What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- Requests for more implementation notes and technical details about the demo.From this comment
- Whether the mid-run score stall around a few thousand is expected behavior.From this comment
- Whether training collapse reflects a code bug or something inherent to the network.From this comment
- Why the snake was penalized for slow apple pickup instead of just survival.From this comment
What they doubted or pushed back on our summary
- Training scores drop noticeably when switching from training to watch and back.From this comment
- Runs on a 10x10 board broke, with scores going negative and games looping.From this comment
- The snake repeats the same path endlessly without learning from failed attempts.From this comment
- Antivirus flagged the site as suspicious, and it fails without WebGPU support.From this comment
What the maker answered our summary
2 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- Training never stabilizes and collapses eventually, likely because weights blow up over time.From this comment
- The process prioritizes speed over stability and is meant as a demo.From this comment
- WebGPU can be turned on in settings, and it works on an older phone.From this comment
What a builder can take from it: Expect demo-scale training to prioritize speed over stability, and document environment choices and browser requirements before launch. our reading
The title, taken apart our calculation
This post got 205 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
Thursday at 15:00 UTC. Of 4,000 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 133 (3.3%) 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 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