LLM Evaluation Tooling Reimagined: Say Goodbye to Frustration and High Costs with de_valIn the ever-evolving landscape of AI development, the tools we use to track and evaluate LLMs play a crucial role in determining the…Feb 13Feb 13
de_val’s Evaluation API: Live and Ready for Beta Testing!While we’ve recently announced the exciting launch of our de_val Evaluation API, today we wanted to dive a little deeper and share more…Jan 23Jan 23
de_val Updates: Live API, Progress, and Where Do We Go From Here?At de_val, our mission is simple yet, we think, transformative: to elevate large language models (LLMs) to their peak performance with…Jan 6Jan 6
2024 LLM Evaluation Trends: Major Advancements and (Hilarious) Fails in AI DevelopmentWhat a YEAR. 2024 has marked a significant uptick in LLM-powered products across various sectors. These products have absolutely exploded…Dec 20, 2024Dec 20, 2024
Securing the Future of LLMs: How de_val Handles SecurityLet’s face it — navigating the world of decentralized AI submissions can sometimes feel like walking a tightrope. You’ve poured weeks into…Dec 12, 2024Dec 12, 2024
What Makes LLMs So Hard to Evaluate?Evaluating Large Language Models (LLMs) is incredibly challenging, and has continuously grown more complex as these models gain…Nov 27, 2024Nov 27, 2024
de_val v1.0: Setting the New Standard in LLM EvaluationAs the AI landscape continues to evolve, so must our methods for evaluating and improving LLMs. At de_val, we’re committed to pushing the…Nov 13, 2024Nov 13, 2024
Overcoming LLM Limitations: A New Approach to Evaluation with de_valAs AI continues to expand across industries, businesses face a critical challenge: how to trust their large language models (LLMs). With…Sep 12, 2024Sep 12, 2024
