Aakash Gupta says teams are using Claude Code like a visual coworker by iterating via screenshots and feedback, but argues this is humans doing QA on a system that can QA itself.
The PMs screenshotting Claude Code outputs and saying "fix the alignment" five times are playing QA on a system that can QA itself.
The default workflow for anything visual: generate a slide, screenshot it, give feedback, screenshot again, give more feedback.
Five rounds of you
This finding is one of many signals tracked across Artificial Intelligence. The live feed updates every few hours with new expert voices, debates, and emerging ideas.
← Back to Artificial Intelligence