Copying my comment from a previous post:<p>From the first example:<p>> <i>return -tf.reduce_mean((T("input") - 0.5)</i>2)*<p>Don't you want to use the average instead of "<i>0.5</i>"?<p>From the explanation:<p>> <i>The code is a function that takes in an input tensor and returns the mean squared error of the input.</i><p>It's hard to believe that the system can detect that it's the "mean squared error". Is this an explanation a real example from the implementation, or it's just a handmade example?<p>Note: Wait more time to repost. Users usually get angry and start to flag our post is you repost too often.<p>Also, as mimixco said in <a href="https://news.ycombinator.com/item?id=28131271" rel="nofollow">https://news.ycombinator.com/item?id=28131271</a><p>> <i>The live example on the home page doesn't seem to work. I assumed JS was supported and typed this:</i><p>> <i>const addOne = function(someNumber) { return someNumber + 1 }</i><p>> <i>The "explain" box shows nothing.</i><p>> <i>This site makes bold claims which, so far, I don't see backed up by anything. Even the "join waitlist" dialog is broken!</i><p>> <i>Next...</i><p>I tried and got the same outcome.