What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- What are solid examples where hosted LLMs perform well on CAD problems?From this comment
- Whether improvements come from specific models or from tool integration.From this comment
- How the system processes CAD data when files are binary rather than text.From this comment
- If support could extend to other CAD programs like AutoCAD or Fusion 360.From this comment
- What the best user interface for AI-assisted 3D modeling might be.From this comment
What they doubted or pushed back on our summary
- Text prompts are not the best interface for 3D modeling, and current models grasp spatial geometry poorly.From this comment
- LLMs first need to read datasheets accurately before they can generate conforming CAD models.From this comment
- A local desktop agent might be a better alternative to a hosted approach.From this comment
- Models already trained to produce precise geometry may outperform having an LLM write code.From this comment
What the maker answered our summary
8 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- Stock models perform poorly on CAD, so the team tested how far a strong harness could push them.From this comment
- LAD snapshots the model before each query so users can revert unwanted changes.From this comment
- The model receives the conversation, the feature tree, and often a screenshot of the current model.From this comment
- Dimensions default to millimeters, though the models often suggest reasonable sizes despite other shortcomings.From this comment
What a builder can take from it: A builder should expect weak native CAD abilities, so invest in context like feature trees and screenshots, and add snapshot rollback for safety. our reading
The title, taken apart our calculation
This post got 191 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 16:00 UTC. Of 3,565 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 146 (4.1%) 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