What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- Whether someone will build a similar setup for Civilization so agents compete over resources and fighting.From this comment
- Whether there is a timelapse view of the cities being built.From this comment
- What internal reward function the agent is aiming for.From this comment
- What it would take to run the setup locally on cheap hardware.From this comment
- How to actually play the original SimCity nowadays.From this comment
What they doubted or pushed back on our summary
- Claims that language models handle spatial reasoning badly, with some asking for specifics or training data.From this comment
- Skepticism that spatial reasoning claims are overstated, since toys like this drive progress.From this comment
- Surprise that people remain interested in these model-access protocols.From this comment
- A vision-based approach may reason about the map more naturally than raw data.From this comment
What the maker answered our summary
13 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- The breakthrough came when struggling with emulator screenshots, so they switched to an open-source engine and built an API.From this comment
- They created mayors for two new models but admit the prompting was not very scientific.From this comment
- Agents were given instructions derived from old game guides, which may bias the models.From this comment
- One mayor uses parameterized code with a tunable genome rather than a language model.From this comment
What a builder can take from it: Pick an open-source engine and build a clean API first, then let agents, evolution, or both compete while you watch. our reading
The title, taken apart our calculation
This post got 216 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 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 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