Comment by vidarh

Heh. For this specific task, if the output is the same quality or better per token output, it'd actually be positive, but I have plenty of tasks where extra verbosity would be undesirable as well, so I'll be keeping a close eye on this.

Currently has Opus running a comparative test of itself against Kimi K3 on one project, and it keeps finding that Kimi is competitive for multiple stages of the pipeline, so I may well end up reducing my use overall anyway...