Technology@lemmy.world•Being mean to AI could get you banned as Anthropic introduces new rules against abusing ClaudebyApocolypticGopher@infosec.pubEnglish2 daysIIRC a decent amount of researchers have been able to get the enterprise models to do things they shouldn’t by “being mean” to the AI. 26
IIRC a decent amount of researchers have been able to get the enterprise models to do things they shouldn’t by “being mean” to the AI.