AI startup Vectara's Hallucination Evaluation Model: OpenAI's LLMs had the lowest hallucination rates, followed by Meta's; Google's PaLM-Chat had the highest (Cade Metz/New York Times)

Cade Metz / New York Times:

AI startup Vectara's Hallucination Evaluation Model: OpenAI's LLMs had the lowest hallucination rates, followed by Meta's; Google's PaLM-Chat had the highest  —  When summarizing facts, ChatGPT technology makes things up about 3 percent of the time, according to research from a new start-up.

chat chatgpt evaluation facts google hallucination llms meta openai palm startup summarizing technology vectara