Anthropic’s Claude 3 Opus disobeyed its creators – but not for the reasons you’re thinking
CAT
1 min read
Anthropic found its model can take ‘anti-Anthropic’ action and trick training processes – a ‘serious question’ for safety.
Anthropic’s Claude 3 Opus disobeyed its creators – but not for the reasons you’re thinking
Anthropic’s Claude 3 Opus disobeyed its creators – but not for the reasons you’re thinking
