I’m realizing how often I say “we” (or the equivalent) instead of “I” when working on projects with an agent.
Instead of always saying “I want this” or “Here is my goal,” I’ll say things like “How might we do X?” or “Update the markdown file to make it easier for us to resume next session.”
I prompt for input and recommendations like I’m speaking to a human (e.g., “WDYT?”). I treat it like a colleague, not just a machine.
I suppose the reality is that it’s easier, since that’s how I work with colleagues. But I do wonder if this anthropomorphizing will have any lingering consequences.