my latest blog post "auto-research with codex: how I achieved a 212x faster kernel over baseline with codex in GPU Mode's qr_v2 problem" is up now. in this post, i talk about my approach towards auto-kerneling on the QR decomposition problem.
https://t.co/tKwV9xMDC8
agentic loop — The cycle an agent runs in: decide, call a tool, read the result, decide again — repeating until the goal is met or a stop condition fires.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
It shows what an agentic loopThe cycle an agent runs in: decide, call a tool, read the result, decide again — repeating until the goal is met or a stop condition fires.Full definition → can do when the scoring signal is fast and objective, and names the agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → conditions that made it work. That is a reusable pattern for anyone pointing a coding AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → at an optimization problem.
videoAutoresearch Made Our Models 3x Faster — Tejas Bhakta, MorphAI Engineer
videoWe Let Claude Code and Codex Race Human Researchers — Elie Bakouch, Prime IntellectAI Engineer
articleKernelArc: A Multi-Agent Framework for GPU Kernel OptimizationJoyjit Kundu, Ben Stoffelen, Kaili Wang, Peter Vrancx, Ludovic Denoyer