https://hackerpaper.kaipfister.de/p/2406.20094/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMThttps://news.ycombinator.com/item?id=42387852urn:hackerpapers:submission:2406.20094:42387852Wed, 11 Dec 2024 14:13:34 GMT<p>LLM Synthetic Conversations Unlock?</p><p>I&#x27;m looking for experts that have similar line of research that I find quite interesting. I&#x27;m a ML eng with ~10 yrs of experience but previously I was a psychologist (unusual transition I know ha). Reading over the research, I kept thinking LLM personas were underutilized or not fully understood. I finally found the Qwen paper on 1 Billion personas to capture more complete &amp; diverse stores of information within a FM. The paper intention was for synthetic data generation for LLM training data. This paper was very cool and triggered my hypothesis that distinct personas collaborating with each…</p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2406.20094/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CL