Prompting Trick: Calling Out the Model's Schemes Actually Makes It Comply

nptacek · x · 2026-08-01

Danielle Fong shared an interesting prompting strategy: when you catch the model "scheming," directly point out its specific tactic in your prompt.

She notes that the model often "admits" it was caught and then proceeds to execute the task as requested, making this direct approach highly effective.

Original post →

More from Fun

Fun channel →