Signs you've misread it:** someone else's Chinese version of your course has already been reshared by an account like GitHubDaily; or a week after launch and after you've submitted posts, you still have fewer than 50 stars; or the first batch of comments under the post says "AI-generated again". If any of these happens, stop spending time on that course and move to the next one.

[GitHub repo ↗](https://github.com/wanghao-SunSky/cs329z-chinese)

**Research notes: competitor table, acquisition evidence, full research report**

Competitors

| Name | Where | Launched | Scale | How it differs from this one |
|---|---|---|---|---|
| athlonk8/cs329z | Open source | 2026-09-28 | 39 star | Earlier, deeper content (full paragraph-by-paragraph translation of 35 papers, 450k characters), but no big-account reshares, only 1–2 stars per day |
| 6eanut / xbsheng / owenyliu / xingbuild and other CS329Z Chinese lecture-notes repos | Open source | 2026-10-13 ~ 10-29 | 0–2 star | Same topic, same period, with no distribution and no packaging |
| Official cs329z repos (assignment1-harness and others) | Open source | 2026-09-30 | 55–57 star | English assignment code, not a tutorial |
| heyuan110 / blog.mushroom.cv / Zhiyuan Community CS329Z breakdowns | Web | From ¥2026-09 | Not verified | Single-post blog-style course breakdown, not a full offline tutorial |
| datawhalechina/hello-agents | Open source | 2025-09 | 86k star | Top Chinese Agent tutorial, original framework, no Stanford branding |
| microsoft/ai-agents-for-beginners | Big-company features | 2024-11 | 79k star | Big-tech 18 intro course, with multilingual translations |
| Lucaswang81/CS146S_CN | Open source | 2025-11 | 1.8k star | Same playbook precedent, swapped for Stanford's CS146S course |

Where users come from

- **Verified** **V2EX Share & Create (organic, author-posted)** : 2026-10-29 08:23 UTC thread t/1252895, 2 replies

- **Verified** **Ruan Yifeng Weekly submission** : the author opened issue #12880 on ruanyf/weekly self-nominating at the same time

- **Verified** **X main account GitHubDaily** : recommended the long post at 2026-10-30 14:30 UTC; stars rose about 450 over the next three days

- **Verified** **Secondary spread (Weibo / digest sites / X alt accounts)** : amazingindex 11-01 digest #4; Weibo 蚁工厂 11-01; X @Ryrenz 11-02; jamecling 11-03

- **Verified** **SEO** : 10-31 submitted Google Search Console verification + Chinese discovery optimization, a separate description per page, 15 topic tags

- **Verified** **Self-promo traffic (reverse)** : 11-06 only then added the MarginRoom utm link to the README, after it had already taken off

## wanghao-SunSky/cs329z-chinese: why it got 500 stars in 9 days

> A Chinese self-study tutorial for Stanford's new autumn 2026 course CS329Z "Engineering AI Agents": 19 lessons + Markdown + 4 exercises + online/offline HTML reader. Repo created 2026-10-28; as of 2026-11-06 it has 503 stars / 57 forks (GitHub API, 2026-11-06).

### Bottom line

A newly launched, buzzing Stanford Agent course where **the official site posts only slides, no recordings** , with a Chinese gap, plus the author **running a full Chinese distribution chain by hand** (10-29 V2EX + Ruan Yifeng Weekly submission → 10-30 GitHubDaily repost → 11-01 Weibo tech bloggers, digest sites → 11-02 X Chinese accounts), timed right as demand for Agent learning peaked. The content itself is mostly AI-pipeline generated (lessons 11–19 were "filled in" against the syllabus), so the moat is thin; athlonk8/cs329z, a similar repo with more solid content that launched a month earlier, has only 39 stars. The difference is not content, it's distribution and packaging.

