Patronus AI, a NYC-based provider of an automated evaluation and security platform that helps companies use large language models (LLMs) safely, launched out of stealth with a $3m in seed funding.
The round was led by Lightspeed Venture Partners with participation from Factorial Capital, the CEO of Replit Amjad Masad, Gokul Rajaram and a number of other Fortune 500 executives and board members.
Founded by machine learning experts Anand Kannappan and Rebecca Qian, Patronus AI leverages proprietary AI to enable enterprise development teams to score model performance, generate adversarial test cases, benchmark models and more. The platform automates and scales the manual and costly model evaluation methods prevalent in the enterprise today, enabling organizations to deploy LLMs while minimizing the risk of model failures and misaligned outputs.
The system automates:
- Scoring: Scores model performance in real world scenarios and key criteria like hallucinations and safety.
- Test generation: Automatically generates adversarial test suites at scale.
- Benchmarking: Compares models to help customers identify the best model for specific use cases.
Early platform partners include leading AI companies, including Cohere, Nomic AI, and Naologic. Additionally, several high profile companies in traditional industries like financial services will be piloting Patronus AI in the coming months.
FinSMEs
14/09/2023