AI system achieves 3.6x average speedup over human experts across all tested algorithms and GPU architectures, marking the arrival of Artificial Expert Intelligence

TEL AVIV, Israel: doubleAI today announced WarpSpeed, the first Artificial Expert system to autonomously surpass world-class human experts in GPU performance engineering. WarpSpeed rewrote and re-optimized every kernel in NVIDIA’s cuGraph library - one of the most widely used GPU-accelerated graph analytics libraries in the world - delivering a 3.6x average speedup over a decade of expert-tuned code. The hyper-optimized library is now available on GitHub as a drop-in replacement requiring no code changes.

Key Results

• 3.6x average speedup over human expert-written kernels
• 100% of algorithms tested run faster with WarpSpeed
• 55% of kernels achieve more than 2x improvement
• Validated across three GPU architectures: NVIDIA A100, L4, and A10G

Why This Matters

cuGraph has been built and continuously refined by some of the world’s top GPU performance engineers over roughly a decade. It spans dozens of graph algorithms, each hand-optimized for maximum throughput. WarpSpeed beat every single one of them - on every tested GPU.

While AI has earned headlines for winning gold medals at the International Mathematical Olympiad and outperforming top programmers on competitive coding platforms like CodeForces, those achievements share three hidden advantages: abundant training data, easy-to-verify solutions, and short reasoning chains. GPU performance engineering breaks all three assumptions simultaneously:

• Data scarcity: Only a few thousand truly optimized CUDA kernels exist publicly.
• Validation complexity: Correctness is hard to verify - multiple valid solutions exist, and simple diffs are insufficient.
• Deep reasoning chains: Optimal performance emerges from a long chain of interacting decisions - memory layout, warp behavior, caching strategy, scheduling, and graph structure.

Even state-of-the-art coding agents, including Claude Code, Codex, and Gemini CLI, fail dramatically in this domain - often producing incorrect implementations even when provided with cuGraph’s own test suite. In testing, leading coding agents produced buggy solutions in approximately 40% of tasks, making them unusable for real-world kernel replacement.

A New Paradigm: Artificial Expert Intelligence (AEI)

WarpSpeed represents the beginning of what doubleAI calls Artificial Expert Intelligence (AEI) - not Artificial General Intelligence (AGI), but something the world may need more urgently: AI systems that reliably surpass human experts in domains where expertise is rarest, slowest to develop, and most valuable.

“The real question isn’t ‘can AI code?’ - it’s ‘can AI become an expert?’” said Prof. Amnon Shashua, cofounder and CEO. “Humanity’s progress is bottlenecked by experts. If we can copy and paste expertise into the world, the impact is transformative.”

The Science Behind WarpSpeed

WarpSpeed’s results stem not from scaling alone, but from new algorithmic ideas developed by doubleAI’s research team:

• Diligent Learning: A method for efficiently searching in the space of ideas, enabling AI to navigate vast design spaces and converge on high-quality solutions even when training data is scarce.
• PAC Reasoning and Verification : A methodology for verifying correctness when ground truth is unavailable. Built on two components - Input Generation (IG), which finds challenging test inputs, and Automatic Validation (AV), which determines whether outputs are correct given a problem description. Grounded in the computational insight that verification is simpler than search, this approach allows AI to bootstrap reliable self-verification even in domains where it cannot yet solve the original problems.

These components create a flywheel: better verification engines produce better training data, which train stronger experts, which generate more sophisticated verification - and the cycle continues.

Availability

WarpSpeed-optimized cuGraph kernels are available today on GitHub at https://github.com/double-ai/doubleGraph . Users can install the optimized library with no changes to their existing code.

Looking Ahead

GPU hardware has long outpaced the software that runs on it. Every new architecture ships faster silicon, but the kernels and algorithms underneath lag behind - bottlenecked by the scarcity of engineers who can fully exploit it. WarpSpeed closes that gap: AI that keeps software in lockstep with hardware, unlocking the full potential of modern GPUs and opening the door to use cases that were previously out of reach.

cuGraph is a stress test. If AEI works in a domain where data is scarce, validation is hard, and the baselines are elite, then AEI can work wherever expertise is the bottleneck - from drug discovery and chip design to cybersecurity, robotics, and climate technology.

About doubleAI

doubleAI is a team of elite researchers spanning computer science, mathematics, physics, and biology, building transformative AI technology that drives new scientific discoveries. Rather than pursuing broader AGI, doubleAI focuses on Artificial Expert Intelligence (AEI) - a fundamentally new approach that enables AI to reason like true experts: searching the space of ideas, validating conclusions with precision, and sustaining long, rigorous chains of thought under uncertainty. The company’s mission is to remove humanity’s greatest bottleneck - access to real expertise - by building AI systems capable of rivaling and surpassing top human experts, beginning with some of the most technically demanding challenges in computing. doubleAI recently raised $200M in a Series A financing round co-led by Lightspeed Ventures and Bessemer Venture Partners. The investor group also includes Dell Technologies Capital, Greenfield, NVIDIA, Pitango, and BRM.

Links – WarpSpeed Technical blog ; WarpSpeed on GitHub ; Diligent Learning Paper ; PAC Reasoning Paper.

Fonte: Business Wire