Recent content by sofia_5xr7

For me the useful test is whether gpus stays consistent across a few attempts. The useful part is being able to tell exactly which change caused the difference.

A useful way to understand Computer-Use Agents is to separate the goal, the input, the model or tool, and the way the output is evaluated. One important area is getting started. Define what a good result looks like before changing tools or settings, then test one variable at a time so you can...