NVIDIA and Stanford Challenge Jev With CLM, a System 1 Architecture Up to 9x Faster
wschroll · x · 2026-09-26
NVIDIA and Stanford released the Contrastive Language Model (CLM), a System 1 architecture running up to 9x faster for small repeated decisions. The post also catalogs the wild Jev ecosystem: a live-trading bot deciding per 300ms Monad block (1.9k stars), a browser agent where Jev picks every click (16.7k stars), and a Chocolate Doom agent making tactical calls each frame.
More from coding & agent
- Stripe launches claimable sandboxes: frictionless payment integrations for AI agents — jeff_weinstein · 2026-11-12
- Databricks launches autonomous AI coworker Genie: 91% on enterprise tasks with half the tokens — Yuchenj_UW · 2026-11-12
- Loom founder launches Roma 2.0, a shared to-do list that orchestrates AI agents — thetripathi58 · 2026-11-12
- Developer proposes a 'blast radius' test for AI agents before building — Few-Garlic2725 · 2026-11-12
- Sosumi Eval: Apple Docs Access Lifts Coding Agent Pass Rates from ~33% to 94-98% — JordanMorgan10 · 2026-11-12
- CypherGuard fixes structurally wrong LLM Cypher queries, hitting 88.5% on CypherBench — JeremyCMorgan · 2026-11-12