Galileo, a provider developing generative AI for the enterprise, is releasing Galileo Luna, a suite of Evaluation Foundation Models (EFMs) designed to transform how generative AI evaluations are conducted.
“For GenAI to achieve mass adoption, it's crucial that enterprises can evaluate hundreds of thousands of AI responses for hallucinations, toxicity, security risk, and more, in real time,” said Vikram Chatterji, co-founder and CEO of Galileo. “In speaking with customers, we found that existing approaches, such as human evaluation or LLM-based evaluation, were too expensive and slow, so we set out to solve that. With Galileo Luna, we're setting new benchmarks for speed, accuracy, and cost efficiency. Luna can evaluate millions of responses per month 97% cheaper, 11x faster, and 18% more accurately than evaluating using OpenAI GPT-3.5.”
According to the company, this novel approach is faster, more cost-effective, and more accurate than existing evaluation methods such as askGPT and human “vibe checks.” With Galileo Luna, enterprises can bring trustworthy AI solutions to market faster and at production scale.
Core to Luna’s innovation is the creation of EFMs, which are the first models purpose built for generative AI evaluation. Each of these models has been fine-tuned to solve specific evaluation tasks, such as detecting hallucinations, context quality, data leakage, and malicious prompts. By creating smaller purpose built EFMs, Luna can conduct evaluations with never-before-seen accuracy, speed, and cost-efficiency.
Key Galileo Luna features include:
- Evaluation accuracy
- Ultra low-cost operations
- Millisecond speed
- No ground truth required
- Unmatched customizability
With its release, Luna is already integrated into all Galileo platforms, including the new Galileo Protect and Evaluate.
These tools utilize Luna’s capabilities to intercept harmful inputs, improve system security, and enhance operational efficiencies, according to the company.
For more information about this news, visit www.rungalileo.io.