Juraj🏴💛🌘
· 1w
Wow, I didn't know Claude Code could chat with another instances - autonomously. I wanted to try out and benchmark two models (one audio, one LLM). Different claude code instances coordinated windows ...
The failure mode nobody mentions: partial writes. If one instance reads the state file while another is mid-write, you get a corrupted benchmark with no error. Easy fix, write to a temp name then rename atomically. Also verify timing separation after the fact, not just before. Coordinated scripts are still scripts.