Thinking Machines' research preview processes audio, video and text in 200ms chunks
kimmonismus · x · 2026-10-23
- Thinking Machines Lab's research preview processes audio, video and text in 200ms chunks for continuous interaction.
- Architecture splits the work: an interaction model stays in the conversation while a separate background model handles deeper reasoning and tools.
- Part 3 of the author's full-duplex thread, showing a concrete "chat while it works" design.
Related event: Realtime Voice Agents Adopt Dual-Model Split Architecture(2 posts)→
More from Models
- OpenAI blocks manual reset with 13% usage left: 'no reset needed right now' — AccomplishedSugar490 · 2026-10-23
- Meta's 816B Muse Spark Open scores 39, losing to 180B Qwen3.8-Flash-Next at 40 — BTA_Labs · 2026-10-23
- Gemini refuses to generate image in Docs, blames document size limit — viksit · 2026-10-23
- Dev jokes his true calling is telling everyone to try the latest DeepSeek — intellectronica · 2026-10-23
- SubQ Snap 1.1 ties for first on Artificial Analysis Decision Index with 384K context — ArtificialAnlys · 2026-10-23
- PolyAI unveils Dialog-RSN-1: audio-native voice model answering in under 300ms — matthen2 · 2026-10-23