TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: Hypersplit – Like Infinite Craft but in reverse

61 点作者 hopfog大约 1 年前
Hypersplit is like Neal&#x27;s Infinite Craft but turned upside down. Instead of crafting your way up from the four elements, you start big and go small, down to quarks.<p>It&#x27;s using GPT-4 to split the words, but a big difference from Infinite Craft is that I can precalculate the possible paths since they are limited (sooner or later you hit a quark or a loop). This means that I can ship it with the whole dictionary locally instead of hitting an LLM every split.<p>While it started with just the splitting, I quickly got the urge to split things faster... which turned the app into the incremental clicker it is now. It&#x27;s pretty short and starts lagging a lot once things get crazy with a lot of chain reactions (turning off Effects helps a bit), but I plan to focus on optimizations next.<p>I also wanted to try and build something without any graphical assets. The whole game is all just emojis and CSS. A big gotcha is that you can&#x27;t rely on emojis looking the same on different platforms (for example, on Windows, the explosions are misaligned).

8 条评论

garrettjoecox大约 1 年前
Love to automate these types of things. Unfortunately there isn&#x27;t much benefit to automating the shopping&#x2F;leveling, as this performs far better than any passive bonus those provide<p><pre><code> let stop = false; let play = () =&gt; { const button = document.querySelector(&#x27;[data-word-button]&#x27;); if (stop || !button) return; button.click(); setTimeout(play, 0); } play(); &#x2F;&#x2F; to play stop = true; &#x2F;&#x2F; to stop localStorage.clear(); location.reload(); &#x2F;&#x2F; to restart</code></pre>
petargyurov大约 1 年前
It was fun until I split &quot;Latitude&quot; and it gave me &quot;Lat&quot; and &quot;itude&quot;! Nice implementation though.
SamBam大约 1 年前
The Infinite Craft game was sending queries up to ChatGPT to make the new items, if I recall correctly. This one is happening so quickly it must be happening locally. Is that right? Is it using a local Javascript LLM?
评论 #39756009 未加载
评论 #39767295 未加载
评论 #39756001 未加载
评论 #39755985 未加载
评论 #39755996 未加载
评论 #39756002 未加载
joshstrange大约 1 年前
This was cool but then after leaving it running and switching back to the tab caused it to hang until the tab got killed and I lost progress.
评论 #39768514 未加载
评论 #39768579 未加载
boxed大约 1 年前
Proton should probably be splittable into quarks.
评论 #39756053 未加载
评论 #39756130 未加载
l3x4ur1n大约 1 年前
<a href="https:&#x2F;&#x2F;ibb.co&#x2F;x2BC9v9" rel="nofollow">https:&#x2F;&#x2F;ibb.co&#x2F;x2BC9v9</a> what is going on, help
评论 #39767538 未加载
albert_e大约 1 年前
Innovation &gt; Execution + Creativity &gt; Imagination &gt; Memory &gt; Storage + Retrieval &gt; Re + Trieval
AlexErrant大约 1 年前
Game idea for someone with more time than me: an LLM powered &quot;roguelike&quot;.<p>You fine-tune the LLM to spit out RPG skills based on the player&#x27;s chosen class. (Dwarven princess = summon dwarf minions, has a rare bloodline magic, whatever). The classes could get _real_ weird, like a school bus character could summon school children minions and skill up to flying a la The Magic School Bus. (Or that could be a prestige class haha.)<p>A second model would match the RPG skills to a known&#x2F;finite set of game mechanics supported by your game. This is ultimately a simple classifier - not really an LLM (though the skills on the input side are language, okay pedants). Determining the set of game mechanics to support shouldn&#x27;t be too hard - how many different ways of doing damage and (de)buffs could there be? (Okay there can be a shit-ton.) Balancing the game could be done live via reinforcement learning. To constrain the search space, it&#x27;d follow the old Zelda format of limiting you to one room&#x2F;screen until the enemy is defeated (or like Binding of Isaac for those too young.)<p>It&#x27;d have to use 2d&#x2F;sprite based&#x2F;placeholder graphics because I don&#x27;t think the rigging&#x2F;animation AI is currently good enough... but bad graphics hasn&#x27;t stopped fun gameplay before. Imagine Charizard vs Death Star. Good luck with the DMCAs.<p>Another problem is that with simple graphics and <i>literally infinitely variable enemies</i>, there&#x27;s no learning on the player&#x27;s side so there&#x27;s no real &quot;skill&quot; accumulation to improve on for the next run. There would be a lot of reading on the player&#x27;s part if you decide to just show a stats-list for an enemy type. I suppose you could turn it into a zombie game where new enemies are slowly introduced in a horde of other enemies the player&#x27;s familiar with.
评论 #39770223 未加载