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。

LangChain Agent Simulation – Multi-Player Dungeons and Dragons

95 点作者 vvoruganti将近 2 年前

8 条评论

gareth_untether将近 2 年前
One of my side projects has been hacking a ChatGPT model and a JS App to make a multiplayer dnd style game. The AI does all the creative descriptions which are saved by the JS app and fed to the players.<p>It has been a lot of fun working on it because it gave me a taste of new way of working, honing prompts and finding the limits of the AI, then figuring out how to offload the parts it struggled with (mainly storing stats, inventory, regurgitating room descriptions, etc.).
评论 #37118764 未加载
评论 #37118129 未加载
xrd将近 2 年前
I&#x27;ve been experimenting with using local LLMs (Llama of course) and building d&amp;d games for my kids (not multiplayer but we just pass the phone around in the car so each kid can have a turn talking to the DM). It&#x27;s going surprisingly well, and has been a fun way to explain LLMs and the tech behind them. I wrote up the initial experiences here:<p><a href="https:&#x2F;&#x2F;blog.katarismo.com&#x2F;2023-05-26-i-m-a-dad-i-replaced-myself-with-an-llm" rel="nofollow noreferrer">https:&#x2F;&#x2F;blog.katarismo.com&#x2F;2023-05-26-i-m-a-dad-i-replaced-m...</a><p>I&#x27;m doing all of it in JavaScript. I&#x27;m still not excited about langchain, and the JS version is lagging a lot from the python version. By the way, pocketbase is amazing for something like that.
评论 #37121784 未加载
ianbicking将近 2 年前
How do people work without seeing the underlying prompts being sent to the LLM? I think I know what&#x27;s going on (which probably isn&#x27;t much?) but at least make it clear what&#x27;s going on. The details all matter.<p>Not much here though, just rotating chat with the LLM taking on both sides. The prompts (<a href="https:&#x2F;&#x2F;python.langchain.com&#x2F;docs&#x2F;use_cases&#x2F;agent_simulations&#x2F;two_player_dnd#protagonist-and-dungeon-master-system-messages" rel="nofollow noreferrer">https:&#x2F;&#x2F;python.langchain.com&#x2F;docs&#x2F;use_cases&#x2F;agent_simulation...</a>) are fine, but not great. No guidance on tension, on actions failing or succeeding, on plot advancement. Nothing to break out of anticipation loops, which are common (when the LLM promises something &quot;is about to happen&quot; but doesn&#x27;t actually know what and keeps deferring the action).<p>It probably will work OK because the LLM plays both sides, and does so &quot;fairly&quot;, i.e., always in character and never trying to &quot;win&quot;. It&#x27;ll run out of space for the history, but simple pagination might fix it (maybe that&#x27;s even a LangChain feature?) – it&#x27;ll drift, maybe dramatically. Or, given the system prompt, it might _not_ drift when appropriate; that is, it might not allow diverging from the original concept, and so not allow consequential action.
justinlloyd将近 2 年前
Am too also working on a multiplayer D&amp;D Dungeon Master agent, Banderschnappen, though right now it is in a non-playable state as I convert a number of Jupyter Notebooks into more modular and cleaner code. I treat the LLM (ChatGPT in this case) like a rendering engine of the world, and also of the user interface, but ultimately all the heavy lifting of logic is done by a traditional game engine.
avereveard将近 2 年前
&gt; this won&#x27;t be easy<p>&gt; I know that they are afraid of fire<p>The player side is doing a lot of heavy lifting here in actually directing the game.
startupsfail将近 2 年前
It is pretty broken. Models are aligned for safety not gameplay.
评论 #37118451 未加载
upwardbound将近 2 年前
Would anyone who has a throwaway OpenAI key be willing to host this on HuggingFace so people stopping by this thread can play the game? If I have free time in a few hours I&#x27;ll try.
Ycros将近 2 年前
Every time I look at LangChain it seems like unnecessary abstraction. The value in this example are the prompts.
评论 #37118386 未加载
评论 #37119256 未加载