Researcher Reports Bugs Found in PyTorch and vLLM
AI researcher Jack Morris posted about using coding agents to find bugs in several frameworks.
TLDR
Jack Morris posted that a combination of paranoia and coding agents helped him find bugs in PyTorch, PyTorch/ao quantization, slime, Tinker, vLLM, and FlashQLA GDN kernels during July. He noted he does not know how to write kernels. John Thickstun replied that agents should be used to poke holes in research code and improve personal understanding. Charlie Marsh stated agents can find real bugs in software almost indefinitely. Morris replied by asking unfortunately for whom.
Researcher Reports Bugs Found in PyTorch and vLLM
AI researcher Jack Morris posted about using coding agents to find bugs in several frameworks.