alt Hacker NewsYes, all the major CLIs (Claude Code, Codex, etc) and many agentic applications use a large model main agent with task delegation to small model sub-agent. For example in CC using Opus4.5 it will delegate an Explore task to a Haiku/Sonnet subagent or multiple subagents.
The agent interfaces are for human interaction. Some tasks can be fully unattended though. For those, I find smaller models more capable due to their speed.
Think beyond interfaces. I'm talking about rapid-firing hundreds of small agents and having zero human interaction with them. The feedback is deterministic (non agentic) and automated too.