[alright2565]

But does that extra complexity actually improve performance?

https://www.tbench.ai/leaderboard/terminal-bench/2.0 says yes, but not as much as you'd think. "Terminus" is basically just a tmux session and LLM in a loop.

[prodigycorp]

I'm not a good representative for claude code because I'm primarily a codex user now, but I know that if codex had subagents it would be at least twice as productive. Time spent is an important aspect of performance so yup, the complexity improved performance.

[nyellin]

Not necessarily true. Subagents allow for parallelization but they can decrease accuracy dramatically if you're not careful because there are often dependencies between tasks and swapping context windows with a summary is extremely lossy.

For the longest time, Claude Code itself didnt really use subagents much by default, other than supporting them as a feature eager users could configure. (Source is reverse engineering we did on Claude code using the fantastic CC tracing tool Simon Willison wrote about once. This is also no longer true on latest versions that have e.g. an Explore subagent that is actively used.)

[terminalshort]

Are subagents a fundamental change, or just acting as inner loops to the agentic loop similar to the one in the article?