What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- Request for a write-up covering how the network was designed and which references informed it.From this comment
- Whether longer context holds up or the model starts making things up after a couple of sentences.From this comment
- How it responds to inputs that were not part of the training data.From this comment
- Whether a model could learn only from chat turns, with no separate offline training data.From this comment
- Questions about how the dataset was made, where training runs, and how the output file is produced.From this comment
What they doubted or pushed back on our summary
- The shown responses appear copied from training data, so handling unfamiliar questions is doubted.From this comment
- Lowercase-only training data causes odd replies to capitalized input, suggesting a data limitation.From this comment
- Suspicion about the many removed comments posted by newly created accounts.From this comment
What the maker answered our summary
10 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- The maker liked a suggestion for a personality that communicates using emoji and called it a future idea.From this comment
- The maker wished they had thought of the fish name joke tied to memory recall problems.From this comment
- The maker conceded that with nine million parameters it handles unfamiliar queries poorly by design.From this comment
- The maker said the post's popularity was unexpected and came from a weekend practice exercise.From this comment
What a builder can take from it: A deliberately tiny, end-to-end demo with obvious limits can teach more and attract more interest than a polished but opaque model. our reading
The title, taken apart our calculation
This post got 915 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
Monday at 00:00 UTC. Of 1,199 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 46 (3.8%) reached 50 points; on Mondays it was 3.1% of 7,396. 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