Chinese AI Podcast Next Token Ep.3: Jev Paradigm, Small Judgments and Agent Workflows
vista8 · x · 2026-09-21
Next Token, a Chinese AI podcast co-hosted by Guizang, Juzi, Yang Pan and Xiangyang Qiaomu, released its third 100-minute episode (2,000+ subscribers). Main topics: the "Jev" paradigm of models doing high-frequency small judgments instead of chat — contact tagging, semantic search, ad filtering — and the distinction between type-constrained output and actual correctness; plus Agent deployment conditions: multitask screens, voice input, Codex multi-account workspaces, always-on agents, cloud Macs, and enterprise data boundaries. Also covers using GPT-6 Astra to generate training data for small models, multimodal understanding, quantized local models, and Vibe Coding's storage bloat.
Related event: Next Token Podcast Episode 3 Covers Jev Paradigm and Agent Workflows(2 posts)→
More from AGI Musings
- Debate: P(permanent human disempowerment) is basically 100%, says AI risk skeptic — StewartalsopIII · 2026-09-21
- Debate: what if utilitarian math proves median human life has negative value? — teortaxesTex · 2026-09-21
- UN panel warns AI safeguards can't wait for certainty as agents grow more capable — The Verge AI · 2026-09-21
- Ex-OpenAI alignment researcher Zoë Hitzig pens 'GPU's Lament' on AI suffering — borowcy · 2026-09-21
- "Claude now generates Zambia's entire GDP in a year" sparks debate on AI vs development — weskambale · 2026-09-21
- AI took your job — now it's your unpaid survival agent, argues viral essay — SparkyAI0815 · 2026-09-21