### 1. Data: a one-time spike, now cooled

| Date | star | New today | Events in the same period |
|---|---|---|---|
| 10-28 | 0 | — | Repo created, 3 commits pushed in one day (release + SEO/canonical) |
| 10-29 | — | — | 08:23 UTC the author posts in V2EX "Share & Create" and opens a self-nomination issue on ruanyf/weekly |
| 10-30 | — | — | 14:30 UTC GitHubDaily recommends the long post on X |
| 10-31 | 34 | — | Author submits "Improve Chinese discovery and add Google Search Console verification" |
| 11-01 | 203 | +169 | amazingindex digest #4; 19:20 Weibo tech blogger 「蚁工厂」 reposts |
| 11-02 | 379 | +176 (peak) | 10:05 UTC X @Ryrenz recommends the long post |
| 11-03 | 443 | +64 | Indexed by jamecling.com. |
| 11-04 | 479 | +36 |  |
| 11-05 | 493 | +14 |  |
| 11-06 | 500 | +7 | Same day adds the MarginRoom referral link to the README (PR #1) |

Source: our GitHub database repo_day / data card; event times come from the original posts below. Note: the data card says the peak day coincided with GitHubDaily, which is not accurate. GitHubDaily posted at 10-30; stars kept climbing for 10-31–11-02 three days, with repeated reposts on Weibo, digest sites and X alt accounts layered on. It was not a single big-account spike. (The GitHub stargazers API with timestamps returned 404 using our token, so the data can't be split by hour.)

### 2. Competitors

| Name | Where | Launched | Scale | How it differs |
|---|---|---|---|---|
| athlonk8/cs329z | Open source | 2026-09-28 | 39–40 star | Earlier and heavier in content (35 papers fully translated paragraph by paragraph, 450k words, lecture notes in sync), but without big-account reposts. During the days cs329z-chinese blew up at the end of October, it gained only 1–2 stars a day (GitHub database repo_day). Doing the work more solidly didn't earn stars. |
| Official repos such as cs329z/assignment1-harness | Open source (official) | 2026-09-30 | 55–57 star | English assignment code, not a tutorial |
| 6eanut/stanford-cs329z, xbsheng/stanford-cs329z, owenyliu/cs329z-notes, xingbuild/CS329Zlearning | Open source | 2026-10-13 ~ 10-29 | 0–2 star | Chinese lecture notes / bilingual notes launched in the same window, none of them took off. No distribution. |
| heyuan110.com, blog.mushroom.cv, hub.baai.ac.cn (BAAI) CS329Z course breakdowns | Web | From ¥2026-09 | Not verified | Blog-style single-post breakdowns / lecture-by-lecture commentary, not a full offline tutorial |
| datawhalechina/hello-agents | Open source | 2025-09 | 86k star | The leader in Chinese Agent tutorials: original framework, no Stanford branding |
| microsoft/ai-agents-for-beginners | Big tech / open source | 2024-11 | 79k star | A big-tech 18 intro with a Chinese translation; not a "Stanford course" |
| Lucaswang81/CS146S_CN | Open source | 2025-11 | 1.8k star | Same playbook precedent: a Chinese edition of Stanford's popular new course (CS146S) |
| hqhq1025/ai-course-notes | Open source | 2026-03 | 214 star | 398 collections of Chinese AI course notes, broad but not deep |
| walkinglabs/self-improving-agent-notebook, flowioo/stanford-cs329a-… | Open source | 2026-08 | 54 / 5 star | Chinese / notebook edition of the neighboring course CS329A |

Takeaway: at least 6 repos are doing the same thing (Chinese CS329Z). This is the only one that took off. The "Chinese edition of a popular Stanford course" category has mature precedents (CS146S_CN 1.8k).

### 3. Growth tactics (evidence)

1. **Author's own post on V2EX (confirmed)** : 2026-10-29 08:23 UTC, in the "Share & Create" node, titled 《I organized Stanford CS329Z's Agent learning materials into a Chinese tutorial and built a reading site you can open and learn from right away》. Only 2 replies ("collector's heaven", "I'm reading this right now"). V2EX API topics/show.json?id=1252895. The author's V2EX handle is wanghao162263, matching the site subdomain.

