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 do you think is coming next for generative AI?

5 点作者 rexbee超过 2 年前
It seems GPT3 suggests the best token&#x2F;word given the previous words.<p>Will it be possible to, given a large enough dataset of MP3 files, predict the next millisecond of audio based on previous milliseconds of audio and generate songs? Will we generate videos by predicting the next best frame?<p>Is there any technical reason we couldn&#x27;t collect first person audio and video data with the cameras and microphone on a Quest Pro and generate how the next few minutes of our life could look?

3 条评论

CrypticShift超过 2 年前
&gt; predict the next millisecond of audio based on previous milliseconds of audio<p>Not milliseconds, but AudioLM [1] already does it with just seconds, for speech (and piano). Results are already very convincing (to me).<p>[1] <a href="https:&#x2F;&#x2F;google-research.github.io&#x2F;seanet&#x2F;audiolm&#x2F;examples&#x2F;" rel="nofollow">https:&#x2F;&#x2F;google-research.github.io&#x2F;seanet&#x2F;audiolm&#x2F;examples&#x2F;</a>
评论 #33846422 未加载
terminal_d超过 2 年前
&quot;Signatures&quot; on videos to prove that, yes, they are &quot;authentic&quot; and not AI-generated. I have no idea how it&#x27;d be enforced though.
drKarl超过 2 年前
Ah, you mean like in Devs?