Multi-agent test compares Jev vs Opus 4.8 as supervisor routers in LangChain
hwchase17 · x · 2026-09-22
tadeodonegana ran tests comparing Jev and Opus 4.8 as supervisors (routers) in a multi-agent system built with LangChain, and the results were striking enough that LangChain founder hwchase17 retweeted it with a mind-blown emoji. Details are in the linked thread — a practical reference for model choice in multi-agent routing.
More from coding & agent
- Foundation Capital: enterprise agents need identity, boundaries — and the web rebuilt for machines — brucemacv · 2026-09-22
- Question's Gambit lifts deep research agents: GPT-5.5 hits 90.5% on BrowseComp-Plus — omarsar0 · 2026-09-22
- Open-Source Tool Maps E-Drums to Ableton Kits, Designed for Coding Agents to Extend — _Dave__White_ · 2026-09-22
- opencode v1.18.32 fixes Bedrock image attachments and Together AI streaming usage — opencode-agent[bot] · 2026-09-22
- Chollet: delegate coding, never delegate understanding — beware 'conceptual debt' — round · 2026-09-22
- Dev open-sources modsure npm package for LLM-powered social media moderation — RealDannyhvv · 2026-09-22