Karlheinz Agsteiner<p>TL;DR: I used Google Gemini 2.5 Pro to create what might be the strongest (and perhaps only) app for the Namibian board game Hus. Gemini wrote ~99% of the code, cutting development time from weeks to hours, despite minor issues with specific rules and refactoring. My focus shifted from code quality to basic checks. Early analysis suggests player 2 has a winning advantage in the standard Hus rules on a 8x4 board.</p><p>With the (massive) help of Google Gemini 2.5 pro (experimental) I present: the probably strongest Hus playing app on this planet. Hus is a board game stemming from Namibia.</p><p>(okay, seems to be the only one, according to googling, and Gemini took a single prompt to implement a basic Alpha-Beta tree search, that works very well for a game where players have something like 10 moves, and complete information).</p><p><a href="https://agsteiner.neocities.org/Kalaha/hus.html" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">https://</span><span class="ellipsis">agsteiner.neocities.org/Kalaha</span><span class="invisible">/hus.html</span></a></p><p>Experience from working with Gemini on this:</p><p>- it could code 99%, making virtually no bugs. I changed only about 10 lines of code of >1000 lines of Javascript<br />- we did have a longish dispute because it wouldn't want to understand how a game where both players move their stones counterclockwise works.<br />- Creating a second flavor of the game that works a bit differently didn't work so well, so refactoring is still not its strength.<br />- Overall creating four independent little apps (one playing with one ruleset, the other with a slightly different ruleset, and two simulations to do fast engine-vs-engine match to get strong game logs) took me 2-3 hours, instead of 2-3 weeks that hand coding would have taken.<br />- I notice that I am moving away from trying to understand the code, and wanting beautiful code to something like "developer due dilligence" (did a hacker compromise the AI and code a virus into my app), and not caring too much about how the code looks.</p><p>Also from a lengthy 12-ply self-play it seems that this variation of the game is won for player 2. First evaluation is "player 2 wins 13 stones", which is pretty decisive already.</p><p>The original variation where you don't capture stones on the row behind the inner one gives more balanced games.</p><p><a href="https://hachyderm.io/tags/hus" class="mention hashtag" rel="tag">#<span>hus</span></a> <a href="https://hachyderm.io/tags/kalaha" class="mention hashtag" rel="tag">#<span>kalaha</span></a> <a href="https://hachyderm.io/tags/mancala" class="mention hashtag" rel="tag">#<span>mancala</span></a> <a href="https://hachyderm.io/tags/googlegemini" class="mention hashtag" rel="tag">#<span>googlegemini</span></a> <a href="https://hachyderm.io/tags/gemini25pro" class="mention hashtag" rel="tag">#<span>gemini25pro</span></a> <a href="https://hachyderm.io/tags/llm" class="mention hashtag" rel="tag">#<span>llm</span></a> <a href="https://hachyderm.io/tags/ai" class="mention hashtag" rel="tag">#<span>ai</span></a> <a href="https://hachyderm.io/tags/development" class="mention hashtag" rel="tag">#<span>development</span></a></p>