1/ Introducing the Patronus API: powerful AI evaluation models to accelerate your AI development 🚀 - 20% more accurate than ragas on hallucination detection - Beats Perspective and Llama Guard on safety tasks by 28% and 11% - Excels in practical domains like finance and customer support Hundreds of elite AI teams across companies like @hospitable, @ExaAILabs, and Algomo use Patronus to do alpha evals ⚡ Try it out today:

Llama Guard is Off Duty 😲 It’s weak at toxicity detection! We benchmarked popular toxicity datasets spanning languages like Portuguese, Ukrainian, and Turkish, and found that Llama Guard has a very high false negative rate for toxic content! We found that base models like Llama 3.1 do all the heavy lifting on toxicity filtering, and that the joint usage of Llama Guard might be redundant. 🤔 It’s time for a thread 🧵

Join @rebeccatqian, Sunitha Ravi, @cojennin, and @dennylee for our upcoming webinar on the creation of #Lynx, a state-of-the-art hallucination detection model from @PatronusAI on August 1, 2024 9:05am PT. #LLMs used in Retrieval Augmented Generation (#RAG) systems often produce hallucinations, which result in misinformation to the end user. Lynx outperforms GPT-4o, Claude-3.5-Sonnet, and other LLM-as-a-judge models, and excels in advanced reasoning across complex real-world domains like finance and medicine. We are excited to discuss the training and development of Lynx and share research findings