What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- Whether models may practise against the very bots they are later graded on.From this comment
- How leading human players would fare against the agent-written bots.From this comment
- Whether agent bots reveal anything new or merely reuse existing human-written bot code.From this comment
- Whether agents could play the game directly rather than only writing bot code.From this comment
- Where the fuller charts are, since one model shown in video is missing from the graphs.From this comment
What they doubted or pushed back on our summary
- Unclear what the benchmark actually measures, since code speed, game knowledge and strategy all mix together.From this comment
- Much bot code likely sits in training data, so the task may just measure improvement over public solutions.From this comment
- Suspicion that models draw on pre-training data instead of genuinely solving the task.From this comment
What the maker answered our summary
11 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- Practice matches against graded opponents are allowed during the hour, but source code is withheld.From this comment
- Lower scores against top-tier bots simply reflect that those opponents are harder to beat.From this comment
- A long run finished in far less time than the window, though its format favoured these bots.From this comment
- The maker wants to move past hand-written bot code toward limited-time neural network training.From this comment
What a builder can take from it: Time-limited bot-writing benchmarks are informative, but you must explain what they measure and control for training-data contamination. our reading
The title, taken apart our calculation
This post got 254 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 14:00 UTC. Of 4,022 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 113 (2.8%) 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