🚀🤖 The launch of YandexGPT 2 excited the AI community and it surpassed even compared to GPT-4! Google conducted a study to evaluate the accuracy of Large Language Models (LLMs) with Search Engine Retrieval. 🌐🔍
📊 In the study, GPT-4 and ChatGPT were successful in solving questions with false assumptions. GPT-4 achieved 28% accuracy, while ChatGPT remained at 26%. PPLX.AI achieved 52% success. 📈🏆
🧪 In a new approach, a Google search was performed for each question and the results were included in the request. LLMs were required to “read” this information and then construct their answers. This allowed GPT-4 to achieve a 77% quality score. 🎯🌟
💬 Share your thoughts in the comments section and let's talk about these exciting developments in the world of AI! 🗨️👥