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: How to use ChatGPT+ARKit to script experiences with natural language

54 点作者 trzy超过 2 年前
Video demonstration: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;bJFa5HOmhl4" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;bJFa5HOmhl4</a><p>I created a demo involving ChatGPT, OpenAI&#x27;s Whisper running on-device for speech-to-text (because why not?), and ARKit. By defining a custom JavaScript environment with JavaScriptCore and describing it to ChatGPT, I was able to get it to produce functioning scripts that instantiate and manipulate 3D objects.<p>Sketchfab is used to import 3D assets on the fly. Google Poly had a much better catalog of assets for this sort of thing but sadly, it&#x27;s no longer available.<p>The README.md describes how it all works but the gist of it is that user prompts are wrapped in a larger prompt that describes the environment (i.e., which functions are available to use and how they work) and constraints. The code is then executed directly. Assets for objects are fetched as needed by searching Sketchfab.

8 条评论

cloudmike超过 2 年前
It&#x27;s great to see you applying the latest tech to this idea.<p>We got pretty far with this a few years ago using more basic ML&#x2F;NLP. The app was called Moatboat: <a href="https:&#x2F;&#x2F;twitter.com&#x2F;moatboat&#x2F;status&#x2F;1082425681210859520" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;moatboat&#x2F;status&#x2F;1082425681210859520</a><p>The area I think is most exciting (and in need of more innovation) is using natural language to create (and modify!) the actual simulation &#x2F; rules &#x2F; behaviors. Our approach was to map language outputs to actions that could be chained together using Goal Oriented Action Planning plus an Entity Component System. The user&#x27;s verbs &#x2F; prepositions &#x2F; etc. would add layers of goals, each of which would enable or disable certain behavior components when triggered.<p>More details here for anyone interested: <a href="https:&#x2F;&#x2F;medium.com&#x2F;@mikejohnstn&#x2F;whatever-you-say-happens-2fa4b0d108fd" rel="nofollow">https:&#x2F;&#x2F;medium.com&#x2F;@mikejohnstn&#x2F;whatever-you-say-happens-2fa...</a><p>Directly generating source code from natural language would be a fun alternative approach to try today.
评论 #34087737 未加载
photoGrant超过 2 年前
This just gave me chills knowing at some point in the future, Children will be able to dream up their perfect fantasy land and program their surroundings by just asking for it. Then these children will become adults. The future is (undefined)
评论 #34086956 未加载
评论 #34092263 未加载
ladberg超过 2 年前
JavaScriptCore is definitely underrated! I&#x27;ve used it for quickly prototyping business logic of apps because you can iterate without having to recompile, reload, or even reopen the app on device. You can also use Safari to open up a web inspector for the context in your app and do some remote debugging.
评论 #34087017 未加载
matthieubulte超过 2 年前
This idea is genius, I love it! It inspired me to do exactly the same thing for my app. I built a small UI&#x2F;server to interactively build routines via natural language by teaching ChatGPT about our APIs and automatically running the code coming out of ChatGPT. This is a small video of the result: <a href="https:&#x2F;&#x2F;twitter.com&#x2F;matthieubulte&#x2F;status&#x2F;1606057139645992960" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;matthieubulte&#x2F;status&#x2F;1606057139645992960</a>
wildpeaks超过 2 年前
I wish ChatGPT had a public API: every demo has to use the session token trick which was recently made more difficult because OpenAI increased Cloudflare anti-bot protection to fight against it (see <a href="https:&#x2F;&#x2F;github.com&#x2F;terry3041&#x2F;pyChatGPT#features">https:&#x2F;&#x2F;github.com&#x2F;terry3041&#x2F;pyChatGPT#features</a>).
paul7986超过 2 年前
This so cool and I need to learn ARKit...there&#x27;s so many cool things to be created using Apple&#x27;s future Smart Glasses.<p>Anyone know if there&#x27;s an iPhone developer boot camp with a focus on ARKit around anywhere?<p>To me it&#x27;s like the start of the iPhone ..a land grab of innovation to be created.
评论 #34088038 未加载
coyotespike超过 2 年前
I love this, a real future shock moment. Jarvis wen??<p>Have you seen LangChain? It has a similar idea of getting GPT to output runnable code, and then using that to search the web or run Python, and giving the results back to GPT.
评论 #34086945 未加载
redgetan超过 2 年前
Cool project. Does the code generated from ChatGPT for ARKit always work? Or are there instances where it doesn&#x27;t do what you want?
评论 #34088002 未加载