https://hackerpaper.kaipfister.de/p/2304.09655/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=35684455urn:hackerpapers:mention:2304.09655:35684455Mon, 24 Apr 2023 06:59:58 GMT<p>The exact full prompt and methodology is missing from the paper[1] and Github repo[2], which makes this non-reproducible and not particularly useful in understanding the actual issue. I really think this sort of research is critical to do more of however as these outputs are going to be used in places where the assumption is that we&#x27;re looking for these sorts of things. As others have mentioned however, GPT generates insecure code, but so to most devs. The good thing though is that GPT can be systemically trained not to, while devs being more heterogeneous are more difficult to do the same.…</p><p><a href="https://hackerpaper.kaipfister.de/p/2304.09655/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CRhttps://news.ycombinator.com/item?id=35650604urn:hackerpapers:submission:2304.09655:35650604Fri, 21 Apr 2023 07:06:57 GMT<p>How Secure Is Code Generated by ChatGPT?</p><p></p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2304.09655/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CR