What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- Whether the model itself can be shared for people without the app.From this comment
- Whether input could come from a microphone or whistling instead of MIDI.From this comment
- How extra musical details like key attack velocity, grace notes and pedal would be modelled.From this comment
- How large the preference training set was and how long training took.From this comment
- How much optimisation was needed to run the model quickly on a phone.From this comment
What they doubted or pushed back on our summary
- Rhythm and composition need work, since the output lacks clear musical form.From this comment
- Generation speed is unrealistically high, as nobody plays that many notes per second.From this comment
- Language models performed poorly when asked to parse sheet music.From this comment
What the maker answered our summary
6 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- Quality is around an early general model: worth sharing but still clearly improvable.From this comment
- They plan longer-term planning, parallel candidate generation and automatic ranking of the best continuation.From this comment
- Note-level attributes could become extra fields, while pedal and similar global effects fit better as control events.From this comment
- Preference tuning used only about 700 examples and took minutes; pretraining took about half a day.From this comment
What a builder can take from it: A compact model with fast on-device inference wins attention even when musical quality is rough, as long as the maker states limits plainly. our reading
The title, taken apart our calculation
This post got 598 points; the median for all 1442 posts is 112.
When it was posted our calculation
Thursday at 12:00 UTC. Of 3,017 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 80 (2.7%) reached 50 points; on Thursdays it was 2.7% of 8,077. 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 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