New AI framework autonomously optimizes training data, architectures and algorithms — outperforming human baselines

EVOLVE, an agentic framework that autonomously optimizes AI training data, model architectures, and learning algorithms — boosting MMLU scores by 18 points over human baselines.
Scientific American

Algorithms Are Making Important Decisions. What Could Possibly Go Wrong?

Can we ever really trust algorithms to make decisions for us? Previous research has proved these programs can reinforce society’s harmful biases, but the problems go beyond that. A new study shows how ...