Anthropic
September 17, 2024
Anthropic Unicorn News - September 17, 2024
Anthropic's AI model Claude 3.5 has outperformed its competitors in a recent safety evaluation by Chatterbox Labs, demonstrating superior performance in rejecting or redirecting harmful prompts across various safety metrics.
(
) Introduction(
) Anthropic's AI Model Claude 3.5 Excels in Safety Test