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。

Calypso: LLMs as Dungeon Masters' Assistants [pdf]

92 点作者 azhenley大约 1 个月前

8 条评论

vunderba大约 1 个月前
So story time.<p>I&#x27;ve been hosting a DnD campaign with a group of college friends for almost a decade at this point. Since we&#x27;ve all moved away, we use Tabletop Simulator to play weekly.<p>In one of my adventures, the players met a creature named Dorian with the same backstory as the classic tale The Picture of Dorian Gray. Later, the players discovered the secret to the creature&#x27;s immortality was an indestructible painting of the creature.<p>Nearly a month before encountering this creature, my players had explored a random dungeon I’d made where one of the rooms had a huge, ornate mirror on the wall. It made everything in the reflection appear older, covered in a layer of cobwebs and dust.<p>Although this was not the primary solution to defeating Dorian, I laid subtle clues to see if anyone would remember that far back. Well, one of them did in fact remember the dungeon. They stole the painting and brought it back to the dungeon along with a secondary mirror. They then placed the mirrors across from each other along with the painting to create a sort of <i>“hall of mirrors”</i> effect on the painting itself, which caused the painting of Dorian to accelerate in age—creating a feedback loop that infinitely aged Dorian (think drinking from the wrong Holy Grail).<p>It was amazingly satisfying to all my players, and it&#x27;s also the exact sort of thing that I don&#x27;t think the current batch of SOTA LLMs (even with the temperature cranked to 1) would ever think of in <i>a MILLION years</i>.
评论 #43678053 未加载
derektank大约 1 个月前
I would really like to see what a reasoning model with access to player character information, resources available in the location, and the monster manual could do. One of the hardest things as a DM, in my experience, is creating a balanced encounter without fudging. This has always made it hard for me to justify presenting a truly deadly encounter which I feel has lowered the stakes of the game. It seems like it should be possible to create a system that knows the strengths&#x2F;weaknesses of a party and that could create a challenging but not overwhelming encounter most of the time.
评论 #43678440 未加载
评论 #43679561 未加载
评论 #43678524 未加载
评论 #43695454 未加载
评论 #43678033 未加载
gavmor30 天前
I&#x27;ve been using an LLM as DM Assistant for almost a year, now, by way of EchoDelphi[0], a tool we built at a public weekend hackathon[1].<p>It listens to the game, then sends the transcript for inference. I&#x27;ve been prompting the LLM to generate &quot;threats&quot; and &quot;setbacks&quot; based on the current scenario, and that way I always have something handy when the dice[2] indicate fortunes&#x27; turn.<p>I use this for about three hours a week, 50+ weeks in a row. Pretty good for a weekend hack!<p>0. Https:&#x2F;&#x2F;EchoDelphi.github.io<p>1. Thank you Hacker Dojo, Mtn. View<p>2. <a href="https:&#x2F;&#x2F;3.bp.blogspot.com&#x2F;-FyXSpsn-z28&#x2F;WgfgacmVdtI&#x2F;AAAAAAAAAX8&#x2F;L86bgPbbHvwY6DO0bzwzP7AMSI7imwdcQCLcBGAs&#x2F;s1600&#x2F;SWRPG%2BDice.png" rel="nofollow">https:&#x2F;&#x2F;3.bp.blogspot.com&#x2F;-FyXSpsn-z28&#x2F;WgfgacmVdtI&#x2F;AAAAAAAAA...</a>
mnky9800n29 天前
I think that technology is really the last thing I want in a dungeons and dragons game. I prefer only pen and paper to be in a pen and paper game. And while it is an obvious problem to be solved by LLMs, an LLM will never recreate the fun of using a central casting book to create a backstory [1].<p>[1] <a href="https:&#x2F;&#x2F;open.substack.com&#x2F;pub&#x2F;worldofkamenlandia&#x2F;p&#x2F;the-world-of-kamenlandia?r=2ixmx&amp;utm_medium=ios" rel="nofollow">https:&#x2F;&#x2F;open.substack.com&#x2F;pub&#x2F;worldofkamenlandia&#x2F;p&#x2F;the-world...</a>
Kichererbsen大约 1 个月前
I like to use LLMs to create random tables that I then use to spark my imagination. You can easily get o1 to create a bunch of random tables on a topic. Create multiple columns that you can then mix and match results from - or just roll multiple times on the same column.<p>I also find the image generation great for getting a &quot;feel&quot; for what a room &#x2F; location might look like so I can improvise describing it a bit better.<p>LLMs are _really_ good at finding words that &quot;go well together&quot; - so use it to come up with a bunch of words to describe the atmosphere of a particular location or the mannerisms of a particular NPC.
protocolture大约 1 个月前
I used GPT 3 to help write my halloween one shot a few years ago.<p>The outcome was pretty good. As a language model it had quite a good understanding of tone and context. In fact it ended up adding (without my notice, I was quite tired) a whole layer of subtext, after the game my players were like &quot;Ok now explain the goo!&quot; and it turns out, that in 2 handouts, and 3 scene descriptions GPT had added linked, veiled descriptions of some space goop that I hadnt planned for.
amatern29 天前
It is interesting how many of these play D&amp;D with AI games are out there. Here&#x27;s one example (no affiliation): <a href="https:&#x2F;&#x2F;airealm.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;airealm.com&#x2F;</a>
评论 #43695397 未加载
评论 #43695175 未加载
ofirg大约 1 个月前
I&#x27;m building a game with a similar idea. encounters are controlled by the AI. there is a classic RPG system built around it and human generated content for the world and story.
评论 #43679150 未加载