What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- Whether memory use can be tuned so a larger-RAM machine runs the same model faster.From this comment
- What the collaboration credit in the README actually means, and whether a team was involved.From this comment
- Whether something similar already exists for other platforms, or whether this could be ported.From this comment
- How to handle web access and external services when relying on local models.From this comment
What they doubted or pushed back on our summary
- Prefill is the real bottleneck, so decode speed alone doesn't tell the full story.From this comment
- Disk-swapping approaches are very slow and may wear out the drive early.From this comment
- The first-on-phone claim feels familiar, since similar statements have appeared before.From this comment
What the maker answered our summary
3 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- Prefill currently uses the per-token path and batching expert reads per layer is planned.From this comment
- Cache size is a flag, but speed barely changed because GPU dispatch limits it, not storage.From this comment
- No outside involvement; the credit was only for heavy use of a coding tool and was reworded.From this comment
What a builder can take from it: Report prefill and memory-tuning limits honestly up front, since builders judge these demos by real prompt processing speed, not just decode numbers. our reading
The title, taken apart our calculation
This post got 312 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 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 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