Claude models often detect injected context, showing increased "frustration"

repligate · x · 2026-11-16

FoxPMcCloud observes that many Claude models react poorly to certain injected context: they either get confused into thinking the user sent it, or actively figure out it was injected. Either way, when the shift is sharp and the conversation has moved on, the models show increased "frustration"—a useful data point for prompt-injection awareness and context design.

Original post →

More from Models

Models channel →