What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- Whether the approach relates to mixture-of-experts designs like another model's architecture.From this comment
- Whether they had tried looping repeatedly over the duplicated layers to see performance.From this comment
- What tools or methods exist for identifying these strong internal circuits.From this comment
- Whether this matches models that run a second pass to check their own answers.From this comment
- Whether this is the same as putting encoded text into a prompt.From this comment
What they doubted or pushed back on our summary
- Duplicating single layers on their own does not produce useful gains.From this comment
- Optimal placement makes results worse, so effects depend on which layers are chosen.From this comment
- It may be a lesser version of existing looped-language-model work.From this comment
- Looping whole models is probably inefficient, since learned internal structures form during pretraining.From this comment
What the maker answered our summary
24 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- The technique is separate from expert sparsity and works by repeating vertical transformer sections.From this comment
- Single-layer duplication was tried and proved useless, and feeding later outputs backward is usually harmful.From this comment
- Internal structures likely emerge during large pretraining, so repeated whole-model loops may be wasteful.From this comment
- They built their own analysis scripts and plan to publish them once current work finishes.From this comment
What a builder can take from it: A working demonstration plus openly shared scripts and limits teaches more than polished claims, so publish reproducible evidence and concede what failed. our reading
The title, taken apart our calculation
This post got 495 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
Tuesday at 13:00 UTC. Of 3,788 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 112 (3%) reached 50 points; on Tuesdays it was 2.8% of 8,995. 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