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。

OpenAI Multimodal Research

16 点作者 david2016超过 4 年前

3 条评论

saeranv超过 4 年前
Fascinating stuff. The idea that visual and language generation could be generalized with the same underlying model was the most interesting part of Lex Fridman&#x27;s podcast with Ilya Sutskever in May: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=13CZPWmke6A" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=13CZPWmke6A</a>
dang超过 4 年前
<a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=25649557" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=25649557</a><p>and <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=25649740" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=25649740</a><p>point to the specific two releases.
greenburg超过 4 年前
Very cool stuff. However, I didn&#x27;t find any links to the Github Code. Is this release as well part of their GPT-2 strategy?