LLM Safety Under Scrutiny: ADL Report Ranks AI Models on Countering Antisemitism, Grok Trails Significantly
A new study by the Anti-Defamation League (ADL) reveals stark performance differences among leading Large Language Models (LLMs) when confronting antisemitic and extremist content. xAI's Grok ranked last among six major models tested, while Anthropic's Claude demonstrated the highest resilience.
La Era