LLMs are generating device kernels, debugging kernel subsystems, and acting as minimal coding agents. This shifts software maintenance toward AI-assisted development, especially for Linux and local inference stacks.
The kernel's removal of legacy Silicon Graphics drivers—mirrored by a surge of AI-generated patches—marks a shift in maintenance philosophy. For on-premise legacy hardware users, it raises hard questions about system longevity and the trustworthiness...
A user prompted DeepSeek to generate a Metal kernel to run the quantized Kimi K2 model on a Mac Studio, achieving modest performance but proving LLMs can bridge software gaps for self-hosted inference on non-Nvidia hardware. The case reshapes the TCO...
In 50 minutes, an LLM wrote the code to run a 90GB quantized model on a Mac Studio with no existing kernel. Modest performance, but enough to show that consumer hardware can become a credible alternative for local inference.
An open-source experiment demonstrates an essential coding agent: 9 lines of Python, standard library only, no external dependencies. It works with any OpenAI Responses-compatible API, uses a single sh tool, session-based caching, and shows context w...
Linux kernel 7.2-rc7 brings dozens of fixes to the hardware monitoring subsystem, mostly critical or high-severity bugs spotted by the Sashiko bot. It's the latest sign that LLM-based agents are accelerating defect discovery in foundational code, wit...
