What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- What the network input looks like, whether token bits map to context size, and how short inputs are handled, since embeddings get little coverage.From this comment
- Whether the BPE tokenizer demo is accurate, given it split a made-up phrase differently from a real tokenizer.From this comment
- Whether the token-merging diagram wrongly suggests older short tokens get discarded rather than added.From this comment
- Whether embedding data added at the final task step changes predictions and could be covered.From this comment
What they doubted or pushed back on our summary
- The site was AI-generated wholesale, which detractors said means no real value or original effort.From this comment
- The claim that 44 terabytes fits a single hard drive undermines trust before the explanation starts.From this comment
- The look follows generic AI styles, gradients and dark mode, suggesting no deliberate design choices.From this comment
- Colored text boxes fall short of being genuinely interactive or visual, despite looking attractive.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.
- The maker removed the flawed tokenizer demo and instead added a more prominent link to an external tokenizer.From this comment
- The maker fixed the hard drive claim, added a direct attribution link, and noted the figures are approximate and changing.From this comment
- The maker pushed back that LLM output is worth reading when accurate source material is supplied directly.From this comment
What a builder can take from it: When building a study guide from a source lecture, verify factual claims and fix weak interactive demos, because small errors invite dismissal. our reading
The title, taken apart our calculation
This post got 245 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
Friday at 06:00 UTC. Of 1,105 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 25 (2.3%) 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 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