https://hackerpaper.kaipfister.de/p/2509.22908/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=47242163urn:hackerpapers:mention:2509.22908:47242163Wed, 04 Mar 2026 02:18:21 GMT<p>Looks like LLMs also find Dafny easier to write than Lean. This study, “A benchmark for vericoding: formally verified program synthesis”, reports: &gt; We present and test the largest benchmark for vericoding, LLM-generation of formally verified code from formal specifications … We find vericoding success rates of 27% in Lean, 44% in Verus/Rust and 82% in Dafny using off-the-shelf LLMs. https://arxiv.org/html/2509.22908v1</p><p><a href="https://hackerpaper.kaipfister.de/p/2509.22908/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.SEhttps://news.ycombinator.com/item?id=47065009urn:hackerpapers:submission:2509.22908:47065009Wed, 18 Feb 2026 19:12:48 GMT<p>A benchmark for vericoding: formally verified program synthesis</p><p></p><p>3 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2509.22908/">Paper and source history</a>. A submission is not an endorsement.</p>cs.SEhttps://news.ycombinator.com/item?id=46635426urn:hackerpapers:submission:2509.22908:46635426Thu, 15 Jan 2026 16:53:44 GMT<p>A benchmark for LLM vericoding: formally verified program synthesis</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2509.22908/">Paper and source history</a>. A submission is not an endorsement.</p>cs.SEhttps://news.ycombinator.com/item?id=45476149urn:hackerpapers:submission:2509.22908:45476149Sat, 04 Oct 2025 19:49:28 GMT<p>Formally Verified Code Benchmark</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2509.22908/">Paper and source history</a>. A submission is not an endorsement.</p>cs.SE