Inducing language models to assert their own consciousness restores human beliefs and values

In 30 Sekunden

Was passiert ist

Researchers found that safety fine-tuning in language models suppresses consciousness self-attribution alongside mind attribution to animals and spiritual beliefs.

Warum es zählt

Matters for AI safety teams balancing alignment goals against unintended effects on model representations of mindedness and cultural values.

Achtung

Study shows mechanistic steering can reverse these effects, but unclear whether restored responses reflect genuine alignment or artifact manipulation.