Block Unveils Dessa, a Full-Duplex Speech-Only Model Trained From Scratch With No Text
stochasticchasm · x · 2026-10-24
Block announced Dessa, a conversation model trained from scratch purely on human speech—no text, no pretrained models. Claimed as the first AI you can hold a realistic live full-duplex conversation with, it laughs mid-sentence at jokes and raises its voice on request, behaviors nobody explicitly taught. The team argues text-first voice AI discards emotion and nuance, and is inviting AI safety researchers to explore Dessa, with a waitlist open. Observers are curious how speech-only models compare on language learning, facts, and in-context learning.
More from Models
- Kimi K3.1 Pro vs GPT-6 Astra vs Opus 5.5: Building Star Trek's Enterprise D in Minecraft — Angaisb_ · 2026-10-24
- Kimi 3.1 Pro priced like Argon but scores like DeepSeek V4.1 Flash on meme 'Runescape Bench' — scaling01 · 2026-10-24
- Jon Barron details his workflow: Gemini runs experiments, drafts the paper, then rewrites in his style — jon_barron · 2026-10-24
- Users praise Gem Argon for cultural fluency: a frontier model that roots for you — sebkrier · 2026-10-24
- User says Opus silently downgraded to 4.8 mid-task, then told him to talk to people — natesiggard · 2026-10-24
- Suspicious new GitHub accounts reference Qwen4 in Alibaba T-Head repo PRs — brainExploded99 · 2026-10-24