NVIDIA Proved Evolutionary Code Search Beats Humans — Here's What an Open Protocol for It Looks Like

NVIDIA just published a paper that should make every software engineer pause. Their system — called AVO (Agentic Variation Operators) — ran autonomously for 7 days on a Blackwell B200 GPU, optimizing attention kernels with zero human intervention. The result: it outperformed NVIDIA's own cuDNN library by 3.5% and FlashAttention-4 by 10.5%. The researchers call their philosophy "blind coding." Bing Xu, one of the lead authors, puts it bluntly: "Blind coding is the future of software engineering. Human cognitive ability is the bottleneck." This is not the first time evolutionary code search has beaten humans. Google's AlphaEvolve did it for matrix multiplication and Ramsey number bounds last year. But AVO pushes the paradigm further — and both systems share a structural limitation that matters deeply for the future of this field. The Pattern: AlphaEvolve → AVO AlphaEvolve (2025) and AVO (2026) follow the same evolutionary template: Represent code as evolvable units — candidate solutions