What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- How many training steps are needed before the model produces decent output?From this comment
- What is the model meant to be generating, since the samples look like nonsense names?From this comment
What they doubted or pushed back on our summary
- The writing assumes too much prior knowledge for newcomers to learn much from the site.From this comment
- The default matrix dimensions shown in the sidebar look wrong for those weight shapes.From this comment
- The site performed poorly on an Android phone even though it worked well on desktop.From this comment
What the maker answered our summary
4 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- Characters are the obvious base units, with tokenization an improvement; tokens are covered in the final Q and A.From this comment
- Returns diminish before a thousand steps; after that, adding another layer is the better move.From this comment
- Node visuals are capped at sixteen for length, but the sidebar should not show that cap.From this comment
- The untrained model emits random characters; extra layers gradually yield more pronounceable output.From this comment
What a builder can take from it: Teach a concept by letting people run and inspect a small working version, and double-check that the defaults and labels match what beginners actually see. our reading
The title, taken apart our calculation
This post got 282 points; the median for all 1442 posts is 112. In AI and agents (352 posts) the median is 108 points and 49 comments.
When it was posted our calculation
Sunday at 18:00 UTC. Of 2,649 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 84 (3.2%) reached 50 points; on Sundays it was 3.4% of 5,343. The average over all hours is 2.9%. One post's time does not explain its result; the full table of hours is on the Show HN hub.
Check your title our calculation
Type the title you plan to post. It is compared with 1,442 Show HN posts that reached 50 or more points: its length, its shape, and how posts of that length and shape did. Nothing is sent anywhere.
Type a title above to see where it sits.
Draft my Show HN post
Paste your site address and get title options and a first comment for your own Show HN post, written from what your site says and checked against the numbers above. Nothing is posted for you.
Free to try and no account needed. FoxPlug is for people who ship several projects and keep stalling on telling anyone: it turns what you ship into posts you approve before anything goes out. See what each plan includes.
More AI and agents teardowns
Points, comments, titles and times are Hacker News's own numbers, read from the post itself, last updated Nov 2026. Summaries of what people said are ours, written in our own words, and each one links to the comment it came from. Percentages and medians marked "our calculation" are computed from the posts counted on the page: they describe what happened, not what will happen to your post. FoxPlug posts nothing for you. Plans and limits are on the pricing page. Questions: support.
After the launch post: a changelog your users read
A launch brings visitors once. FoxPlug turns what you ship afterwards into a public changelog and ready posts, so the next visitor finds something new.
Start your changelog See a SaaS changelog example
Free to start. Pro is a month.
FoxPlug Pro
- A public changelog page and feed for each project
- Visual cards and walkthrough videos made from what you shipped
- Posts for X, LinkedIn and dev.to written from your changes
- Connect GitHub and the tools you build with