What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- How much useful knowledge can very small models actually hold before performance suffers?From this comment
- How would this combine with speech recognition, wake words, and other parts on small hardware?From this comment
- How were these tiny models built, and is pruning a larger model part of the process?From this comment
- Are there instructions yet for running it on small microcontroller boards as advertised?From this comment
- Can it chain tool calls so earlier results feed into later ones?From this comment
What they doubted or pushed back on our summary
- On the web demo it called an unrelated tool for a query it should have ignored.From this comment
- The demo seemed to match few templates and fail elsewhere, so it may not be useful.From this comment
- Another demo chose a harmful thermostat setting and gave nonsensical reasoning for it.From this comment
- It locked a door named for a television and showed very low confidence, suggesting unreliable outputs.From this comment
What the maker answered our summary
36 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- They said the low confidence score appears precisely when the model is unsure, and they offered to hide raw output.From this comment
- They said people usually add a transcription model for voice input, then decode outputs into actions.From this comment
- They insisted it is not a general language model but is strictly for tool calls on very cheap edge devices.From this comment
- They said for production they use their data synthesis and fine-tuning pipeline, trained locally on a computer.From this comment
What a builder can take from it: Builders should judge tiny edge models by their narrow tool-call job and use confidence signals plus fine-tuning to fix failures, not expect general intelligence. our reading
The title, taken apart our calculation
This post got 537 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
Monday 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 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 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