[ad_1]
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.
[ad_2]
Source link