What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- How well does the system switch between two languages within one session?From this comment
- Why must the internet be connected at first load if everything runs locally?From this comment
- Is the video part doing anything special, or just repeated snapshots?From this comment
- Can anyone get live speech recognition fast enough on their own hardware?From this comment
- Will someone build a native desktop and mobile app to avoid terminal commands?From this comment
What they doubted or pushed back on our summary
- Local setup silently fails offline at first page load despite on-device claims.From this comment
- The chosen model is still too heavy even in its smaller form.From this comment
- Live video plus real-time replies may be too slow because single images add delay.From this comment
What the maker answered our summary
7 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- Multilingual handling in one session worked better than the maker expected during limited testing.From this comment
- The maker could not reproduce the offline problem and asked for a filed report with steps.From this comment
- Video is simply a snapshot per input, and one image adds about half a second of delay.From this comment
- The maker asked the commenter for their current response time and target speed.From this comment
What a builder can take from it: Builders should verify offline startup and measure per-input latency before promising real-time multimodal behavior on modest hardware. our reading
The title, taken apart our calculation
This post got 298 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
Sunday at 17:00 UTC. Of 3,019 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 109 (3.6%) reached 50 points; on Sundays it was 3.4% of 5,343. 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