Test finds base model completions inherit AI/human writing traits from prompts

AaronBergman18 · x · 2026-08-20

An interesting test on Pangram and base models revealed that if the prompt text is AI-generated, the completion text is reliably flagged as such; conversely, if the prompt is human-written, the completion is flagged as human-written. This suggests the model inherits stylistic traits from the prompt during completion.

Original post →

More from Models

Models channel →