[KongchangAI]
Concept

Self-Awareness Hallucination

A phenomenon in which an AI model produces incorrect descriptions of its own capabilities, version or features, typically arising from mixed training data or a lack of metacognitive calibration.

Timeline (last 90 days)

Oct 21

The phenomenon of a model contradicting itself in descriptions of its own capabilities is called self-awareness hallucination, usually stemming from mixed training data and a lack of metacognitive calibration.

Unverified50%

All Facts (1)

Source Articles