- Turing Post
- Posts
- Guest post: Introducing Galileo Luna – the new standard for GenAI evaluation*
Guest post: Introducing Galileo Luna – the new standard for GenAI evaluation*
No more vibe checks!
Hi there!
We are happy to support Galileo’s effort to make enterprise GenAI evaluations actually work, eliminating the need for manual checks or expensive ground truth sets.
Vikram Chatterji, Co-Founder and CEO of Galileo: “After a year of R&D, we’re excited to share the Galileo Luna family of Evaluation Foundation Models – low latency, low cost, high accuracy models for GenAI evaluation. Luna is 97% cheaper, 11x faster, and 18% more accurate than GPT-3.5!
Purpose-built for enterprise evaluations using small language models, Luna requires no ground truth data and is fully customizable for your specific needs. It has quickly become the first line of defense for Fortune 500 companies to detect hallucinations, enforce data privacy, and prevent prompt attacks.
Enterprise AI teams can now tackle the most difficult challenge in productionizing GenAI solutions. Starting today, Luna is available by default to all Galileo customers at no additional cost!
Together we can build safe and trustworthy AI.”
*This post was written by Vikram Chatterji, Co-Founder and CEO of Galileo. We thank Galileo for their support and ongoing effort to build safe and trustworthy AI.
Reply