If the best AI models in the tech industry had superlatives, OpenAI’s GPT-4, backed by Microsoft, would be the best in math, Meta’s Llama 2 would be middle of the road, Anthropic’s Claude 2 would be the best to know its limits and Cohere AI would receive the best. title of most hallucinations and most likely wrong answers.
That’s according to a Thursday report from researchers at Arthur AI, a machine learning monitoring platform.
The research comes at a time when disinformation from artificial intelligence systems is being debated more than ever, amid a boom in generative AI ahead of the 2024 US presidential election.
It’s the first report “to take a comprehensive look at hallucination rates, rather than sort of…provide a single number that speaks to where they are on an LLM league table,” Adam Wenchel, co-founder and CEO of Arthur, told CNBC.
Español de Venezuela 
English 