https://hackerpaper.kaipfister.de/p/1906.02735/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=35808140urn:hackerpapers:mention:1906.02735:35808140Wed, 03 May 2023 21:38:43 GMT<p>(follow-up: Figured this should be a different comment) I wanted to demonstrate what I said above so I came up with some examples of things I think a human would have an easy time implementing but might be hard to implement. BUT a key part is that I expect these to be in the dataset! I just don&#x27;t expect these to be in hundreds or thousands of githubs because they will be uncommon (but not rare). Also, we&#x27;ll pretty much ask for few-liners to give the model the biggest advantage we can (errors will compound). Prompt: from torch import nn class LipSwish(nn.Module): &quot;&quot;&quot;&quot; The Swish activation…</p><p><a href="https://hackerpaper.kaipfister.de/p/1906.02735/">Paper and discussion history</a>. A mention is not an endorsement.</p>stat.ML