Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2509.16332/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTPsychometric Personality Shaping Modulates Capabilities and Safety in Language Models — mentioned by neomhttps://news.ycombinator.com/item?id=47261512urn:hackerpapers:mention:2509.16332:47261512Thu, 05 Mar 2026 13:47:45 GMT<p>They don&#x27;t work well if you do that: https://arxiv.org/html/2509.16332v1 - they apparently require a sense of self to preform the way they do - You&#x27;d have to do it deterministically on the front end I suspect. 2 problems of many are: context windows + compacting + whatever they do behind the scene to stitch cohesive narrative over time - single LLM convos should just never be allowed to get that long, you can effectively build whatever you want as a personality, people return to the same convo a lot, It gets wild fast. Cross Section memory is a bad feature as implemented in many chat bots…</p><p><a href="https://hackerpaper.kaipfister.de/p/2509.16332/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AI