What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- Whether the architecture generalises rather than mainly memorising, and whether simple generalisation tasks were tried.From this comment
- Whether information from early in the stream is retained after the topics change.From this comment
- What character prediction rates it achieves on unseen datasets.From this comment
- What a single graph in the results graphic shows, since its axes are unlabelled.From this comment
- How it compares with context management and retrieval rather than storing trained knowledge.From this comment
What they doubted or pushed back on our summary
- The scores look weak: a small dense model trained for two hours reportedly beats this one.From this comment
- The linked transcript shows no coherent responses, which may explain why no benchmarks exist.From this comment
- Storing knowledge in weights is lossy, so retrieval-based approaches may be more reliable.From this comment
- Tokenisation could raise the work to a semantic level and might yield large gains here.From this comment
What the maker answered our summary
13 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- The model is too small and under-trained for any generalisation claims; benchmarks come after full corpus training.From this comment
- Random 32K-character streams are interleaved to avoid ordinary forgetting, but other window sizes are untested.From this comment
- The held-out scores in the readme are already measured on unseen data.From this comment
- There are no practical means to scale it and no money to be made, so hoarding had no reason.From this comment
What a builder can take from it: If you present a small, novel continual-learning model, expect scrutiny of benchmarks, labelled charts and demo outputs, and answer scope limits plainly. our reading
The title, taken apart our calculation
This post got 277 points; the median for all 1442 posts is 112. In Open source projects (328 posts) the median is 103 points and 38 comments.
When it was posted our calculation
Monday at 04:00 UTC. Of 1,003 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 30 (3%) 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 Open source projects 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