https://hackerpaper.kaipfister.de/p/2603.18090/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=48835154urn:hackerpapers:mention:2603.18090:48835154Wed, 08 Jul 2026 18:04:06 GMT<p>&gt; GPT-Live-1 is the first version of a new generation of models, and we believe the full-duplex architecture + delegation enables entirely new ways of human-AI interaction. Awesome. Are you guys able to share anything about the model architecture? I&#x27;ve been interested lately in split-transformer RVQ-based conversational agents, e.g. via stuff like https://arxiv.org/abs/2412.10208 (ResGen) and https://arxiv.org/abs/2603.18090 (MOSS-ITT) and of course Moshi (https://arxiv.org/pdf/2410.00037). Intuitively, decoupling semantic and audio-timeslice-space generations with coupled but distinct…</p><p><a href="https://hackerpaper.kaipfister.de/p/2603.18090/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.SD