AI chatbots still can’t accurately answer high-level history questions: study
AI chatbots still can’t accurately answer high-level history questions: study 2025-01-20 at 16:53 By Ariel Zilber While artificial intelligence excels at tasks like coding and podcast generation, it struggles to accurately answer high-level history questions, according to a study. Researchers tested OpenAI’s GPT-4, Meta’s Llama and Google’s Gemini using a newly developed benchmark called Hist-LLM. […]
React to this headline:
AI chatbots still can’t accurately answer high-level history questions: study Read More »