PhD research proposes 'intra-turn interaction': AI UIs shouldn't be turn-based
mattbeane · x · 2026-11-15
Researcher liuxingyu argues AI interfaces today are still essentially turn-based: you prompt, the model responds. His PhD thesis explores what interaction could look like beyond taking turns, with one concrete example: intra-turn interaction, where human and model collaborate continuously within a single turn rather than strictly alternating. swyx amplified it, adding that AI UX is 'so suboptimal it is crazy' given models are now effectively too cheap to meter.
More from AGI Musings
- Professor pushes back on mandatory AI disclosure: "bureaucratic theater" — ipeirotis · 2026-11-15
- Economist roasts Star Wars: a world with AI still full of sitting-at-computers jobs — AndyMasley · 2026-11-15
- US voters rejected data centers 44 of 45 times; China builds a million-chip AI campus — ccerrato147 · 2026-11-15
- Gary Marcus: Doomers who can't tell an LLM from Claude Code are arguing in a muddle — GaryMarcus · 2026-11-15
- Ben Todd: 3 factors explain AI hitting 10,000-hour math tasks without superexponential growth — ben_j_todd · 2026-11-15
- MotherDuck CEO: AI agents will collapse data teams into one Data Intelligence Engineer role — teodorio · 2026-11-15