llms.blog

Samsung's System LSI is using Claude Code to compress chip verification from weeks to days

Samsung’s chip unit used Claude Code to cut a month-long verification task to two days, with engineers still reviewing the output.

axc
axc
1 min
Samsung's System LSI is using Claude Code to compress chip verification from weeks to days

Written by

axc

More to read

  • Linus Torvalds Credits AI in Linux Kernel Commit After 24-Patch Driver Debug Session

    In a notable public milestone for AI-assisted systems programming, Linux creator Linus Torvalds credited an artificial intelligence model with doing the heavy analytical work during an intensive driver debugging session, allowing the model to author the commit message merged into the upstream kernel. The commit, titled drm/xe: Don't hand out the flat CCS storage as usable VRAM (commit 818bebeb63dd6bf5f4e07e145f6cdbace520a34c), resolves a memory allocation bug in the Intel Xe Direct Rendering Ma

    1 min

  • SGLang v0.5.18 Cuts LLM Cold Starts by 2.4x with Overlapped Weight Loading and CUDA Graph Capture

    The open-source LLM serving engine SGLang has released version 0.5.18, introducing an overlapped startup engine that significantly reduces cold-start latency for large language models, alongside communication kernel optimizations and expanded architecture support. Comprising 710 pull requests from 212 contributors, the release addresses operational overheads in LLM infrastructure where autoscaling, rolling cluster deployments, and worker node recovery frequently pay steep restart penalties. O

    1 min

  • Active RAG in Production: Dynamic Triggering, Forward-Looking Queries, and Interleaved Retrieval Architectures

    Standard Retrieval-Augmented Generation (RAG) relies on a static, single-shot execution model: the system takes a user prompt, executes a vector or hybrid search upfront, prepends the retrieved chunks into the prompt context, and executes autoregressive generation. While this pattern suffices for short question-answering workloads, it breaks down systematically in complex, long-horizon generation tasks such as comprehensive technical reports, multi-step agent trajectories, and iterative problem

    1 min