JEV decision model:剥离Agent高频小判断，省下大模型延迟与token费
大模型之路 · wechat · 2026-09-29
TypeSafe's JEV "decision model" goes viral by fixing a hidden cost mismatch in agents: most LLM calls are tiny classifications (routing, risk gating, scoring), not generation. JEV offers three question types — Noul (yes/no probability), Choice (up to 255 options), Score (continuous value) — computed in parallel from a state plus predefined questions, with a built-in confidence threshold for auto-execute vs. escalate. The article also covers APUS's MIT-licensed open-source reproduction fast-browser-use (local Qwen3.5-9B, single forward pass for element selection) since JEV is closed-source and unavailable in mainland China. Best for high-frequency, low-latency, finite-answer decisions; unsuitable where explainability is required.
Related event: TypeSafe's Jev: A Text-Free Decision Model That's Fast and Dirt Cheap(6 posts)→
More from coding & agent
- Setting /autocompact to 400k saved 29% of weekly Claude usage without hurting performance — rickasaurus · 2026-10-10
- Eazo hands-on: one-prompt apps with 6 design variants, Stripe payments, 50-70% referral cuts — vista8 · 2026-10-10
- Nested parallelism: running Hermes agents inside Grok bot VMs for compute offload — alexcovo_eth · 2026-10-10
- Brian Holt sold his 42U homelab — a Framework Desktop plus coding agents does more — film_girl · 2026-10-10
- Group-Evolving Agents wins COLM 2026 award, hits 71% on SWE-bench Verified — xwang_lk · 2026-10-10
- Asking an agent to fix a bug you don't understand is continuous paperclip maxxing — brandon_xyzw · 2026-10-10