What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- Whether models are scored on speed as well as output qualityFrom this comment
- Whether specific general models will be added and how they perform on PDFsFrom this comment
- Whether layout or bounding-box modes exist to show full page reconstructionFrom this comment
- Whether a model will be added, and separately when another one is plannedFrom this comment
- Which offline in-browser OCR works with reasonable CPU and memory costFrom this comment
What they doubted or pushed back on our summary
- Most entries are general models, not dedicated OCR tools, with several familiar ones missingFrom this comment
- Large general models can skip, transpose, or invent text even when layout looks betterFrom this comment
- There should be a way to say both outputs are badFrom this comment
- The site should state it covers English, since other scripts and accented languages differ greatlyFrom 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.
- Speed, cost, and accuracy will all be shown soon so users pick per use caseFrom this comment
- Another model is being added shortlyFrom this comment
- Focus is foundation vision models and open source OCR; one was dropped for unstable results, others comingFrom this comment
- One model will arrive within roughly an hourFrom this comment
What a builder can take from it: Builders can learn that listing clear model criteria, publishing speed and cost metrics, and stating language scope early prevents predictable gaps and complaints. our reading
The title, taken apart our calculation
This post got 216 points; the median for all 1442 posts is 112.
When it was posted our calculation
Friday at 16:00 UTC. Of 3,565 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 146 (4.1%) reached 50 points; on Fridays it was 2.7% of 6,422. 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