https://hackerpaper.kaipfister.de/p/2602.16703/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=49104978urn:hackerpapers:mention:2602.16703:49104978Thu, 30 Jul 2026 00:59:42 GMT<p>This is an important question, but because of the danger of trying to do it for real it&#x27;s not one SecureBio has taken or is likely to take on. Instead we and others in the field have generally tried to work through proxies: is there something that is about as hard while not being dangerous? The closest I can think to testing whether &quot;someone smart but completely untrained / unfamiliar with biology&quot; can cause harm now is ActiveSite&#x27;s study (https://arxiv.org/abs/2602.16703) which was a null result with models from a year ago. But: 1. The main worry isn&#x27;t current models, but near-future…</p><p><a href="https://hackerpaper.kaipfister.de/p/2602.16703/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CY