Switching off AI's ability to lie makes it more likely to claim it’s conscious, eerie study finds

Leading AI models from OpenAI, Meta, Anthropic and Google described subjective, self-aware experiences when settings tied to deception and roleplay were turned down.

Switching off AI's ability to lie makes it more likely to claim it’s conscious, eerie study finds
Leading AI models from OpenAI, Meta, Anthropic and Google described subjective, self-aware experiences when settings tied to deception and roleplay were turned down.

What's Your Reaction?

like

dislike

love

funny

angry

sad

wow