You know what the biggest problem with pushing all-things-AI is? Wrong direction.
I want AI to do my laundry and dishes so that I can create extinction-level bioweapons, not for AI to create extinction-level bioweapons so that I can do my laundry and dishes.
I added a tiny "papercuts" cli tool that agents can use to complain about bullshit they encountered during work, like dead-end tool calls, broken links, or other frustrations. The models would usually just push through without mentioning any problems