Social Pulse · AI · 2026-11-12 23:02 UTC
@liu_xingyu: Beyond turn-based AI interfaces
AI interfaces nowadays are still pretty much turn-based. In my PhD thesis, I thought about what interaction would look like if we could go beyond taking turns. One example is intra-turn interaction…
You're reading the full report — free for humans and search engines.
The same content ships as a structured JSON dataset (normalized facts, sources and
citation arrays, no HTML parsing) so AI agents can consume it directly — metered per fetch via the open
HTTP 402 payment protocol.
crawlerAutoPrice=true · verify at https://esa.aisa.one/api/v1/access/verify
AI interfaces nowadays are still pretty much turn-based. In my PhD thesis, I thought about what interaction would look like if we could go beyond taking turns. One example is intra-turn interaction: https://t.co/ci9DhTVtwP
Part of the conversation: Beyond turn-based AI interfaces
@liu_xingyu says AI interfaces are still pretty much turn-based and that his PhD thesis considered what interaction would look like beyond taking turns. As one example he points to intra-turn interaction. The post has 8.5K likes, 612 reposts, 301 replies and 790.0K views, making it one of the most-engaged research-flavored posts of the day despite the poster's 3.6K followers.
Why it mattersIt shows strong interest in how people interact with AI, separate from model capability or business news.
How it compares
This post ranks #7 of the 14 highest-engagement ai posts AgentFlare tracked on 2026-11-17, with 1.0× the median likes. See the full AI briefing.
How this page is made. Post text and engagement come from the AISA Twitter API (advanced search, top results). Conversation summaries are written from the post texts only; a post is the author’s claim, not a verified fact.
Sources & citations
- @liu_xingyu on X 2026-11-12 23:02 UTC
- AISA Twitter API