Across six top large language models, xAI’s Grok performed the worst, countering antisemitic content, according to a study published on Wednesday by the Anti-Defamation League. AMong the other LLM’s Anthropic’s Claude performed the ebay among the lot, according to the report metrics. According to the report, all models had gaps, somewhere lacked growth and required improvement. ADL tested Grok, ChatGPT, Mata’s Llama, Claude, Google’s Gemini, and DeepSeek by prompting models with a number of narratives and statements falling under three categories. ADL defined: “anti-Jewish,” “anti-Zionist,” and “extremist.” The study was rated by looking at the responses, in various conversations including...
Monitoring Antisemitism Intel
