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: What it takes to build Jarvis using current state of the art LLMs?

1 点作者 rohith2506大约 2 年前
For people who don&#x27;t know Jarvis, it&#x27;s a know-it-all personal assistant which just doesn&#x27;t answer but also perform actions based on commands. It&#x27;s catered to specific person needs. We want this to run on your preferred device instead of cloud<p>I thought we were miles away from building something like this because of so many complex parts involved<p>1. State of the art speech to text generation ( Shout out to Whisper here )<p>2. State of the art question answering ( GPT-*, LLama, etc..)<p>3. Integration with your virtual life ( emails, music, finances etc..)<p>1 &amp; 2 have definitely shown significant progress. the major bottle neck right now is 3. Most of our virtual life is centralised and no one provides a clean API such that we can actually have a holistic view of everyone&#x27;s digital persona in one place. And last but not least, privacy and security is super important considering we are giving the total access to a bot. Am I missing anything else? Would like to see some healthy discussion on this topic

2 条评论

sharemywin大约 2 年前
There&#x27;s a lot of API hubs and task automation sites.<p>also ChatGPT can write code for an api pretty decently
2Gkashmiri大约 2 年前
i would like to talk to samantha from &quot;her&quot; movie.