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。

Automating Interactive Fiction Logic Generation with LLMs in Emacs

100 点作者 dskhatri大约 1 个月前

8 条评论

spudlyo大约 1 个月前
GPTel is a very powerful interface for working with LLMs in Emacs. It took me a while to understand that its real value isn&#x27;t what you get with M-x gptel, which creates a dedicated chat session and buffer, but rather the ability to sling prompts, context, and LLM output around in a native Emacs way. You can add to the context from dired, from a file, from a buffer, you can select from various prescribed system prompts for different functionality, you can prompt from the minibuffer, the kill-ring, the existing buffer, a selection, you can have the responses go to the minibuffer, the kill-ring, a buffer, the echo area -- it&#x27;s extremely flexible.<p>I have a little helper function that uses gptel-request that I use while reading Latin texts. It sets the system prompt so the LLM acts as either a Latin to English translator, or with a prefix argument it breaks down the grammatical structure and vocabulary of a sentence for me. It&#x27;s very cool.
评论 #43542764 未加载
zoogeny大约 1 个月前
This is one of the most promising uses of LLMs that I have found in my own work. Many times I have an idea for a refactor or even a feature but I have this mental reluctance just due to the amount of code I would have to write. Like, I have this counter in my head on the number of key-strokes it will take to write a wrapper object in several places, and I hesitate.<p>Just being able to tell an LLM &quot;rewrite all of this code using this new pattern&quot; and then dozens of code sites are correctly updated is a huge help. It makes me consider bigger refactoring or minor features that I might normally skip because I am lazy.
IngoBlechschmid大约 1 个月前
Gwern shared an idea how to exploit the strength of current-generation LLMs, despite their weaknesses, for &quot;create your own adventure&quot;-style fiction. <a href="https:&#x2F;&#x2F;gwern.net&#x2F;cyoa" rel="nofollow">https:&#x2F;&#x2F;gwern.net&#x2F;cyoa</a> Having people vote on AI-generated potential continuations should yield better results and cut costs at the same time.<p>From the title I thought this was an implementation of Gwern&#x27;s idea, but it&#x27;s not.
评论 #43540850 未加载
评论 #43539248 未加载
ZeroGravitas大约 1 个月前
I&#x27;ve thought that an LLM wrapper that&#x27;s able to turn valid moves that you haven&#x27;t phrased exactly as the old parser expected into one of the acceptable versions, could be a good quality of life improvement to classic text adventures.<p>I thought this might be related based on the title, but it&#x27;s more about refactoring code.
noufalibrahim大约 1 个月前
This is probably the most tightly specified use case of an LLM that I&#x27;ve come across so far.
anthk大约 1 个月前
I wouldn&#x27;t use that for Inform6. If you can&#x27;t grasp the simples OOP language ever...<p>Also, Inform6 allows you far more interactivity than a CYOA game. Which both are systems based on states, but a text adventure allows timers, random events, even chat simulations...
kleiba大约 1 个月前
What strikes me as odd in the video: why would the author not fill the paragraphs?!
评论 #43538527 未加载
bradleyy大约 1 个月前
Honestly, seeing this, I&#x27;m 1&#x2F;2 tempted to revisit org-mode and retrying emacs as a dev environment.<p>Don&#x27;t get me wrong; I use emacs all the time, I just can&#x27;t seem to make it work for me when working with teams of people on large-ish software projects.<p>But maybe org mode is worth a revisit as a &quot;managing my ADHD&quot; tool; it&#x27;s got to be better than Jira, haha.
评论 #43542314 未加载
评论 #43547690 未加载