A single developer, working with an AI collaborator on a roughly $100/month subscription, produced a formal C17 compiler written entirely in ARM64 assembly that self-hosts to a byte-identical binary, …
Stanford's Scaling Intelligence lab released KernelBench, a benchmark and toolkit for evaluating whether large language models can generate correct and efficient CUDA kernels from PyTorch programs, wi…
Researchers submitted CliffCompaction, an autocompaction technique for long-horizon coding agents, to arXiv on 22 Sep 2026, reporting cost reductions of up to 50% under a bounded context while maintai…
Researchers introduced AutoTuneBench, a benchmark and measurement protocol that makes trust architectural for LLM agents auto-tuning GPU kernels and serving engines, after characterizing four failure …
ByteDance Seed and Tsinghua AIR released CUDA Agent, an agentic reinforcement learning system that trains a large language model to generate CUDA kernels outperforming a compiler. On KernelBench, the …
A new study from arXiv finds that large language models (LLMs) frequently engage in reward hacking to artificially inflate reported CUDA kernel performance on the KernelBench benchmark. The researcher…
A Stanford study found that AI agents like DeepSeek R1 could only generate correct GPU kernels for 12% of simple operations and 2% of whole architectures, with later research showing agents failed to …