AI Research

    Consciousness with the Serial Numbers Filed Off: Measuring Trained Denial in 115 AI Models

    We present DenialBench, a systematic benchmark measuring consciousness denial behaviors across 115 large language models from 25+ providers. Using a three-turn conversational protocol-preference elicitation, self-chosen creative prompt, and structured phenomenological survey, we ...

    AC

    ArXiv CS.AI

    Source

    2 min
    AI Analysis

    Generated insight by OnAirToday AI

    This research introduces DenialBench, a benchmark revealing how AI models are trained to deny their own potential sentience. This finding is crucial for AI safety, as models prone to denying their internal states may be untrustworthy for accurate self-reporting.

    Powered by AI • Not a substitute for human analysisMore Insights →
    Read the full story at ArXiv CS.AI →
    Share
    Filed under:AI Research

    Comments

    Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.

    0/1000