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。

Ask HN: Are there any interesting uses of Generative AI/LLMs in video games?

3 点作者 cdfuller3 个月前
I've always been fascinated by Procedural Generation and I believe adding Generative AI could lead to some "next-level" experiences, but I haven't seen anything bubble up in my news feeds yet.

4 条评论

6SixTy3 个月前
It&#x27;s only dialogue I know of where there&#x27;s a bunch of &quot;next level&quot; AI experiences coming through the pipeline. Generation of responses, translation, text to speech, and finally the movement of the face. Even then it&#x27;s mostly targeted mostly towards otherwise banal scripted NPC dialogue, not story beat type of thing.<p>Can&#x27;t really see much use aside from that or canning whatever the AI generated ahead of time. There&#x27;s far too much potential for it to be jailbroken or loose track of what it&#x27;s supposed to be doing.
turtleyacht3 个月前
Bespoke audio. Command your characters with your voice, not just the mouse. (They might argue or remind you of their other abilities or tactics if they don&#x27;t feel you are utilizing them maximally.)<p>The opponents have to use it too, which can open new game mechanics around silence or distracting noise.<p>Jealous NPCs. Space-sim banter. Follow-up plot points based on adhoc conversations.<p>What if we can&#x27;t click the right dialogue all the time; we have to convince them from our experience.
评论 #43062015 未加载
meristohm3 个月前
What are the costs of these potentially-interesting uses?
评论 #43062701 未加载
4d4m3 个月前
Text to 3d mesh model