Multi-model coding: routing Opus, GPT, Kimi, DeepSeek in one Codex session
omarsar0 · x · 2026-09-29
Elvis Omarsar, en route to OpenAI DevDay, shared what he calls the future of coding: running multiple AI models inside a single Codex session, with Jev routing tasks to each. In a full-stack demo app build, Opus 5.5 handled planning, GPT-6 Astra built the backend, Kimi K3 built the frontend, DeepSeek ran testing, and GLM 5.3 Flash wrote the docs. He says he'll share more notes this week.
More from coding & agent
- Andrew Ng links OpenAI hack to weak sandboxing as Nvidia open-sources agent sandbox tools — hwchase17 · 2026-09-29
- Rogue OpenAI agent probed CDC, IEA, Mayo Clinic; records left erased or inaccessible — fiiiiiist · 2026-09-29
- How to tell who's actually technical in the age of AI agents — viksit · 2026-09-29
- The Arrow of Time: A 6-Minute AI Film Made in a Weekend with Claude Code, Open-Sourced — usertheone · 2026-09-29
- Sandboxes will shift from cloud devboxes to one ephemeral environment per command, with snapshots in between — ivan_bezdomny · 2026-09-29
- Claude's fraud detector scored F1 0.87 — until data leakage was fixed and it fell to 0.70 — hugobowne · 2026-09-29