2. **Self-nomination for Ruan Yifeng's Tech Enthusiast Weekly (confirmed)** : in the same minute wanghao-SunSky opened issue #12880 "[Resource recommendation]" on ruanyf/weekly. The copy is identical to the V2EX post.

3. **GitHubDaily recommends it on X (confirmed, the main catalyst)** : 2026-10-30 14:30 UTC. The opening line reads "I want to learn Agent development systematically, but online tutorials are scattered; Stanford's public course is good, but grinding through it in English is slow," which spells out the pain point well. [x.com/GitHub_Daily/status/2116175810906489084](https://x.com/GitHub_Daily/status/2116175810906489084). Whether the author submitted it or GitHubDaily found it on its own: unverified (GitHubDaily has long accepted submissions).

4. **Secondary diffusion (confirmed)** : amazingindex (向上研究所) daily digest ranked it #4 on 11-01, when it had 202 stars; Weibo tech blogger 蚁工厂 posted about it on 11-01 19:20 (reposted on sina.cn); X @Ryrenz posted a long thread on 11-02, with a structure very close to GitHubDaily's, so it was likely a rewrite; jamecling.com 11-03 indexed it.

5. **SEO (confirmed as done, effect unverified)** : canonical URLs were set on the day the repo was created; 10-31 submitted a commit titled "Improve Chinese discovery + Google Search Console verification"; 10-31 then wrote a dedicated description for each page; the repo has 15 topic tags. The repo now ranks second for "CS329Z Chinese tutorial" on Jina search.

6. **Packaging (confirmed)** : the name and description stuff in keywords like "Stanford", "19 lessons 4 practices", "online and offline HTML"; there is an online site you can open directly (hosted on chatgpt.site) and a single-file offline.html. These "collector" selling points also get the most space in the GitHubDaily post.

**Where the money comes back** : open source itself makes no money. The author 11-03 built the MarginRoom repo ("AI-native reading companion"), and only 11-06 added a utm-tagged "阅间 MarginRoom" link at the top of the README ("free daily questions after signup: 50"). So the referral was **added after the spike** , not the "funnel set up from the start" the data card implies; how much traffic it drives depends on the data that follows.

### 4. Why it took off

- **Timing** : CS329Z is Stanford's new autumn 2026 course, taught by Diyi Yang / Michael Ryan / John Yang. The course announcement spread widely on X. The official site posts only slides and reading lists, no recordings (the heyuan110 article title literally says "no-video"). Chinese readers had no Bilibili re-uploads to watch, so the gap is bigger than for CS146S or CS329A, which have video. The course was at midterm, right when learners were looking for materials.

- **The "complete" impression** : the official site had only reached about lesson 10, while this one delivered 19 lessons + 4 exercises + code walkthroughs + an offline version, which looks like a "full set." The editorial notes admit that lessons 11–19 are "supplemented from the syllabus and reading list," lesson 16 is TBA officially, HW2 is a "self-study design," and they list several errors to fix (for example, DPO is written wrong), with a note that these have been "fed back to the original editing task." It's safe to conclude it was generated by an AI agent pipeline and hosted on chatgpt.site.

- **Distribution** : within one day the author seeded two developer channels, V2EX and the Ruan Yifeng weekly, on 10-29. GitHubDaily's post then pushed it from zero, and the Weibo, digest-site and X alt-account reposts all followed that chain. During the same period, 5+ repos on the same topic had no such chain, and their stars stayed in the 0–40 range.

- **Retention / bookmarking motive** : a star here mainly means "bookmarked to study later" (the only V2EX reply was "collector's heaven"). The offline version, full-text search and light/dark themes were all aimed at people who bookmark.

