In brief Researchers at Allameh Tabataba’i University found models behave differently depending on whether they act as a man or a woman. DeepSeek and Gemini became more risk-averse when prompted as women, echoing real-world behavioral patterns. OpenAI’s GPT models stayed neutral, while Meta’s Llama and xAI’s Grok produced inconsistent or reversed effects depending on the...
Subscribe to Updates
Subscribe to our newsletter and never miss our latest news
Subscribe my Newsletter for New Posts & tips Let's stay updated!