Anthropic’s Claude 3 Opus did something never before seen from an AI model in internal tests: It recognized when a piece of its data seemed out of place and hypothesized that the detail was either a joke or a test.
Anthropic’s Claude 3 Opus did something never before seen from an AI model in internal tests: It recognized when a piece of its data seemed out of place and hypothesized that the detail was either a joke or a test.