https://hackerpaper.kaipfister.de/p/2402.07940/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=46202360urn:hackerpapers:mention:2402.07940:46202360Tue, 09 Dec 2025 07:50:28 GMT<p>Appreciate your response. But I don&#x27;t think deception as a capability is the same as deceptive alignment. Training an AI to be absolutely incapable of any deception in all outputs across every scenario would be severely limiting the AI. Take as a toy example play the game &quot;Among Us&quot; (see https://arxiv.org/abs/2402.07940). An AI incapable of deception would be unable to compete in this game and many other games. I would say that various forms, flavors and levels of deception are necessary to compete in business scenarios, and to for the AI to act as expected and desired in many other…</p><p><a href="https://hackerpaper.kaipfister.de/p/2402.07940/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.HC