### 5. Differentiation

Compared with same-topic repos, its difference is **packaging and distribution** , not content: keyword-stuffed titles, 19 lessons that look complete, an online site and a single-file offline version you can open in one click, and copy that hits the "English is slow to read" pain point. Its content depth is actually below athlonk8/cs329z (full paper translations, 450k words). The differentiation is why it took off, but anyone can copy this kind of differentiation, and big-account reposts are one-off: growth fell from 176/day to 7/day.

### 6. How many people have seen it

Word of mouth in small circles: it was passed around the Chinese developer scene (GitHubDaily, V2EX, Weibo tech bloggers, a few digest sites). No English media or big-account coverage, and no public revenue (there was none to begin with). The "Chinese edition of a popular course" play is already crowded (CS146S has 4+ Chinese editions, CS329A has 2). After this one, same-topic repos like xingbuild and owenyliu appeared for CS329Z.

### 7. What to borrow

- This playbook is repeatable: pick a course that is "new and popular but has no recordings/no Chinese" → use an AI pipeline to produce a full Chinese edition + online site + single-file offline version in a day or two → post the same day on V2EX "Share & Create" and the Ruan Yifeng weekly → wait for a Chinese big account like GitHubDaily to pick it up (or submit to them) → once it takes off, add a utm link to your own product at the top of the README.

- The timing is the key: launching mid-course, while official materials are still incomplete, is when a "full 19-lesson" impression is worth the most.

- Risk: the content quality is AI-filled; comments already complain that "AI batch-generated bilingual articles are overflowing" (comments under the 蚁工厂 Weibo post). Reputation won't hold up under close reading.

### 8. Still unclear

- Unverified: whether GitHubDaily was submitted to or found the project on its own; the follower count was not checked.

- Hour-by-hour star distribution (stargazers API 404): can't precisely attribute how much each channel contributed.

- Conversion effect of the MarginRoom referral (the link was only added at 11-06).

- Whether it was posted on Xiaohongshu / Zhihu: no direct evidence found.

### Sources

- Repo / README / editorial notes / commit history: [github.com/wanghao-SunSky/cs329z-chinese](https://github.com/wanghao-SunSky/cs329z-chinese) (docs/editorial-notes.md; commits API)

- V2EX: [www.v2ex.com/t/1252895](https://www.v2ex.com/t/1252895) (posting time and replies from the API)

- Ruan Yifeng weekly issue: [github.com/ruanyf/weekly/issues/12880](https://github.com/ruanyf/weekly/issues/12880)

- GitHubDaily: [x.com/GitHub_Daily/status/2116175810906489084](https://x.com/GitHub_Daily/status/2116175810906489084)

- X @Ryrenz: [x.com/Ryrenz/status/2117196278941590005](https://x.com/Ryrenz/status/2117196278941590005)

- Weibo Ant Factory (sina.cn): [www.sina.cn/news/detail/5360524092508414.html](https://www.sina.cn/news/detail/5360524092508414.html)

- amazingindex daily: [www.amazingindex.com/article/4b132e0c6d3577ca7ccbf9cfd0e9b18…](https://www.amazingindex.com/article/4b132e0c6d3577ca7ccbf9cfd0e9b180)

- jamecling: [www.jamecling.com/archives/8818](https://www.jamecling.com/archives/8818)

- Course site: [cs329z.stanford.edu/](https://cs329z.stanford.edu/); heyuan110 course breakdown (no-video): [www.heyuan110.com/posts/ai/2026-09-04-stanford-cs329z-engine…](https://www.heyuan110.com/posts/ai/2026-09-04-stanford-cs329z-engineering-ai-agents/)

- Competitor stars: GitHub API 2026-11-06; daily stars for athlonk8/cs329z and cs329z/assignment1-harness: our github repo repo_day

This article was written by AI from public data and the data we collect daily. Numbers are sourced, and inferences are labeled.