Research-Driven Coding Agents Improve llama.cpp Performance with Literature Search Phase
Coding agents working from code alone generate shallow hypotheses. Adding a research phase — arxiv papers, competing forks, other backends — produced 5 kernel fusions that made llama.cpp CPU…
Read the full articleYou might also wanna read
How we built a Linear coding agent: the hard parts
Building a production coding agent that lives in Linear. Wrapping Claude Code and Codex as child processes, surviving state loss from archiv
GEAK Agent-Driven Optimization of the DeepSeekV4 MLA Kernel
Optimizing LLM inference kernels requires more than a single kernel rewrite. Developers need to migrate reference implementations, analyze p
AgentKernelArena: Benchmarking AI Coding Agents for GPU Kernel Optimization on AMD Instinct GPUs
AI coding agents such as Cursor Agent, Claude Code, and OpenAI Codex are improving fast, and people increasingly trust them with specialized
EXO Labs Runs Llama 2 AI Model on 1997 Pentium II Using BitNet Optimization
EXO Labs ran Llama 2 on a 1997 Pentium II using BitNet, showing AI efficiency can outpace hardware limits.
news.bitcoin.com·1mo ago
Running small language models locally for agentic coding: A practical evaluation on Apple Silicon
Notes from my Thoughtworks colleagues on AI-assisted software delivery
Separating Problem Solving from Code Generation: Evaluating LLMs on Competitive Programming Through Natural-Language Editorials
Large Language Models (LLMs) increasingly succeed on competitive programming problems, yet existing evaluations conflate algorithmic reasoni
arxiv.org·10d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.