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: Denigma – AI that clearly explains code in plain English

1 点作者 codeenlightener将近 4 年前

2 条评论

mimixco将近 4 年前
The live example on the home page doesn&#x27;t seem to work. I assumed JS was supported and typed this:<p>const addOne = function(someNumber) { return someNumber + 1 }<p>The &quot;explain&quot; box shows nothing.<p>This site makes bold claims which, so far, I don&#x27;t see backed up by anything. Even the &quot;join waitlist&quot; dialog is broken!<p>Next...
评论 #28136529 未加载
gus_massa将近 4 年前
From the first example:<p>&gt; <i>return -tf.reduce_mean((T(&quot;input&quot;) - 0.5)*2)</i><p>Don&#x27;t you want to use the average instead of &quot;0.5&quot;?<p>From the explanation:<p>&gt; <i>The code is a function that takes in an input tensor and returns the mean squared error of the input.</i><p>It&#x27;s hard to believe that the system can detect that it&#x27;s the &quot;<i>mean squared error</i>&quot;. Is this an explanation a real example from the implementation, or it&#x27;s just a handmade example?