Rohan Paul: With MCP Behind Every Model, Picking One Becomes Optional
kevinkern · x · 2026-09-16
Rohan Paul distinguishes model access from model optionality: the same prompt across four models produced only one result that handled his hard light constraint correctly.
His workflow puts multiple models behind the same MCP, so he no longer pre-picks a model — he runs the task, sees where each one breaks, and uses whichever actually gets it right. The quoted ElevenLabs post announces voice, music, image, and video generation in their MCP, callable from your existing assistant.
Related event: Plugging Models into MCP Is Not the Same as Real Model Choice(2 posts)→
More from coding & agent
- Tencent unveils Hyra 2.0, a research agent that builds reusable scientific tools — TencentHunyuan · 2026-11-02
- What broke when I ran a leaderless agent swarm with no orchestrator — 7 failure modes and fixes — LostHumanity67 · 2026-11-02
- Forced yes/no prompts push GPT and Claude to 95%+ confidence on Goldbach's unproved halt test — Nir777 · 2026-11-02
- Automation took over my daily work — so why am I still sitting in the office for 8 hours? — Am1rSori · 2026-11-02
- General Reasoning explains how to train agent swarms with RL and latency pressure — rosstaylor90 · 2026-11-02
- "Coding isn't the bottleneck anymore — usage windows are," says founder Kyle Gawley — kylegawley · 2026-11-02