"The model has no idea what its own biases are": designers on AI slop

petergyang · x · 2026-11-18

Sharing Ashley Xie's finding: "the model has no idea what its own biases are." Output that designers instantly recognize as AI slop is not obvious to LLMs themselves, so the fix is to name and counteract these biases in the prompt before building even starts, rather than expecting the model to avoid them on its own.

Original post →

More from coding & agent

coding & agent channel →